specification/cognitiveservices/data-plane/AzureOpenAI/inference/preview/2024-09-01-preview/inference.yaml

openapi: 3.0.0 info: title: Azure OpenAI Service API description: Azure OpenAI APIs for completions and search version: 2024-09-01-preview servers: - url: https://{endpoint}/openai variables: endpoint: default: your-resource-name.openai.azure.com security: - bearer: - api.read - apiKey: [] paths: /deployments/{deployment-id}/completions: post: summary: Creates a completion for the provided prompt, parameters and chosen model. operationId: Completions_Create parameters: - in: path name: deployment-id required: true schema: type: string example: davinci description: Deployment id of the model which was deployed. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version requestBody: required: true content: application/json: schema: $ref: "#/components/schemas/createCompletionRequest" example: prompt: |- Negate the following sentence.The price for bubblegum increased on thursday. Negated Sentence: max_tokens: 50 responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/createCompletionResponse" example: model: davinci object: text_completion id: cmpl-4509KAos68kxOqpE2uYGw81j6m7uo created: 1637097562 choices: - index: 0 text: The price for bubblegum decreased on thursday. logprobs: null finish_reason: stop headers: apim-request-id: description: Request ID for troubleshooting purposes schema: type: string default: description: Service unavailable content: application/json: schema: $ref: "#/components/schemas/errorResponse" headers: apim-request-id: description: Request ID for troubleshooting purposes schema: type: string /deployments/{deployment-id}/embeddings: post: summary: Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms. operationId: embeddings_create parameters: - in: path name: deployment-id required: true schema: type: string example: ada-search-index-v1 description: The deployment id of the model which was deployed. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version requestBody: required: true content: application/json: schema: type: object additionalProperties: true properties: input: description: |- Input text to get embeddings for, encoded as a string. To get embeddings for multiple inputs in a single request, pass an array of strings. Each input must not exceed 2048 tokens in length. Unless you are embedding code, we suggest replacing newlines (\n) in your input with a single space, as we have observed inferior results when newlines are present. oneOf: - type: string default: "" example: This is a test. nullable: true - type: array minItems: 1 maxItems: 2048 items: type: string minLength: 1 example: This is a test. nullable: false user: description: A unique identifier representing your end-user, which can help monitoring and detecting abuse. type: string nullable: false input_type: description: input type of embedding search to use type: string example: query encoding_format: description: The format to return the embeddings in. Can be either `float` or `base64`. Defaults to `float`. type: string example: base64 nullable: true dimensions: description: The number of dimensions the resulting output embeddings should have. Only supported in `text-embedding-3` and later models. type: integer example: 1 nullable: true required: - input responses: "200": description: OK content: application/json: schema: type: object properties: object: type: string model: type: string data: type: array items: type: object properties: index: type: integer object: type: string embedding: type: array items: type: number required: - index - object - embedding usage: type: object properties: prompt_tokens: type: integer total_tokens: type: integer required: - prompt_tokens - total_tokens required: - object - model - data - usage x-ms-examples: Create a embeddings.: $ref: ./examples/embeddings.yaml /deployments/{deployment-id}/chat/completions: post: summary: Creates a completion for the chat message operationId: ChatCompletions_Create parameters: - in: path name: deployment-id required: true schema: type: string description: Deployment id of the model which was deployed. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version requestBody: required: true content: application/json: schema: $ref: "#/components/schemas/createChatCompletionRequest" responses: "200": description: OK content: application/json: schema: oneOf: - $ref: "#/components/schemas/createChatCompletionResponse" - $ref: "#/components/schemas/createChatCompletionStreamResponse" headers: apim-request-id: description: Request ID for troubleshooting purposes schema: type: string default: description: Service unavailable content: application/json: schema: $ref: "#/components/schemas/errorResponse" headers: apim-request-id: description: Request ID for troubleshooting purposes schema: type: string x-ms-examples: Create a chat completion.: $ref: ./examples/chat_completions.yaml Creates a completion based on Azure Search data and system-assigned managed identity.: $ref: ./examples/chat_completions_azure_search_minimum.yaml Creates a completion based on Azure Search image vector data.: $ref: ./examples/chat_completions_azure_search_image_vector.yaml Creates a completion based on Azure Search vector data, previous assistant message and user-assigned managed identity.: $ref: ./examples/chat_completions_azure_search_advanced.yaml Creates a completion for the provided Azure Cosmos DB.: $ref: ./examples/chat_completions_cosmos_db.yaml Creates a completion for the provided Mongo DB.: $ref: ./examples/chat_completions_mongo_db.yaml Creates a completion for the provided Elasticsearch.: $ref: ./examples/chat_completions_elasticsearch.yaml Creates a completion for the provided Pinecone resource.: $ref: ./examples/chat_completions_pinecone.yaml /deployments/{deployment-id}/audio/transcriptions: post: summary: Transcribes audio into the input language. operationId: Transcriptions_Create parameters: - in: path name: deployment-id required: true schema: type: string example: whisper description: Deployment id of the whisper model. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version requestBody: required: true content: multipart/form-data: schema: $ref: "#/components/schemas/createTranscriptionRequest" responses: "200": description: OK content: application/json: schema: oneOf: - $ref: "#/components/schemas/audioResponse" - $ref: "#/components/schemas/audioVerboseResponse" text/plain: schema: type: string description: Transcribed text in the output format (when response_format was one of text, vtt or srt). x-ms-examples: Create an audio transcription with json response format.: $ref: ./examples/audio_transcription_object.yaml Create an audio transcription with text response format.: $ref: ./examples/audio_transcription_text.yaml /deployments/{deployment-id}/audio/translations: post: summary: Transcribes and translates input audio into English text. operationId: Translations_Create parameters: - in: path name: deployment-id required: true schema: type: string example: whisper description: Deployment id of the whisper model which was deployed. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version requestBody: required: true content: multipart/form-data: schema: $ref: "#/components/schemas/createTranslationRequest" responses: "200": description: OK content: application/json: schema: oneOf: - $ref: "#/components/schemas/audioResponse" - $ref: "#/components/schemas/audioVerboseResponse" text/plain: schema: type: string description: Transcribed text in the output format (when response_format was one of text, vtt or srt). x-ms-examples: Create an audio translation with json response format.: $ref: ./examples/audio_translation_object.yaml Create an audio translation with text response format.: $ref: ./examples/audio_translation_text.yaml /deployments/{deployment-id}/audio/speech: post: summary: Generates audio from the input text. operationId: Speech_Create parameters: - in: path name: deployment-id required: true schema: type: string example: tts-1 description: Deployment id of the tts model which was deployed. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version requestBody: required: true content: multipart/form-data: schema: $ref: "#/components/schemas/createSpeechRequest" responses: "200": description: OK content: application/octet-stream: schema: type: string format: binary x-ms-examples: Create an audio from text with response format mp3.: $ref: ./examples/audio_speech.yaml /deployments/{deployment-id}/images/generations: post: summary: Generates a batch of images from a text caption on a given DALLE model deployment operationId: ImageGenerations_Create requestBody: required: true content: application/json: schema: $ref: "#/components/schemas/imageGenerationsRequest" parameters: - in: path name: deployment-id required: true schema: type: string example: dalle-deployment description: Deployment id of the dalle model which was deployed. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version responses: "200": description: Ok content: application/json: schema: $ref: "#/components/schemas/generateImagesResponse" default: description: An error occurred. content: application/json: schema: $ref: "#/components/schemas/dalleErrorResponse" x-ms-examples: Create an image.: $ref: ./examples/image_generation.yaml /assistants: get: operationId: List_Assistants tags: - Assistants summary: Returns a list of assistants. parameters: - name: limit in: query description: &pagination_limit_param_description | A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20. required: false schema: type: integer default: 20 - name: order in: query description: &pagination_order_param_description | Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order. schema: type: string default: desc enum: - asc - desc x-ms-enum: name: ListAssistantsOrder modelAsString: true values: - value: asc description: Order results in ascending order - value: desc description: Order results in descending order - name: after in: query description: &pagination_after_param_description | A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list. schema: type: string - name: before in: query description: &pagination_before_param_description | A cursor for use in pagination. `before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list. schema: type: string - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/listAssistantsResponse" x-ms-examples: Create an image.: $ref: ./examples/list_assistants.yaml post: operationId: Create_Assistant tags: - Assistants summary: Create an assistant with a model and instructions. parameters: - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version requestBody: required: true content: application/json: schema: $ref: "#/components/schemas/createAssistantRequest" responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/assistantObject" x-ms-examples: Create an assistant.: $ref: ./examples/create_assistant.yaml /assistants/{assistant_id}: get: operationId: Get_Assistant tags: - Assistants summary: Retrieves an assistant. parameters: - in: path name: assistant_id required: true schema: type: string description: The ID of the assistant to retrieve. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/assistantObject" x-ms-examples: Create an assistant.: $ref: ./examples/retrieve_assistant.yaml post: operationId: Modify_Assistant tags: - Assistant summary: Modifies an assistant. parameters: - in: path name: assistant_id required: true schema: type: string description: The ID of the assistant to modify. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version requestBody: required: true content: application/json: schema: $ref: "#/components/schemas/modifyAssistantRequest" responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/assistantObject" x-ms-examples: Create an assistant.: $ref: ./examples/modify_assistant.yaml delete: operationId: Delete_Assistant tags: - Assistants summary: Delete an assistant. parameters: - in: path name: assistant_id required: true schema: type: string description: The ID of the assistant to delete. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/deleteAssistantResponse" x-ms-examples: Create an assistant.: $ref: ./examples/delete_assistant.yaml /threads: post: operationId: Create_Thread tags: - Assistants summary: Create a thread. parameters: - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version requestBody: required: true content: application/json: schema: $ref: "#/components/schemas/createThreadRequest" responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/threadObject" x-ms-examples: Create a thread.: $ref: ./examples/create_thread.yaml /threads/{thread_id}: get: operationId: Get_Thread tags: - Assistants summary: Retrieves a thread. parameters: - in: path name: thread_id required: true schema: type: string description: The ID of the thread to retrieve. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/threadObject" x-ms-examples: Create a thread.: $ref: ./examples/retrieve_thread.yaml post: operationId: Modify_Thread tags: - Assistants summary: Modifies a thread. parameters: - in: path name: thread_id required: true schema: type: string description: The ID of the thread to modify. Only the `metadata` can be modified. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version requestBody: required: true content: application/json: schema: $ref: "#/components/schemas/modifyThreadRequest" responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/threadObject" x-ms-examples: Modify a thread.: $ref: ./examples/modify_thread.yaml delete: operationId: Delete_Thread tags: - Assistants summary: Delete a thread. parameters: - in: path name: thread_id required: true schema: type: string description: The ID of the thread to delete. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/deleteThreadResponse" x-ms-examples: Delete a thread.: $ref: ./examples/delete_thread.yaml /threads/{thread_id}/messages: get: operationId: List_Messages tags: - Assistants summary: Returns a list of messages for a given thread. parameters: - in: path name: thread_id required: true schema: type: string description: The ID of the [thread](/docs/api-reference/threads) the messages belong to. - name: limit in: query description: *pagination_limit_param_description required: false schema: type: integer default: 20 - name: order in: query description: | Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order. schema: type: string default: desc enum: - asc - desc x-ms-enum: name: ListMessagesOrder modelAsString: true values: - value: asc description: Order results in ascending order - value: desc description: Order results in descending order - name: after in: query description: | A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list. schema: type: string - name: before in: query description: | A cursor for use in pagination. `before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list. schema: type: string - name: run_id in: query description: | Filter messages by the run ID that generated them. schema: type: string - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/listMessagesResponse" x-ms-examples: List messages.: $ref: ./examples/list_messages.yaml post: operationId: Create_Message tags: - Assistants summary: Create a message. parameters: - in: path name: thread_id required: true schema: type: string description: The ID of the [thread](/docs/api-reference/threads) to create a message for. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version requestBody: required: true content: application/json: schema: $ref: "#/components/schemas/createMessageRequest" responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/messageObject" x-ms-examples: Create a message.: $ref: ./examples/create_message.yaml /threads/{thread_id}/messages/{message_id}: get: operationId: Get_Message tags: - Assistants summary: Retrieve a message. parameters: - in: path name: thread_id required: true schema: type: string description: The ID of the [thread](/docs/api-reference/threads) to which this message belongs. - in: path name: message_id required: true schema: type: string description: The ID of the message to retrieve. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/messageObject" x-ms-examples: Retrieve a message.: $ref: ./examples/get_message.yaml post: operationId: Modify_Message tags: - Assistants summary: Modifies a message. parameters: - in: path name: thread_id required: true schema: type: string description: The ID of the thread to which this message belongs. - in: path name: message_id required: true schema: type: string description: The ID of the message to modify. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version requestBody: required: true content: application/json: schema: $ref: "#/components/schemas/modifyMessageRequest" responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/messageObject" x-ms-examples: Modify a message.: $ref: ./examples/modify_message.yaml /threads/runs: post: operationId: Create_Thread_And_Run tags: - Assistants summary: Create a thread and run it in one request. parameters: - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version requestBody: required: true content: application/json: schema: $ref: "#/components/schemas/createThreadAndRunRequest" responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/runObject" x-ms-examples: Create a thread and run it.: $ref: ./examples/create_thread_and_run.yaml /threads/{thread_id}/runs: get: operationId: List_Runs tags: - Assistants summary: Returns a list of runs belonging to a thread. parameters: - name: thread_id in: path required: true schema: type: string description: The ID of the thread the run belongs to. - name: limit in: query description: *pagination_limit_param_description required: false schema: type: integer default: 20 - name: order in: query description: *pagination_order_param_description schema: type: string default: desc enum: - asc - desc x-ms-enum: name: ListRunsOrder modelAsString: true values: - value: asc description: Order results in ascending order - value: desc description: Order results in descending order - name: after in: query description: *pagination_after_param_description schema: type: string - name: before in: query description: *pagination_before_param_description schema: type: string - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/listRunsResponse" x-ms-examples: List runs.: $ref: ./examples/list_runs.yaml post: operationId: Create_Run tags: - Assistants summary: Create a run. parameters: - in: path name: thread_id required: true schema: type: string description: The ID of the thread to run. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version requestBody: required: true content: application/json: schema: $ref: "#/components/schemas/createRunRequest" responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/runObject" x-ms-examples: Create a run.: $ref: ./examples/create_run.yaml /threads/{thread_id}/runs/{run_id}: get: operationId: Get_Run tags: - Assistants summary: Retrieves a run. parameters: - in: path name: thread_id required: true schema: type: string description: The ID of the [thread](/docs/api-reference/threads) that was run. - in: path name: run_id required: true schema: type: string description: The ID of the run to retrieve. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/runObject" x-ms-examples: Retrieve a run.: $ref: ./examples/get_run.yaml post: operationId: Modify_Run tags: - Assistants summary: Modifies a run. parameters: - in: path name: thread_id required: true schema: type: string description: The ID of the [thread](/docs/api-reference/threads) that was run. - in: path name: run_id required: true schema: type: string description: The ID of the run to modify. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version requestBody: required: true content: application/json: schema: $ref: "#/components/schemas/modifyRunRequest" responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/runObject" x-ms-examples: Modify a run.: $ref: ./examples/modify_run.yaml /threads/{thread_id}/runs/{run_id}/submit_tool_outputs: post: operationId: Submit_Tool_Outputs_To_Run tags: - Assistants summary: | When a run has the `status: "requires_action"` and `required_action.type` is `submit_tool_outputs`, this endpoint can be used to submit the outputs from the tool calls once they're all completed. All outputs must be submitted in a single request. parameters: - in: path name: thread_id required: true schema: type: string description: The ID of the [thread](/docs/api-reference/threads) to which this run belongs. - in: path name: run_id required: true schema: type: string description: The ID of the run that requires the tool output submission. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version requestBody: required: true content: application/json: schema: $ref: "#/components/schemas/submitToolOutputsRunRequest" responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/runObject" x-ms-examples: Submit tool outputs to a run.: $ref: ./examples/submit_tool_outputs_to_run.yaml /threads/{thread_id}/runs/{run_id}/cancel: post: operationId: Cancel_Run tags: - Assistants summary: Cancels a run that is `in_progress`. parameters: - in: path name: thread_id required: true schema: type: string description: The ID of the thread to which this run belongs. - in: path name: run_id required: true schema: type: string description: The ID of the run to cancel. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/runObject" x-ms-examples: Cancel a run.: $ref: ./examples/cancel_run.yaml /threads/{thread_id}/runs/{run_id}/steps: get: operationId: List_Run_Steps tags: - Assistants summary: Returns a list of run steps belonging to a run. parameters: - name: thread_id in: path required: true schema: type: string description: The ID of the thread the run and run steps belong to. - name: run_id in: path required: true schema: type: string description: The ID of the run the run steps belong to. - name: limit in: query description: *pagination_limit_param_description required: false schema: type: integer default: 20 - name: order in: query description: *pagination_order_param_description schema: type: string default: desc enum: - asc - desc x-ms-enum: name: ListRunStepsOrder modelAsString: true values: - value: asc description: Order results in ascending order - value: desc description: Order results in descending order - name: after in: query description: *pagination_after_param_description schema: type: string - name: before in: query description: *pagination_before_param_description schema: type: string - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/listRunStepsResponse" x-ms-examples: List run steps.: $ref: ./examples/list_run_steps.yaml /threads/{thread_id}/runs/{run_id}/steps/{step_id}: get: operationId: Get_Run_Step tags: - Assistants summary: Retrieves a run step. parameters: - in: path name: thread_id required: true schema: type: string description: The ID of the thread to which the run and run step belongs. - in: path name: run_id required: true schema: type: string description: The ID of the run to which the run step belongs. - in: path name: step_id required: true schema: type: string description: The ID of the run step to retrieve. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/runStepObject" x-ms-examples: Retrieve a run step.: $ref: ./examples/get_run_step.yaml /vector_stores: get: operationId: List_Vector_Stores tags: - Vector Stores summary: Returns a list of vector stores. parameters: - name: limit in: query description: *pagination_limit_param_description required: false schema: type: integer default: 20 - name: order in: query description: *pagination_order_param_description schema: type: string default: desc enum: ["asc", "desc"] x-ms-enum: name: ListVectorStoresOrder modelAsString: true values: - value: asc - value: desc - name: after in: query description: *pagination_after_param_description schema: type: string - name: before in: query description: *pagination_before_param_description schema: type: string - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/listVectorStoresResponse" x-ms-examples: List vector stores.: $ref: ./examples/list_vector_stores.yaml post: operationId: Create_Vector_Store tags: - Vector Stores summary: Create a vector store. requestBody: required: true content: application/json: schema: $ref: "#/components/schemas/createVectorStoreRequest" parameters: - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/vectorStoreObject" x-ms-examples: Create a vector store.: $ref: ./examples/create_vector_store.yaml /vector_stores/{vector_store_id}: get: operationId: Get_Vector_Store tags: - Vector Stores summary: Retrieves a vector store. parameters: - in: path name: vector_store_id required: true schema: type: string description: The ID of the vector store to retrieve. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/vectorStoreObject" x-ms-examples: Retrieve a vector store.: $ref: ./examples/retrieve_vector_store.yaml post: operationId: Modify_Vector_Store tags: - Vector Stores summary: Modifies a vector store. parameters: - in: path name: vector_store_id required: true schema: type: string description: The ID of the vector store to modify. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version requestBody: required: true content: application/json: schema: $ref: "#/components/schemas/updateVectorStoreRequest" responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/vectorStoreObject" x-ms-examples: Modify a vector store.: $ref: ./examples/modify_vector_store.yaml delete: operationId: Delete_Vector_Store tags: - Vector Stores summary: Delete a vector store. parameters: - in: path name: vector_store_id required: true schema: type: string description: The ID of the vector store to delete. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/deleteVectorStoreResponse" x-ms-examples: Delete a vector store.: $ref: ./examples/delete_vector_store.yaml /vector_stores/{vector_store_id}/files: get: operationId: List_Vector_Store_Files tags: - Vector Stores summary: Returns a list of vector store files. parameters: - name: vector_store_id in: path description: The ID of the vector store that the files belong to. required: true schema: type: string - name: limit in: query description: *pagination_limit_param_description required: false schema: type: integer default: 20 - name: order in: query description: *pagination_order_param_description schema: type: string default: desc enum: ["asc", "desc"] x-ms-enum: name: ListVectorStoreFilesOrder modelAsString: true values: - value: asc - value: desc - name: after in: query description: *pagination_after_param_description schema: type: string - name: before in: query description: *pagination_before_param_description schema: type: string - name: filter in: query description: "Filter by file status. One of `in_progress`, `completed`, `failed`, `cancelled`." schema: type: string enum: ["in_progress", "completed", "failed", "cancelled"] x-ms-enum: name: ListVectorStoreFilesFilter modelAsString: true values: - value: in_progress - value: completed - value: failed - value: cancelled - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/listVectorStoreFilesResponse" x-ms-examples: List vector store files.: $ref: ./examples/list_vector_store_files.yaml post: operationId: Create_Vector_Store_File tags: - Vector Stores summary: Create a vector store file by attaching a [File](/docs/api-reference/files) to a [vector store](/docs/api-reference/vector-stores/object). parameters: - in: path name: vector_store_id required: true schema: type: string example: vs_abc123 description: | The ID of the vector store for which to create a File. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version requestBody: required: true content: application/json: schema: $ref: "#/components/schemas/createVectorStoreFileRequest" responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/vectorStoreFileObject" x-ms-examples: Create a vector store file.: $ref: ./examples/create_vector_store_file.yaml /vector_stores/{vector_store_id}/files/{file_id}: get: operationId: Get_Vector_Store_File tags: - Vector Stores summary: Retrieves a vector store file. parameters: - in: path name: vector_store_id required: true schema: type: string example: vs_abc123 description: The ID of the vector store that the file belongs to. - in: path name: file_id required: true schema: type: string example: file-abc123 description: The ID of the file being retrieved. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/vectorStoreFileObject" x-ms-examples: Retrieve a vector store file.: $ref: ./examples/retrieve_vector_store_file.yaml delete: operationId: Delete_Vector_Store_File tags: - Vector Stores summary: Delete a vector store file. This will remove the file from the vector store but the file itself will not be deleted. To delete the file, use the [delete file](/docs/api-reference/files/delete) endpoint. parameters: - in: path name: vector_store_id required: true schema: type: string description: The ID of the vector store that the file belongs to. - in: path name: file_id required: true schema: type: string description: The ID of the file to delete. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/deleteVectorStoreFileResponse" x-ms-examples: Delete a vector store file.: $ref: ./examples/delete_vector_store_file.yaml /vector_stores/{vector_store_id}/file_batches: post: operationId: Create_Vector_Store_File_Batch tags: - Vector Stores summary: Create a vector store file batch. parameters: - in: path name: vector_store_id required: true schema: type: string example: vs_abc123 description: | The ID of the vector store for which to create a File Batch. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version requestBody: required: true content: application/json: schema: $ref: "#/components/schemas/createVectorStoreFileBatchRequest" responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/vectorStoreFileBatchObject" x-ms-examples: Create a vector store file batch.: $ref: ./examples/create_vector_store_file_batch.yaml /vector_stores/{vector_store_id}/file_batches/{batch_id}: get: operationId: Get_Vector_Store_File_Batch tags: - Vector Stores summary: Retrieves a vector store file batch. parameters: - in: path name: vector_store_id required: true schema: type: string example: vs_abc123 description: The ID of the vector store that the file batch belongs to. - in: path name: batch_id required: true schema: type: string example: vsfb_abc123 description: The ID of the file batch being retrieved. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/vectorStoreFileBatchObject" x-ms-examples: Retrieve a vector store file batch.: $ref: ./examples/retrieve_vector_store_file_batch.yaml /vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel: post: operationId: Cancel_Vector_Store_File_Batch tags: - Vector Stores summary: Cancel a vector store file batch. This attempts to cancel the processing of files in this batch as soon as possible. parameters: - in: path name: vector_store_id required: true schema: type: string description: The ID of the vector store that the file batch belongs to. - in: path name: batch_id required: true schema: type: string description: The ID of the file batch to cancel. - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/vectorStoreFileBatchObject" x-ms-examples: Cancel a vector store file batch.: $ref: ./examples/cancel_vector_store_file_batch.yaml /vector_stores/{vector_store_id}/file_batches/{batch_id}/files: get: operationId: List_Vector_Store_File_Batch_Files tags: - Vector Stores summary: Returns a list of vector store files in a batch. parameters: - name: vector_store_id in: path description: The ID of the vector store that the files belong to. required: true schema: type: string - name: batch_id in: path description: The ID of the file batch that the files belong to. required: true schema: type: string - name: limit in: query description: *pagination_limit_param_description required: false schema: type: integer default: 20 - name: order in: query description: *pagination_order_param_description schema: type: string default: desc enum: ["asc", "desc"] x-ms-enum: name: ListVectorStoreFilesOrder modelAsString: true values: - value: asc - value: desc - name: after in: query description: *pagination_after_param_description schema: type: string - name: before in: query description: *pagination_before_param_description schema: type: string - name: filter in: query description: "Filter by file status. One of `in_progress`, `completed`, `failed`, `cancelled`." schema: type: string enum: ["in_progress", "completed", "failed", "cancelled"] x-ms-enum: name: ListVectorStoreFilesFilter modelAsString: true values: - value: in_progress - value: completed - value: failed - value: cancelled - in: query name: api-version required: true schema: type: string example: 2024-09-01-preview description: api version responses: "200": description: OK content: application/json: schema: $ref: "#/components/schemas/listVectorStoreFilesResponse" x-ms-examples: List vector store files in a batch.: $ref: ./examples/list_vector_store_file_batch.yaml components: schemas: errorResponse: type: object properties: error: $ref: "#/components/schemas/error" errorBase: type: object properties: code: type: string message: type: string error: type: object allOf: - $ref: "#/components/schemas/errorBase" properties: param: type: string type: type: string inner_error: $ref: "#/components/schemas/innerError" innerError: description: Inner error with additional details. type: object properties: code: $ref: "#/components/schemas/innerErrorCode" content_filter_results: $ref: "#/components/schemas/contentFilterPromptResults" innerErrorCode: description: Error codes for the inner error object. enum: - ResponsibleAIPolicyViolation type: string x-ms-enum: name: InnerErrorCode modelAsString: true values: - value: ResponsibleAIPolicyViolation description: The prompt violated one of more content filter rules. dalleErrorResponse: type: object properties: error: $ref: "#/components/schemas/dalleError" dalleError: type: object allOf: - $ref: "#/components/schemas/errorBase" properties: param: type: string type: type: string inner_error: $ref: "#/components/schemas/dalleInnerError" dalleInnerError: description: Inner error with additional details. type: object properties: code: $ref: "#/components/schemas/innerErrorCode" content_filter_results: $ref: "#/components/schemas/dalleFilterResults" revised_prompt: type: string description: The prompt that was used to generate the image, if there was any revision to the prompt. contentFilterResultBase: type: object properties: filtered: type: boolean required: - filtered contentFilterSeverityResult: type: object allOf: - $ref: "#/components/schemas/contentFilterResultBase" - properties: severity: type: string enum: - safe - low - medium - high x-ms-enum: name: ContentFilterSeverity modelAsString: true values: - value: safe description: General content or related content in generic or non-harmful contexts. - value: low description: Harmful content at a low intensity and risk level. - value: medium description: Harmful content at a medium intensity and risk level. - value: high description: Harmful content at a high intensity and risk level. required: - severity - filtered contentFilterDetectedResult: type: object allOf: - $ref: "#/components/schemas/contentFilterResultBase" - properties: detected: type: boolean required: - detected - filtered contentFilterDetectedWithCitationResult: type: object allOf: - $ref: "#/components/schemas/contentFilterDetectedResult" - properties: citation: type: object properties: URL: type: string license: type: string required: - detected - filtered contentFilterIdResult: type: object allOf: - $ref: "#/components/schemas/contentFilterResultBase" - properties: id: type: string required: - id - filtered contentFilterResultsBase: type: object description: Information about the content filtering results. properties: sexual: $ref: "#/components/schemas/contentFilterSeverityResult" violence: $ref: "#/components/schemas/contentFilterSeverityResult" hate: $ref: "#/components/schemas/contentFilterSeverityResult" self_harm: $ref: "#/components/schemas/contentFilterSeverityResult" profanity: $ref: "#/components/schemas/contentFilterDetectedResult" custom_blocklists: $ref: "#/components/schemas/contentFilterDetailedResults" error: $ref: "#/components/schemas/errorBase" contentFilterPromptResults: type: object description: Information about the content filtering category (hate, sexual, violence, self_harm), if it has been detected, as well as the severity level (very_low, low, medium, high-scale that determines the intensity and risk level of harmful content) and if it has been filtered or not. Information about jailbreak content and profanity, if it has been detected, and if it has been filtered or not. And information about customer block list, if it has been filtered and its id. allOf: - $ref: "#/components/schemas/contentFilterResultsBase" - properties: jailbreak: $ref: "#/components/schemas/contentFilterDetectedResult" indirect_attack: $ref: "#/components/schemas/contentFilterDetectedResult" contentFilterChoiceResults: type: object description: Information about the content filtering category (hate, sexual, violence, self_harm), if it has been detected, as well as the severity level (very_low, low, medium, high-scale that determines the intensity and risk level of harmful content) and if it has been filtered or not. Information about third party text and profanity, if it has been detected, and if it has been filtered or not. And information about customer block list, if it has been filtered and its id. allOf: - $ref: "#/components/schemas/contentFilterResultsBase" - properties: protected_material_text: $ref: "#/components/schemas/contentFilterDetectedResult" - properties: protected_material_code: $ref: "#/components/schemas/contentFilterDetectedWithCitationResult" contentFilterDetailedResults: type: object description: Content filtering results with a detail of content filter ids for the filtered segments. allOf: - $ref: "#/components/schemas/contentFilterResultBase" - properties: details: items: $ref: "#/components/schemas/contentFilterIdResult" type: array required: - filtered promptFilterResult: type: object description: Content filtering results for a single prompt in the request. properties: prompt_index: type: integer content_filter_results: $ref: "#/components/schemas/contentFilterPromptResults" promptFilterResults: type: array description: Content filtering results for zero or more prompts in the request. In a streaming request, results for different prompts may arrive at different times or in different orders. items: $ref: "#/components/schemas/promptFilterResult" dalleContentFilterResults: type: object description: Information about the content filtering results. properties: sexual: $ref: "#/components/schemas/contentFilterSeverityResult" violence: $ref: "#/components/schemas/contentFilterSeverityResult" hate: $ref: "#/components/schemas/contentFilterSeverityResult" self_harm: $ref: "#/components/schemas/contentFilterSeverityResult" dalleFilterResults: type: object description: Information about the content filtering category (hate, sexual, violence, self_harm), if it has been detected, as well as the severity level (very_low, low, medium, high-scale that determines the intensity and risk level of harmful content) and if it has been filtered or not. Information about jailbreak content and profanity, if it has been detected, and if it has been filtered or not. And information about customer block list, if it has been filtered and its id. allOf: - $ref: "#/components/schemas/dalleContentFilterResults" - properties: profanity: $ref: "#/components/schemas/contentFilterDetectedResult" jailbreak: $ref: "#/components/schemas/contentFilterDetectedResult" custom_blocklists: $ref: "#/components/schemas/contentFilterDetailedResults" chatCompletionsRequestCommon: type: object properties: temperature: description: |- What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. type: number minimum: 0 maximum: 2 default: 1 example: 1 nullable: true top_p: description: |- An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both. type: number minimum: 0 maximum: 1 default: 1 example: 1 nullable: true stream: description: "If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a `data: [DONE]` message." type: boolean nullable: true default: false stop: description: Up to 4 sequences where the API will stop generating further tokens. oneOf: - type: string nullable: true - type: array items: type: string nullable: false minItems: 1 maxItems: 4 description: Array minimum size of 1 and maximum of 4 default: null max_tokens: description: | The maximum number of tokens allowed for the generated answer. By default, the number of tokens the model can return will be (4096 - prompt tokens). This value is now deprecated in favor of `max_completion_tokens`, and is not compatible with o1 series models. type: integer default: 4096 max_completion_tokens: description: | An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens. type: integer nullable: true presence_penalty: description: Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. type: number default: 0 minimum: -2 maximum: 2 frequency_penalty: description: Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. type: number default: 0 minimum: -2 maximum: 2 logit_bias: description: Modify the likelihood of specified tokens appearing in the completion. Accepts a json object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. type: object nullable: true user: description: A unique identifier representing your end-user, which can help Azure OpenAI to monitor and detect abuse. type: string example: user-1234 nullable: false createCompletionRequest: type: object properties: prompt: description: &completions_prompt_description | The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays. Note that <|endoftext|> is the document separator that the model sees during training, so if a prompt is not specified the model will generate as if from the beginning of a new document. default: "<|endoftext|>" nullable: true oneOf: - type: string default: "" example: "This is a test." - type: array items: type: string default: "" example: "This is a test." best_of: type: integer default: 1 minimum: 0 maximum: 20 nullable: true description: &completions_best_of_description | Generates `best_of` completions server-side and returns the "best" (the one with the highest log probability per token). Results cannot be streamed. When used with `n`, `best_of` controls the number of candidate completions and `n` specifies how many to return – `best_of` must be greater than `n`. **Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`. echo: type: boolean default: false nullable: true description: &completions_echo_description > Echo back the prompt in addition to the completion frequency_penalty: type: number default: 0 minimum: -2 maximum: 2 nullable: true description: &completions_frequency_penalty_description | Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. logit_bias: &completions_logit_bias type: object x-oaiTypeLabel: map default: null nullable: true additionalProperties: type: integer description: &completions_logit_bias_description | Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this [tokenizer tool](https://platform.openai.com/tokenizer?view=bpe) to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. As an example, you can pass `{"50256": -100}` to prevent the <|endoftext|> token from being generated. logprobs: &completions_logprobs_configuration type: integer minimum: 0 maximum: 5 default: null nullable: true description: &completions_logprobs_description | Include the log probabilities on the `logprobs` most likely output tokens, as well the chosen tokens. For example, if `logprobs` is 5, the API will return a list of the 5 most likely tokens. The API will always return the `logprob` of the sampled token, so there may be up to `logprobs+1` elements in the response. The maximum value for `logprobs` is 5. max_tokens: type: integer minimum: 0 default: 16 example: 16 nullable: true description: &completions_max_tokens_description | The maximum number of [tokens](https://platform.openai.com/tokenizer) that can be generated in the completion. The token count of your prompt plus `max_tokens` cannot exceed the model's context length. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens. n: type: integer minimum: 1 maximum: 128 default: 1 example: 1 nullable: true description: &completions_completions_description | How many completions to generate for each prompt. **Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`. presence_penalty: type: number default: 0 minimum: -2 maximum: 2 nullable: true description: &completions_presence_penalty_description | Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. seed: &completions_seed_param type: integer minimum: -9223372036854775808 maximum: 9223372036854775807 nullable: true description: | If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result. Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend. stop: description: &completions_stop_description > Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence. default: null nullable: true oneOf: - type: string default: <|endoftext|> example: "\n" nullable: true - type: array minItems: 1 maxItems: 4 items: type: string example: '["\n"]' stream: description: > Whether to stream back partial progress. If set, tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]` message. [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions). type: boolean nullable: true default: false suffix: description: | The suffix that comes after a completion of inserted text. This parameter is only supported for `gpt-3.5-turbo-instruct`. default: null nullable: true type: string example: "test." stream_options: $ref: "#/components/schemas/chatCompletionStreamOptions" temperature: type: number minimum: 0 maximum: 2 default: 1 example: 1 nullable: true description: &completions_temperature_description | What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. top_p: type: number minimum: 0 maximum: 1 default: 1 example: 1 nullable: true description: &completions_top_p_description | An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both. user: &end_user_param_configuration type: string example: user-1234 description: | A unique identifier representing your end-user, which can help to monitor and detect abuse. required: - prompt createCompletionResponse: type: object description: | Represents a completion response from the API. Note: both the streamed and non-streamed response objects share the same shape (unlike the chat endpoint). properties: id: type: string description: A unique identifier for the completion. choices: type: array description: The list of completion choices the model generated for the input prompt. items: type: object required: - finish_reason - index - logprobs - text properties: finish_reason: type: string description: &completion_finish_reason_description | The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, `length` if the maximum number of tokens specified in the request was reached, or `content_filter` if content was omitted due to a flag from our content filters. enum: ["stop", "length", "content_filter"] index: type: integer logprobs: type: object nullable: true properties: text_offset: type: array items: type: integer token_logprobs: type: array items: type: number tokens: type: array items: type: string top_logprobs: type: array items: type: object additionalProperties: type: number text: type: string content_filter_results: $ref: "#/components/schemas/contentFilterChoiceResults" created: type: integer description: The Unix timestamp (in seconds) of when the completion was created. model: type: string description: The model used for completion. prompt_filter_results: $ref: "#/components/schemas/promptFilterResults" system_fingerprint: type: string description: | This fingerprint represents the backend configuration that the model runs with. Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism. object: type: string description: The object type, which is always "text_completion" enum: [text_completion] usage: $ref: "#/components/schemas/completionUsage" required: - id - object - created - model - choices createChatCompletionRequest: type: object allOf: - $ref: "#/components/schemas/chatCompletionsRequestCommon" - properties: messages: description: A list of messages comprising the conversation so far. [Example Python code](https://github.com/openai/openai-cookbook/blob/main/examples/How_to_format_inputs_to_ChatGPT_models.ipynb). type: array minItems: 1 items: $ref: "#/components/schemas/chatCompletionRequestMessage" data_sources: type: array description: |2- The configuration entries for Azure OpenAI chat extensions that use them. This additional specification is only compatible with Azure OpenAI. items: $ref: "#/components/schemas/azureChatExtensionConfiguration" frequency_penalty: type: number default: 0 minimum: -2 maximum: 2 nullable: true description: *completions_frequency_penalty_description logit_bias: type: object default: null nullable: true additionalProperties: type: integer description: | Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. logprobs: description: Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the `content` of `message`. type: boolean default: false nullable: true top_logprobs: description: An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. `logprobs` must be set to `true` if this parameter is used. type: integer minimum: 0 maximum: 20 nullable: true max_tokens: description: | The maximum number of [tokens](/tokenizer) that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens. type: integer nullable: true n: type: integer minimum: 1 maximum: 128 default: 1 example: 1 nullable: true description: How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep `n` as `1` to minimize costs. parallel_tool_calls: $ref: "#/components/schemas/ParallelToolCalls" presence_penalty: type: number default: 0 minimum: -2 maximum: 2 nullable: true description: *completions_presence_penalty_description response_format: description: | An object specifying the format that the model must output. Compatible with [GPT-4o](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#gpt-4-and-gpt-4-turbo-models), [GPT-4o mini](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#gpt-4-and-gpt-4-turbo-models), [GPT-4 Turbo](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#gpt-4-and-gpt-4-turbo-models) and all [GPT-3.5](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#gpt-35) Turbo models newer than `gpt-3.5-turbo-1106`. Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured Outputs which guarantees the model will match your supplied JSON schema. Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the message the model generates is valid JSON. **Important:** when using JSON mode, you **must** also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length. oneOf: - $ref: "#/components/schemas/ResponseFormatText" - $ref: "#/components/schemas/ResponseFormatJsonObject" - $ref: "#/components/schemas/ResponseFormatJsonSchema" x-oaiExpandable: true seed: type: integer minimum: -9223372036854775808 maximum: 9223372036854775807 nullable: true description: | This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result. Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend. stop: description: | Up to 4 sequences where the API will stop generating further tokens. default: null oneOf: - type: string nullable: true - type: array minItems: 1 maxItems: 4 items: type: string stream: description: > If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]` message. [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions). type: boolean nullable: true default: false stream_options: $ref: "#/components/schemas/chatCompletionStreamOptions" temperature: type: number minimum: 0 maximum: 2 default: 1 example: 1 nullable: true description: *completions_temperature_description top_p: type: number minimum: 0 maximum: 1 default: 1 example: 1 nullable: true description: *completions_top_p_description tools: type: array description: > A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported. items: $ref: "#/components/schemas/chatCompletionTool" tool_choice: $ref: "#/components/schemas/chatCompletionToolChoiceOption" function_call: deprecated: true description: | Deprecated in favor of `tool_choice`. Controls which (if any) function is called by the model. `none` means the model will not call a function and instead generates a message. `auto` means the model can pick between generating a message or calling a function. Specifying a particular function via `{"name": "my_function"}` forces the model to call that function. `none` is the default when no functions are present. `auto` is the default if functions are present. oneOf: - type: string description: > `none` means the model will not call a function and instead generates a message. `auto` means the model can pick between generating a message or calling a function. enum: [none, auto] - $ref: "#/components/schemas/chatCompletionFunctionCallOption" x-oaiExpandable: true functions: deprecated: true description: | Deprecated in favor of `tools`. A list of functions the model may generate JSON inputs for. type: array minItems: 1 maxItems: 128 items: $ref: "#/components/schemas/chatCompletionFunctions" user: *end_user_param_configuration required: - messages chatCompletionFunctions: type: object deprecated: true properties: description: type: string description: A description of what the function does, used by the model to choose when and how to call the function. name: type: string description: The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. parameters: $ref: "#/components/schemas/FunctionParameters" required: - name chatCompletionFunctionCallOption: type: object description: > Specifying a particular function via `{"name": "my_function"}` forces the model to call that function. properties: name: type: string description: The name of the function to call. required: - name chatCompletionFunctionParameters: type: object description: The parameters the functions accepts, described as a JSON Schema object. See the [guide/](https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema/) for documentation about the format. additionalProperties: true chatCompletionRequestMessage: oneOf: - $ref: "#/components/schemas/chatCompletionRequestSystemMessage" - $ref: "#/components/schemas/chatCompletionRequestUserMessage" - $ref: "#/components/schemas/chatCompletionRequestAssistantMessage" - $ref: "#/components/schemas/chatCompletionRequestToolMessage" - $ref: "#/components/schemas/chatCompletionRequestFunctionMessage" chatCompletionRequestSystemMessage: type: object title: System message properties: content: description: The contents of the system message. oneOf: - type: string description: The contents of the system message. title: Text content - type: array description: An array of content parts with a defined type. For system messages, only type `text` is supported. title: Array of content parts items: $ref: "#/components/schemas/chatCompletionRequestSystemMessageContentPart" minItems: 1 role: type: string enum: ["system"] description: The role of the messages author, in this case `system`. name: type: string description: An optional name for the participant. Provides the model information to differentiate between participants of the same role. required: - content - role chatCompletionRequestUserMessage: type: object title: User message properties: content: description: | The contents of the user message. oneOf: - type: string description: The text contents of the message. title: Text content - type: array description: An array of content parts with a defined type, each can be of type `text` or `image_url` when passing in images. You can pass multiple images by adding multiple `image_url` content parts. Image input is only supported when using the `gpt-4o` model. title: Array of content parts items: $ref: "#/components/schemas/chatCompletionRequestUserMessageContentPart" minItems: 1 x-oaiExpandable: true role: type: string enum: ["user"] description: The role of the messages author, in this case `user`. name: type: string description: An optional name for the participant. Provides the model information to differentiate between participants of the same role. required: - content - role chatCompletionRequestAssistantMessage: type: object title: Assistant message properties: content: nullable: true oneOf: - type: string description: The contents of the assistant message. title: Text content - type: array description: An array of content parts with a defined type. Can be one or more of type `text`, or exactly one of type `refusal`. title: Array of content parts items: $ref: "#/components/schemas/chatCompletionRequestAssistantMessageContentPart" minItems: 1 description: | The contents of the assistant message. Required unless `tool_calls` or `function_call` is specified. refusal: nullable: true type: string description: The refusal message by the assistant. role: type: string enum: ["assistant"] description: The role of the messages author, in this case `assistant`. name: type: string description: An optional name for the participant. Provides the model information to differentiate between participants of the same role. tool_calls: $ref: "#/components/schemas/chatCompletionMessageToolCalls" function_call: type: object deprecated: true description: "Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model." nullable: true properties: arguments: type: string description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. name: type: string description: The name of the function to call. required: - arguments - name required: - role chatCompletionRequestToolMessage: type: object title: Tool message properties: role: type: string enum: ["tool"] description: The role of the messages author, in this case `tool`. content: oneOf: - type: string description: The contents of the tool message. title: Text content - type: array description: An array of content parts with a defined type. For tool messages, only type `text` is supported. title: Array of content parts items: $ref: "#/components/schemas/chatCompletionRequestToolMessageContentPart" minItems: 1 description: The contents of the tool message. tool_call_id: type: string description: Tool call that this message is responding to. required: - role - content - tool_call_id chatCompletionRequestFunctionMessage: type: object title: Function message deprecated: true properties: role: type: string enum: ["function"] description: The role of the messages author, in this case `function`. content: nullable: true type: string description: The contents of the function message. name: type: string description: The name of the function to call. required: - role - content - name chatCompletionRequestSystemMessageContentPart: oneOf: - $ref: "#/components/schemas/chatCompletionRequestMessageContentPartText" chatCompletionRequestUserMessageContentPart: oneOf: - $ref: "#/components/schemas/chatCompletionRequestMessageContentPartText" - $ref: "#/components/schemas/chatCompletionRequestMessageContentPartImage" chatCompletionRequestAssistantMessageContentPart: oneOf: - $ref: "#/components/schemas/chatCompletionRequestMessageContentPartText" - $ref: "#/components/schemas/chatCompletionRequestMessageContentPartRefusal" chatCompletionRequestToolMessageContentPart: oneOf: - $ref: "#/components/schemas/chatCompletionRequestMessageContentPartText" chatCompletionRequestMessageContentPartText: type: object title: Text content part properties: type: type: string enum: ["text"] description: The type of the content part. text: type: string description: The text content. required: - type - text chatCompletionRequestMessageContentPartImage: type: object title: Image content part properties: type: type: string enum: ["image_url"] description: The type of the content part. image_url: type: object properties: url: type: string description: Either a URL of the image or the base64 encoded image data. format: uri detail: type: string description: Specifies the detail level of the image. Learn more in the [Vision guide](https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/gpt-with-vision?tabs=rest%2Csystem-assigned%2Cresource#detail-parameter-settings-in-image-processing-low-high-auto). enum: ["auto", "low", "high"] default: "auto" required: - url required: - type - image_url chatCompletionRequestMessageContentPartRefusal: type: object title: Refusal content part properties: type: type: string enum: ["refusal"] description: The type of the content part. refusal: type: string description: The refusal message generated by the model. required: - type - refusal azureChatExtensionConfiguration: required: - type type: object properties: type: $ref: "#/components/schemas/azureChatExtensionType" description: |2- A representation of configuration data for a single Azure OpenAI chat extension. This will be used by a chat completions request that should use Azure OpenAI chat extensions to augment the response behavior. The use of this configuration is compatible only with Azure OpenAI. discriminator: propertyName: type mapping: azure_search: "#/components/schemas/azureSearchChatExtensionConfiguration" azure_cosmos_db: "#/components/schemas/azureCosmosDBChatExtensionConfiguration" elasticsearch: "#/components/schemas/elasticsearchChatExtensionConfiguration" mongo_db: "#/components/schemas/mongoDBChatExtensionConfiguration" pinecone: "#/components/schemas/pineconeChatExtensionConfiguration" azureChatExtensionType: type: string description: |2- A representation of configuration data for a single Azure OpenAI chat extension. This will be used by a chat completions request that should use Azure OpenAI chat extensions to augment the response behavior. The use of this configuration is compatible only with Azure OpenAI. enum: - azure_search - azure_cosmos_db - elasticsearch - mongo_db - pinecone x-ms-enum: name: AzureChatExtensionType modelAsString: true values: - name: azureSearch value: azure_search description: Represents the use of Azure Search as an Azure OpenAI chat extension. - name: azureCosmosDB value: azure_cosmos_db description: Represents the use of Azure Cosmos DB as an Azure OpenAI chat extension. - name: elasticsearch value: elasticsearch description: Represents the use of Elasticsearch® index as an Azure OpenAI chat extension. - name: mongoDB value: mongo_db description: Represents the use of Mongo DB as an Azure OpenAI chat extension. - name: pinecone value: pinecone description: Represents the use of Pinecone index as an Azure OpenAI chat extension. azureSearchChatExtensionConfiguration: required: - parameters description: |- A specific representation of configurable options for Azure Search when using it as an Azure OpenAI chat extension. allOf: - $ref: "#/components/schemas/azureChatExtensionConfiguration" - properties: parameters: $ref: "#/components/schemas/azureSearchChatExtensionParameters" x-ms-discriminator-value: azure_search azureSearchChatExtensionParameters: required: - authentication - endpoint - index_name type: object properties: authentication: oneOf: - $ref: "#/components/schemas/onYourDataApiKeyAuthenticationOptions" - $ref: "#/components/schemas/onYourDataSystemAssignedManagedIdentityAuthenticationOptions" - $ref: "#/components/schemas/onYourDataUserAssignedManagedIdentityAuthenticationOptions" - $ref: "#/components/schemas/onYourDataAccessTokenAuthenticationOptions" top_n_documents: type: integer description: The configured top number of documents to feature for the configured query. format: int32 max_search_queries: type: integer description: The max number of rewritten queries should be send to search provider for one user message. If not specified, the system will decide the number of queries to send. format: int32 allow_partial_result: type: boolean default: false description: If specified as true, the system will allow partial search results to be used and the request fails if all the queries fail. If not specified, or specified as false, the request will fail if any search query fails. in_scope: type: boolean description: Whether queries should be restricted to use of indexed data. strictness: maximum: 5 minimum: 1 type: integer description: The configured strictness of the search relevance filtering. The higher of strictness, the higher of the precision but lower recall of the answer. format: int32 endpoint: type: string description: The absolute endpoint path for the Azure Search resource to use. format: uri index_name: type: string description: The name of the index to use as available in the referenced Azure Search resource. fields_mapping: $ref: "#/components/schemas/azureSearchIndexFieldMappingOptions" query_type: $ref: "#/components/schemas/azureSearchQueryType" semantic_configuration: type: string description: The additional semantic configuration for the query. filter: type: string description: Search filter. embedding_dependency: oneOf: - $ref: "#/components/schemas/onYourDataEndpointVectorizationSource" - $ref: "#/components/schemas/onYourDataDeploymentNameVectorizationSource" - $ref: "#/components/schemas/onYourDataIntegratedVectorizationSource" include_contexts: type: array description: The included properties of the output context. If not specified, the default value is `citations` and `intent`. items: $ref: "#/components/schemas/onYourDataContextProperty" description: Parameters for Azure Search when used as an Azure OpenAI chat extension. azureSearchIndexFieldMappingOptions: type: object properties: title_field: type: string description: The name of the index field to use as a title. url_field: type: string description: The name of the index field to use as a URL. filepath_field: type: string description: The name of the index field to use as a filepath. content_fields: type: array description: The names of index fields that should be treated as content. items: type: string content_fields_separator: type: string description: The separator pattern that content fields should use. vector_fields: type: array description: The names of fields that represent vector data. items: type: string image_vector_fields: type: array description: The names of fields that represent image vector data. items: type: string description: Optional settings to control how fields are processed when using a configured Azure Search resource. azureSearchQueryType: type: string description: The type of Azure Search retrieval query that should be executed when using it as an Azure OpenAI chat extension. enum: - simple - semantic - vector - vector_simple_hybrid - vector_semantic_hybrid x-ms-enum: name: AzureSearchQueryType modelAsString: true values: - name: simple value: simple description: Represents the default, simple query parser. - name: semantic value: semantic description: Represents the semantic query parser for advanced semantic modeling. - name: vector value: vector description: Represents vector search over computed data. - name: vectorSimpleHybrid value: vector_simple_hybrid description: Represents a combination of the simple query strategy with vector data. - name: vectorSemanticHybrid value: vector_semantic_hybrid description: Represents a combination of semantic search and vector data querying. azureCosmosDBChatExtensionConfiguration: required: - parameters description: |- A specific representation of configurable options for Azure Cosmos DB when using it as an Azure OpenAI chat extension. allOf: - $ref: "#/components/schemas/azureChatExtensionConfiguration" - properties: parameters: $ref: "#/components/schemas/azureCosmosDBChatExtensionParameters" x-ms-discriminator-value: azure_cosmos_db azureCosmosDBChatExtensionParameters: required: - authentication - container_name - database_name - embedding_dependency - fields_mapping - index_name type: object properties: authentication: $ref: "#/components/schemas/onYourDataConnectionStringAuthenticationOptions" top_n_documents: type: integer description: The configured top number of documents to feature for the configured query. format: int32 max_search_queries: type: integer description: The max number of rewritten queries should be send to search provider for one user message. If not specified, the system will decide the number of queries to send. format: int32 allow_partial_result: type: boolean default: false description: If specified as true, the system will allow partial search results to be used and the request fails if all the queries fail. If not specified, or specified as false, the request will fail if any search query fails. in_scope: type: boolean description: Whether queries should be restricted to use of indexed data. strictness: maximum: 5 minimum: 1 type: integer description: The configured strictness of the search relevance filtering. The higher of strictness, the higher of the precision but lower recall of the answer. format: int32 database_name: type: string description: The MongoDB vCore database name to use with Azure Cosmos DB. container_name: type: string description: The name of the Azure Cosmos DB resource container. index_name: type: string description: The MongoDB vCore index name to use with Azure Cosmos DB. fields_mapping: $ref: "#/components/schemas/azureCosmosDBFieldMappingOptions" embedding_dependency: oneOf: - $ref: "#/components/schemas/onYourDataEndpointVectorizationSource" - $ref: "#/components/schemas/onYourDataDeploymentNameVectorizationSource" include_contexts: type: array description: The included properties of the output context. If not specified, the default value is `citations` and `intent`. items: $ref: "#/components/schemas/onYourDataContextProperty" description: |- Parameters to use when configuring Azure OpenAI On Your Data chat extensions when using Azure Cosmos DB for MongoDB vCore. azureCosmosDBFieldMappingOptions: required: - content_fields - vector_fields type: object properties: title_field: type: string description: The name of the index field to use as a title. url_field: type: string description: The name of the index field to use as a URL. filepath_field: type: string description: The name of the index field to use as a filepath. content_fields: type: array description: The names of index fields that should be treated as content. items: type: string content_fields_separator: type: string description: The separator pattern that content fields should use. vector_fields: type: array description: The names of fields that represent vector data. items: type: string description: Optional settings to control how fields are processed when using a configured Azure Cosmos DB resource. elasticsearchChatExtensionConfiguration: required: - parameters description: |- A specific representation of configurable options for Elasticsearch when using it as an Azure OpenAI chat extension. allOf: - $ref: "#/components/schemas/azureChatExtensionConfiguration" - properties: parameters: $ref: "#/components/schemas/elasticsearchChatExtensionParameters" x-ms-discriminator-value: elasticsearch elasticsearchChatExtensionParameters: required: - authentication - endpoint - index_name type: object properties: authentication: oneOf: - $ref: "#/components/schemas/onYourDataKeyAndKeyIdAuthenticationOptions" - $ref: "#/components/schemas/onYourDataEncodedApiKeyAuthenticationOptions" top_n_documents: type: integer description: The configured top number of documents to feature for the configured query. format: int32 max_search_queries: type: integer description: The max number of rewritten queries should be send to search provider for one user message. If not specified, the system will decide the number of queries to send. format: int32 allow_partial_result: type: boolean default: false description: If specified as true, the system will allow partial search results to be used and the request fails if all the queries fail. If not specified, or specified as false, the request will fail if any search query fails. in_scope: type: boolean description: Whether queries should be restricted to use of indexed data. strictness: maximum: 5 minimum: 1 type: integer description: The configured strictness of the search relevance filtering. The higher of strictness, the higher of the precision but lower recall of the answer. format: int32 endpoint: type: string description: The endpoint of Elasticsearch®. format: uri index_name: type: string description: The index name of Elasticsearch®. fields_mapping: $ref: "#/components/schemas/elasticsearchIndexFieldMappingOptions" query_type: $ref: "#/components/schemas/elasticsearchQueryType" embedding_dependency: oneOf: - $ref: "#/components/schemas/onYourDataEndpointVectorizationSource" - $ref: "#/components/schemas/onYourDataDeploymentNameVectorizationSource" - $ref: "#/components/schemas/onYourDataModelIdVectorizationSource" include_contexts: type: array description: The included properties of the output context. If not specified, the default value is `citations` and `intent`. items: $ref: "#/components/schemas/onYourDataContextProperty" description: "Parameters to use when configuring Elasticsearch® as an Azure OpenAI chat extension. " elasticsearchIndexFieldMappingOptions: type: object properties: title_field: type: string description: The name of the index field to use as a title. url_field: type: string description: The name of the index field to use as a URL. filepath_field: type: string description: The name of the index field to use as a filepath. content_fields: type: array description: The names of index fields that should be treated as content. items: type: string content_fields_separator: type: string description: The separator pattern that content fields should use. vector_fields: type: array description: The names of fields that represent vector data. items: type: string description: Optional settings to control how fields are processed when using a configured Elasticsearch® resource. elasticsearchQueryType: type: string description: The type of Elasticsearch® retrieval query that should be executed when using it as an Azure OpenAI chat extension. enum: - simple - vector x-ms-enum: name: ElasticsearchQueryType modelAsString: true values: - name: simple value: simple description: Represents the default, simple query parser. - name: vector value: vector description: Represents vector search over computed data. mongoDBChatExtensionConfiguration: required: - parameters description: |- A specific representation of configurable options for Mongo DB when using it as an Azure OpenAI chat extension. allOf: - $ref: "#/components/schemas/azureChatExtensionConfiguration" - properties: parameters: $ref: "#/components/schemas/mongoDBChatExtensionParameters" x-ms-discriminator-value: mongo_db mongoDBChatExtensionParameters: required: - authentication - app_name - collection_name - database_name - endpoint - embedding_dependency - fields_mapping - index_name type: object properties: authentication: $ref: "#/components/schemas/onYourDataUsernameAndPasswordAuthenticationOptions" top_n_documents: type: integer description: The configured top number of documents to feature for the configured query. format: int32 max_search_queries: type: integer description: The max number of rewritten queries should be send to search provider for one user message. If not specified, the system will decide the number of queries to send. format: int32 allow_partial_result: type: boolean default: false description: If specified as true, the system will allow partial search results to be used and the request fails if all the queries fail. If not specified, or specified as false, the request will fail if any search query fails. in_scope: type: boolean description: Whether queries should be restricted to use of indexed data. strictness: maximum: 5 minimum: 1 type: integer description: The configured strictness of the search relevance filtering. The higher of strictness, the higher of the precision but lower recall of the answer. format: int32 endpoint: type: string description: The name of the Mongo DB cluster endpoint. database_name: type: string description: The name of the Mongo DB database. collection_name: type: string description: The name of the Mongo DB Collection. app_name: type: string description: The name of the Mongo DB Application. index_name: type: string description: The The name of the Mongo DB index. fields_mapping: $ref: "#/components/schemas/mongoDBFieldMappingOptions" embedding_dependency: oneOf: - $ref: "#/components/schemas/onYourDataEndpointVectorizationSource" - $ref: "#/components/schemas/onYourDataDeploymentNameVectorizationSource" include_contexts: type: array description: The included properties of the output context. If not specified, the default value is `citations` and `intent`. items: $ref: "#/components/schemas/onYourDataContextProperty" description: |- Parameters to use when configuring Azure OpenAI On Your Data chat extensions when using Mongo DB. mongoDBFieldMappingOptions: required: - content_fields - vector_fields type: object properties: title_field: type: string description: The name of the index field to use as a title. url_field: type: string description: The name of the index field to use as a URL. filepath_field: type: string description: The name of the index field to use as a filepath. content_fields: type: array description: The names of index fields that should be treated as content. items: type: string content_fields_separator: type: string description: The separator pattern that content fields should use. vector_fields: type: array description: The names of fields that represent vector data. items: type: string description: Optional settings to control how fields are processed when using a configured Mongo DB resource. pineconeChatExtensionConfiguration: required: - parameters description: |- A specific representation of configurable options for Pinecone when using it as an Azure OpenAI chat extension. allOf: - $ref: "#/components/schemas/azureChatExtensionConfiguration" - properties: parameters: $ref: "#/components/schemas/pineconeChatExtensionParameters" x-ms-discriminator-value: pinecone pineconeChatExtensionParameters: required: - authentication - embedding_dependency - environment - fields_mapping - index_name type: object properties: authentication: $ref: "#/components/schemas/onYourDataApiKeyAuthenticationOptions" top_n_documents: type: integer description: The configured top number of documents to feature for the configured query. format: int32 max_search_queries: type: integer description: The max number of rewritten queries should be send to search provider for one user message. If not specified, the system will decide the number of queries to send. format: int32 allow_partial_result: type: boolean default: false description: If specified as true, the system will allow partial search results to be used and the request fails if all the queries fail. If not specified, or specified as false, the request will fail if any search query fails. in_scope: type: boolean description: Whether queries should be restricted to use of indexed data. strictness: maximum: 5 minimum: 1 type: integer description: The configured strictness of the search relevance filtering. The higher of strictness, the higher of the precision but lower recall of the answer. format: int32 environment: type: string description: The environment name of Pinecone. index_name: type: string description: The name of the Pinecone database index. fields_mapping: $ref: "#/components/schemas/pineconeFieldMappingOptions" embedding_dependency: $ref: "#/components/schemas/onYourDataDeploymentNameVectorizationSource" include_contexts: type: array description: The included properties of the output context. If not specified, the default value is `citations` and `intent`. items: $ref: "#/components/schemas/onYourDataContextProperty" description: Parameters for configuring Azure OpenAI Pinecone chat extensions. pineconeFieldMappingOptions: required: - content_fields type: object properties: title_field: type: string description: The name of the index field to use as a title. url_field: type: string description: The name of the index field to use as a URL. filepath_field: type: string description: The name of the index field to use as a filepath. content_fields: type: array description: The names of index fields that should be treated as content. items: type: string content_fields_separator: type: string description: The separator pattern that content fields should use. description: Optional settings to control how fields are processed when using a configured Pinecone resource. onYourDataAuthenticationOptions: required: - type type: object properties: type: $ref: "#/components/schemas/onYourDataAuthenticationType" description: The authentication options for Azure OpenAI On Your Data. discriminator: propertyName: type mapping: api_key: "#/components/schemas/onYourDataApiKeyAuthenticationOptions" connection_string: "#/components/schemas/onYourDataConnectionStringAuthenticationOptions" key_and_key_id: "#/components/schemas/onYourDataKeyAndKeyIdAuthenticationOptions" encoded_api_key: "#/components/schemas/onYourDataEncodedApiKeyAuthenticationOptions" access_token: "#/components/schemas/onYourDataAccessTokenAuthenticationOptions" system_assigned_managed_identity: "#/components/schemas/onYourDataSystemAssignedManagedIdentityAuthenticationOptions" user_assigned_managed_identity: "#/components/schemas/onYourDataUserAssignedManagedIdentityAuthenticationOptions" username_and_password: "#/components/schemas/onYourDataUsernameAndPasswordAuthenticationOptions" onYourDataContextProperty: type: string description: The context property. enum: - citations - intent - all_retrieved_documents x-ms-enum: name: OnYourDataContextProperty modelAsString: true values: - name: citations value: citations description: The `citations` property. - name: intent value: intent description: The `intent` property. - name: allRetrievedDocuments value: all_retrieved_documents description: The `all_retrieved_documents` property. onYourDataAuthenticationType: type: string description: The authentication types supported with Azure OpenAI On Your Data. enum: - api_key - connection_string - key_and_key_id - encoded_api_key - access_token - system_assigned_managed_identity - user_assigned_managed_identity - username_and_password x-ms-enum: name: OnYourDataAuthenticationType modelAsString: true values: - name: apiKey value: api_key description: Authentication via API key. - name: connectionString value: connection_string description: Authentication via connection string. - name: keyAndKeyId value: key_and_key_id description: Authentication via key and key ID pair. - name: encodedApiKey value: encoded_api_key description: Authentication via encoded API key. - name: accessToken value: access_token description: Authentication via access token. - name: systemAssignedManagedIdentity value: system_assigned_managed_identity description: Authentication via system-assigned managed identity. - name: userAssignedManagedIdentity value: user_assigned_managed_identity description: Authentication via user-assigned managed identity. - name: usernameAndPassword value: username_and_password description: Authentication via username and password. onYourDataApiKeyAuthenticationOptions: required: - key description: The authentication options for Azure OpenAI On Your Data when using an API key. allOf: - $ref: "#/components/schemas/onYourDataAuthenticationOptions" - properties: key: type: string description: The API key to use for authentication. x-ms-discriminator-value: api_key onYourDataConnectionStringAuthenticationOptions: required: - connection_string description: The authentication options for Azure OpenAI On Your Data when using a connection string. allOf: - $ref: "#/components/schemas/onYourDataAuthenticationOptions" - properties: connection_string: type: string description: The connection string to use for authentication. x-ms-discriminator-value: connection_string onYourDataKeyAndKeyIdAuthenticationOptions: required: - key - key_id description: The authentication options for Azure OpenAI On Your Data when using an Elasticsearch key and key ID pair. allOf: - $ref: "#/components/schemas/onYourDataAuthenticationOptions" - properties: key: type: string description: The Elasticsearch key to use for authentication. key_id: type: string description: The Elasticsearch key ID to use for authentication. x-ms-discriminator-value: key_and_key_id onYourDataEncodedApiKeyAuthenticationOptions: required: - encoded_api_key description: The authentication options for Azure OpenAI On Your Data when using an Elasticsearch encoded API key. allOf: - $ref: "#/components/schemas/onYourDataAuthenticationOptions" - properties: encoded_api_key: type: string description: The Elasticsearch encoded API key to use for authentication. x-ms-discriminator-value: encoded_api_key onYourDataAccessTokenAuthenticationOptions: required: - access_token description: The authentication options for Azure OpenAI On Your Data when using access token. allOf: - $ref: "#/components/schemas/onYourDataAuthenticationOptions" - properties: access_token: type: string description: The access token to use for authentication. x-ms-discriminator-value: access_token onYourDataSystemAssignedManagedIdentityAuthenticationOptions: description: The authentication options for Azure OpenAI On Your Data when using a system-assigned managed identity. allOf: - $ref: "#/components/schemas/onYourDataAuthenticationOptions" x-ms-discriminator-value: system_assigned_managed_identity onYourDataUserAssignedManagedIdentityAuthenticationOptions: required: - managed_identity_resource_id description: The authentication options for Azure OpenAI On Your Data when using a user-assigned managed identity. allOf: - $ref: "#/components/schemas/onYourDataAuthenticationOptions" - properties: managed_identity_resource_id: type: string description: The resource ID of the user-assigned managed identity to use for authentication. x-ms-discriminator-value: user_assigned_managed_identity onYourDataUsernameAndPasswordAuthenticationOptions: required: - username - password description: The authentication options for Azure OpenAI On Your Data when using a username and a password. allOf: - $ref: "#/components/schemas/onYourDataAuthenticationOptions" - properties: username: type: string description: The username to use for authentication. password: type: string description: The password. to use for authentication. x-ms-discriminator-value: username_and_password onYourDataVectorizationSource: required: - type type: object properties: type: $ref: "#/components/schemas/onYourDataVectorizationSourceType" description: An abstract representation of a vectorization source for Azure OpenAI On Your Data with vector search. discriminator: propertyName: type mapping: endpoint: "#/components/schemas/onYourDataEndpointVectorizationSource" deployment_name: "#/components/schemas/onYourDataDeploymentNameVectorizationSource" integrated: "#/components/schemas/onYourDataIntegratedVectorizationSource" model_id: "#/components/schemas/onYourDataModelIdVectorizationSource" onYourDataVectorizationSourceType: type: string description: |- Represents the available sources Azure OpenAI On Your Data can use to configure vectorization of data for use with vector search. enum: - endpoint - deployment_name - integrated - model_id x-ms-enum: name: OnYourDataVectorizationSourceType modelAsString: true values: - name: endpoint value: endpoint description: Represents vectorization performed by public service calls to an Azure OpenAI embedding model. - name: deploymentName value: deployment_name description: |- Represents an Ada model deployment name to use. This model deployment must be in the same Azure OpenAI resource, but On Your Data will use this model deployment via an internal call rather than a public one, which enables vector search even in private networks. - name: integrated value: integrated description: Represents the integrated vectorizer defined within the search resource. - name: modelId value: model_id description: |- Represents a specific embedding model ID as defined in the search service. Currently only supported by Elasticsearch®. onYourDataEndpointVectorizationSource: required: - authentication - endpoint description: |- The details of a a vectorization source, used by Azure OpenAI On Your Data when applying vector search, that is based on a public Azure OpenAI endpoint call for embeddings. allOf: - $ref: "#/components/schemas/onYourDataVectorizationSource" - properties: endpoint: type: string description: Specifies the resource endpoint URL from which embeddings should be retrieved. It should be in the format of https://YOUR_RESOURCE_NAME.openai.azure.com/openai/deployments/YOUR_DEPLOYMENT_NAME/embeddings. The api-version query parameter is not allowed. format: uri authentication: oneOf: - $ref: "#/components/schemas/onYourDataApiKeyAuthenticationOptions" - $ref: "#/components/schemas/onYourDataAccessTokenAuthenticationOptions" dimensions: type: integer description: The number of dimensions the embeddings should have. Only supported in `text-embedding-3` and later models. format: int32 x-ms-discriminator-value: endpoint onYourDataDeploymentNameVectorizationSource: required: - deployment_name description: |- The details of a a vectorization source, used by Azure OpenAI On Your Data when applying vector search, that is based on an internal embeddings model deployment name in the same Azure OpenAI resource. allOf: - $ref: "#/components/schemas/onYourDataVectorizationSource" - properties: deployment_name: type: string description: Specifies the name of the model deployment to use for vectorization. This model deployment must be in the same Azure OpenAI resource, but On Your Data will use this model deployment via an internal call rather than a public one, which enables vector search even in private networks. dimensions: type: integer description: The number of dimensions the embeddings should have. Only supported in `text-embedding-3` and later models. format: int32 x-ms-discriminator-value: deployment_name onYourDataIntegratedVectorizationSource: description: |- Represents the integrated vectorizer defined within the search resource. allOf: - $ref: "#/components/schemas/onYourDataVectorizationSource" x-ms-discriminator-value: integrated onYourDataModelIdVectorizationSource: required: - model_id description: |- The details of a a vectorization source, used by Azure OpenAI On Your Data when applying vector search, that is based on a search service model ID. Currently only supported by Elasticsearch®. allOf: - $ref: "#/components/schemas/onYourDataVectorizationSource" - properties: model_id: type: string description: Specifies the model ID to use for vectorization. This model ID must be defined in the search service. x-ms-discriminator-value: model_id azureChatExtensionsMessageContext: type: object properties: citations: type: array description: The data source retrieval result, used to generate the assistant message in the response. items: $ref: "#/components/schemas/citation" x-ms-identifiers: [] intent: type: string description: The detected intent from the chat history, used to pass to the next turn to carry over the context. all_retrieved_documents: type: array description: All the retrieved documents. items: $ref: "#/components/schemas/retrievedDocument" description: |2- A representation of the additional context information available when Azure OpenAI chat extensions are involved in the generation of a corresponding chat completions response. This context information is only populated when using an Azure OpenAI request configured to use a matching extension. citation: required: - content type: object properties: content: type: string description: The content of the citation. title: type: string description: The title of the citation. url: type: string description: The URL of the citation. filepath: type: string description: The file path of the citation. chunk_id: type: string description: The chunk ID of the citation. rerank_score: type: number description: The rerank score of the retrieved document. format: double description: citation information for a chat completions response message. retrievedDocument: type: object description: The retrieved document. required: - search_queries - data_source_index allOf: - $ref: "#/components/schemas/citation" - properties: search_queries: type: array description: The search queries used to retrieve the document. items: type: string data_source_index: type: integer description: The index of the data source. format: int32 original_search_score: type: number description: The original search score of the retrieved document. format: double filter_reason: $ref: "#/components/schemas/filterReason" description: Represents the rationale for filtering the document. If the document does not undergo filtering, this field will remain unset. filterReason: type: string description: The filtering reason of the retrieved document. enum: - score - rerank x-ms-enum: name: FilterReason modelAsString: true values: - name: score value: score description: The document is filtered by original search score threshold defined by `strictness` configure. - name: rerank value: rerank description: The document is not filtered by original search score threshold, but is filtered by rerank score and `top_n_documents` configure. chatCompletionMessageToolCall: type: object properties: id: type: string description: The ID of the tool call. type: $ref: "#/components/schemas/toolCallType" function: type: object description: The function that the model called. properties: name: type: string description: The name of the function to call. arguments: type: string description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. required: - name - arguments required: - id - type - function toolCallType: type: string enum: - function description: The type of the tool call, in this case `function`. x-ms-enum: name: ToolCallType modelAsString: true values: - value: function description: The tool call type is function. chatCompletionRequestMessageTool: allOf: - $ref: "#/components/schemas/chatCompletionRequestMessage" - type: object nullable: true properties: tool_call_id: type: string description: Tool call that this message is responding to. content: type: string description: The contents of the message. nullable: true required: - tool_call_id - content chatCompletionRequestMessageFunction: allOf: - $ref: "#/components/schemas/chatCompletionRequestMessage" - type: object description: Deprecated. Message that represents a function. nullable: true properties: role: type: string enum: - function description: The role of the messages author, in this case `function`. name: type: string description: The contents of the message. content: type: string description: The contents of the message. nullable: true required: - function_call_id - content createChatCompletionResponse: type: object description: Represents a chat completion response returned by model, based on the provided input. properties: id: type: string description: A unique identifier for the chat completion. prompt_filter_results: $ref: "#/components/schemas/promptFilterResults" choices: type: array description: A list of chat completion choices. Can be more than one if `n` is greater than 1. items: type: object required: - finish_reason - index - message - logprobs properties: finish_reason: type: string description: &chat_completion_finish_reason_description | The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, `length` if the maximum number of tokens specified in the request was reached, `content_filter` if content was omitted due to a flag from our content filters, `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function. enum: [ "stop", "length", "tool_calls", "content_filter", "function_call", ] index: type: integer description: The index of the choice in the list of choices. message: $ref: "#/components/schemas/chatCompletionResponseMessage" content_filter_results: $ref: "#/components/schemas/contentFilterChoiceResults" logprobs: &chat_completion_response_logprobs description: Log probability information for the choice. type: object nullable: true properties: content: description: A list of message content tokens with log probability information. type: array items: $ref: "#/components/schemas/chatCompletionTokenLogprob" nullable: true refusal: description: A list of message refusal tokens with log probability information. type: array items: $ref: "#/components/schemas/chatCompletionTokenLogprob" nullable: true required: - content - refusal created: type: integer description: The Unix timestamp (in seconds) of when the chat completion was created. model: type: string description: The model used for the chat completion. system_fingerprint: type: string description: | This fingerprint represents the backend configuration that the model runs with. Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism. object: type: string description: The object type, which is always `chat.completion`. enum: [chat.completion] usage: $ref: "#/components/schemas/completionUsage" required: - choices - created - id - model - object createChatCompletionStreamResponse: type: object description: Represents a streamed chunk of a chat completion response returned by model, based on the provided input. properties: id: type: string description: A unique identifier for the chat completion. Each chunk has the same ID. choices: type: array description: | A list of chat completion choices. Can contain more than one elements if `n` is greater than 1. items: type: object required: - delta - finish_reason - index properties: delta: $ref: "#/components/schemas/chatCompletionStreamResponseDelta" logprobs: *chat_completion_response_logprobs finish_reason: type: string description: *chat_completion_finish_reason_description enum: [ "stop", "length", "tool_calls", "content_filter", "function_call", ] nullable: true index: type: integer description: The index of the choice in the list of choices. created: type: integer description: The Unix timestamp (in seconds) of when the chat completion was created. Each chunk has the same timestamp. model: type: string description: The model to generate the completion. system_fingerprint: type: string description: | This fingerprint represents the backend configuration that the model runs with. Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism. object: type: string description: The object type, which is always `chat.completion.chunk`. enum: [chat.completion.chunk] required: - prompt_tokens - completion_tokens - total_tokens required: - choices - created - id - model - object chatCompletionStreamResponseDelta: type: object description: A chat completion delta generated by streamed model responses. properties: content: type: string description: The contents of the chunk message. nullable: true function_call: deprecated: true type: object description: "Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model." properties: arguments: type: string description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. name: type: string description: The name of the function to call. tool_calls: type: array items: $ref: "#/components/schemas/chatCompletionMessageToolCallChunk" role: type: string enum: ["system", "user", "assistant", "tool"] description: The role of the author of this message. refusal: type: string description: The refusal message generated by the model. nullable: true chatCompletionMessageToolCallChunk: type: object properties: index: type: integer id: type: string description: The ID of the tool call. type: type: string enum: ["function"] description: The type of the tool. Currently, only `function` is supported. function: type: object properties: name: type: string description: The name of the function to call. arguments: type: string description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. required: - index chatCompletionStreamOptions: description: | Options for streaming response. Only set this when you set `stream: true`. type: object nullable: true default: null properties: include_usage: type: boolean description: | If set, an additional chunk will be streamed before the `data: [DONE]` message. The `usage` field on this chunk shows the token usage statistics for the entire request, and the `choices` field will always be an empty array. All other chunks will also include a `usage` field, but with a null value. chatCompletionChoiceLogProbs: description: Log probability information for the choice. type: object nullable: true properties: content: description: A list of message content tokens with log probability information. type: array items: $ref: "#/components/schemas/chatCompletionTokenLogprob" nullable: true refusal: description: A list of message refusal tokens with log probability information. type: array items: $ref: "#/components/schemas/chatCompletionTokenLogprob" nullable: true required: - content chatCompletionTokenLogprob: type: object properties: token: description: The token. type: string logprob: description: The log probability of this token. type: number bytes: description: A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be `null` if there is no bytes representation for the token. type: array items: type: integer nullable: true top_logprobs: description: List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested `top_logprobs` returned. type: array items: type: object properties: token: description: The token. type: string logprob: description: The log probability of this token. type: number bytes: description: A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be `null` if there is no bytes representation for the token. type: array items: type: integer nullable: true required: - token - logprob - bytes required: - token - logprob - bytes - top_logprobs chatCompletionResponseMessage: type: object description: A chat completion message generated by the model. properties: role: $ref: "#/components/schemas/chatCompletionResponseMessageRole" refusal: type: string description: The refusal message generated by the model. nullable: true content: type: string description: The contents of the message. nullable: true tool_calls: type: array description: The tool calls generated by the model, such as function calls. items: $ref: "#/components/schemas/chatCompletionMessageToolCall" function_call: $ref: "#/components/schemas/chatCompletionFunctionCall" context: $ref: "#/components/schemas/azureChatExtensionsMessageContext" required: - role - content - refusal chatCompletionResponseMessageRole: type: string enum: - assistant description: The role of the author of the response message. chatCompletionToolChoiceOption: description: | Controls which (if any) tool is called by the model. `none` means the model will not call any tool and instead generates a message. `auto` means the model can pick between generating a message or calling one or more tools. `required` means the model must call one or more tools. Specifying a particular tool via `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that tool. `none` is the default when no tools are present. `auto` is the default if tools are present. oneOf: - type: string description: > `none` means the model will not call any tool and instead generates a message. `auto` means the model can pick between generating a message or calling one or more tools. `required` means the model must call one or more tools. enum: - none - auto - required - $ref: "#/components/schemas/chatCompletionNamedToolChoice" chatCompletionNamedToolChoice: type: object description: Specifies a tool the model should use. Use to force the model to call a specific function. properties: type: type: string enum: - "function" description: The type of the tool. Currently, only `function` is supported. function: type: object properties: name: type: string description: The name of the function to call. required: - name required: - type - function ParallelToolCalls: description: Whether to enable parallel function calling during tool use. type: boolean default: true chatCompletionMessageToolCalls: type: array description: The tool calls generated by the model, such as function calls. items: $ref: "#/components/schemas/chatCompletionMessageToolCall" chatCompletionFunctionCall: type: object description: Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model. properties: name: type: string description: The name of the function to call. arguments: type: string description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. required: - name - arguments completionUsage: type: object description: Usage statistics for the completion request. properties: prompt_tokens: type: integer description: Number of tokens in the prompt. completion_tokens: type: integer description: Number of tokens in the generated completion. total_tokens: type: integer description: Total number of tokens used in the request (prompt + completion). completion_tokens_details: type: object description: Breakdown of tokens used in a completion. properties: reasoning_tokens: type: integer description: Tokens generated by the model for reasoning. required: - prompt_tokens - completion_tokens - total_tokens chatCompletionTool: type: object properties: type: type: string enum: ["function"] description: The type of the tool. Currently, only `function` is supported. function: $ref: "#/components/schemas/FunctionObject" required: - type - function FunctionParameters: type: object description: "The parameters the functions accepts, described as a JSON Schema object. See the guide](https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema/) for documentation about the format. \n\nOmitting `parameters` defines a function with an empty parameter list." additionalProperties: true FunctionObject: type: object properties: description: type: string description: A description of what the function does, used by the model to choose when and how to call the function. name: type: string description: The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. parameters: $ref: "#/components/schemas/FunctionParameters" strict: type: boolean nullable: true default: false description: Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the `parameters` field. Only a subset of JSON Schema is supported when `strict` is `true`. Learn more about Structured Outputs in the [function calling guide](docs/guides/function-calling). required: - name ResponseFormatText: type: object properties: type: type: string description: "The type of response format being defined: `text`" enum: ["text"] required: - type ResponseFormatJsonObject: type: object properties: type: type: string description: "The type of response format being defined: `json_object`" enum: ["json_object"] required: - type ResponseFormatJsonSchemaSchema: type: object description: "The schema for the response format, described as a JSON Schema object." additionalProperties: true ResponseFormatJsonSchema: type: object properties: type: type: string description: "The type of response format being defined: `json_schema`" enum: ["json_schema"] json_schema: type: object properties: description: type: string description: A description of what the response format is for, used by the model to determine how to respond in the format. name: type: string description: The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. schema: $ref: "#/components/schemas/ResponseFormatJsonSchemaSchema" strict: type: boolean nullable: true default: false description: Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the `schema` field. Only a subset of JSON Schema is supported when `strict` is `true`. required: - type - name required: - type - json_schema chatCompletionChoiceCommon: type: object properties: index: type: integer finish_reason: type: string createTranslationRequest: type: object description: Translation request. properties: file: type: string description: The audio file to translate. format: binary prompt: type: string description: An optional text to guide the model's style or continue a previous audio segment. The prompt should be in English. response_format: $ref: "#/components/schemas/audioResponseFormat" temperature: type: number default: 0 description: The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit. required: - file audioResponse: description: Translation or transcription response when response_format was json type: object properties: text: type: string description: Translated or transcribed text. required: - text audioVerboseResponse: description: Translation or transcription response when response_format was verbose_json type: object allOf: - $ref: "#/components/schemas/audioResponse" - properties: task: type: string description: Type of audio task. enum: - transcribe - translate x-ms-enum: modelAsString: true language: type: string description: Language. duration: type: number description: Duration. segments: type: array items: $ref: "#/components/schemas/audioSegment" words: type: array items: $ref: "#/components/schemas/audioWord" required: - text audioResponseFormat: title: AudioResponseFormat description: Defines the format of the output. enum: - json - text - srt - verbose_json - vtt type: string x-ms-enum: modelAsString: true createTranscriptionRequest: type: object description: Transcription request. properties: file: type: string description: The audio file object to transcribe. format: binary prompt: type: string description: An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language. response_format: $ref: "#/components/schemas/audioResponseFormat" temperature: type: number default: 0 description: The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit. language: type: string description: The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency. timestamp_granularities[]: description: | The timestamp granularities to populate for this transcription. `response_format` must be set `verbose_json` to use timestamp granularities. Either or both of these options are supported: `word`, or `segment`. Note: There is no additional latency for segment timestamps, but generating word timestamps incurs additional latency. type: array items: type: string enum: - word - segment default: [segment] required: - file audioSegment: type: object description: Transcription or translation segment. properties: id: type: integer description: Segment identifier. seek: type: number description: Offset of the segment. start: type: number description: Segment start offset. end: type: number description: Segment end offset. text: type: string description: Segment text. tokens: type: array items: type: number nullable: false description: Tokens of the text. temperature: type: number description: Temperature. avg_logprob: type: number description: Average log probability. compression_ratio: type: number description: Compression ratio. no_speech_prob: type: number description: Probability of 'no speech'. audioWord: type: object description: Transcription or translation word. properties: word: type: string description: Word start: type: number description: Word start offset. end: type: number description: Word end offset. createSpeechRequest: type: object description: Speech request. properties: input: type: string description: The text to synthesize audio for. The maximum length is 4096 characters. maxLength: 4096 voice: type: string description: The voice to use for speech synthesis. enum: - alloy - echo - fable - onyx - nova - shimmer response_format: type: string description: The format to synthesize the audio in. enum: - mp3 - opus - aac - flac - wav - pcm speed: description: The speed of the synthesize audio. Select a value from `0.25` to `4.0`. `1.0` is the default. type: number default: 1 minimum: 0.25 maximum: 4 required: - input - voice imageQuality: description: The quality of the image that will be generated. type: string enum: - standard - hd default: standard x-ms-enum: name: Quality modelAsString: true values: - value: standard description: Standard quality creates images with standard quality. name: Standard - value: hd description: HD quality creates images with finer details and greater consistency across the image. name: HD imagesResponseFormat: description: The format in which the generated images are returned. type: string enum: - url - b64_json default: url x-ms-enum: name: ImagesResponseFormat modelAsString: true values: - value: url description: The URL that provides temporary access to download the generated images. name: Url - value: b64_json description: The generated images are returned as base64 encoded string. name: Base64Json imageSize: description: The size of the generated images. type: string enum: - 256x256 - 512x512 - 1792x1024 - 1024x1792 - 1024x1024 default: 1024x1024 x-ms-enum: name: Size modelAsString: true values: - value: 256x256 description: The desired size of the generated image is 256x256 pixels. Only supported for dall-e-2. name: Size256x256 - value: 512x512 description: The desired size of the generated image is 512x512 pixels. Only supported for dall-e-2. name: Size512x512 - value: 1792x1024 description: The desired size of the generated image is 1792x1024 pixels. Only supported for dall-e-3. name: Size1792x1024 - value: 1024x1792 description: The desired size of the generated image is 1024x1792 pixels. Only supported for dall-e-3. name: Size1024x1792 - value: 1024x1024 description: The desired size of the generated image is 1024x1024 pixels. name: Size1024x1024 imageStyle: description: The style of the generated images. type: string enum: - vivid - natural default: vivid x-ms-enum: name: Style modelAsString: true values: - value: vivid description: Vivid creates images that are hyper-realistic and dramatic. name: Vivid - value: natural description: Natural creates images that are more natural and less hyper-realistic. name: Natural imageGenerationsRequest: type: object properties: prompt: description: A text description of the desired image(s). The maximum length is 4000 characters. type: string format: string example: a corgi in a field minLength: 1 "n": description: The number of images to generate. type: integer minimum: 1 maximum: 1 default: 1 size: $ref: "#/components/schemas/imageSize" response_format: $ref: "#/components/schemas/imagesResponseFormat" user: description: A unique identifier representing your end-user, which can help to monitor and detect abuse. type: string format: string example: user123456 quality: $ref: "#/components/schemas/imageQuality" style: $ref: "#/components/schemas/imageStyle" required: - prompt generateImagesResponse: type: object properties: created: type: integer format: unixtime description: The unix timestamp when the operation was created. example: "1676540381" data: type: array description: The result data of the operation, if successful items: $ref: "#/components/schemas/imageResult" required: - created - data imageResult: type: object description: The image url or encoded image if successful, and an error otherwise. properties: url: type: string description: The image url. example: https://www.contoso.com b64_json: type: string description: The base64 encoded image content_filter_results: $ref: "#/components/schemas/dalleContentFilterResults" revised_prompt: type: string description: The prompt that was used to generate the image, if there was any revision to the prompt. prompt_filter_results: $ref: "#/components/schemas/dalleFilterResults" line: type: object description: A content line object consisting of an adjacent sequence of content elements, such as words and selection marks. properties: text: type: string spans: type: array description: An array of spans that represent detected objects and its bounding box information. items: $ref: "#/components/schemas/span" required: - text - spans span: type: object description: A span object that represents a detected object and its bounding box information. properties: text: type: string description: The text content of the span that represents the detected object. offset: type: integer description: The character offset within the text where the span begins. This offset is defined as the position of the first character of the span, counting from the start of the text as Unicode codepoints. length: type: integer description: The length of the span in characters, measured in Unicode codepoints. polygon: type: array description: An array of objects representing points in the polygon that encloses the detected object. items: type: object properties: x: type: number description: The x-coordinate of the point. "y": type: number description: The y-coordinate of the point. required: - text - offset - length - polygon runCompletionUsage: type: object description: Usage statistics related to the run. This value will be `null` if the run is not in a terminal state (i.e. `in_progress`, `queued`, etc.). properties: completion_tokens: type: integer description: Number of completion tokens used over the course of the run. prompt_tokens: type: integer description: Number of prompt tokens used over the course of the run. total_tokens: type: integer description: Total number of tokens used (prompt + completion). required: - prompt_tokens - completion_tokens - total_tokens nullable: true runStepCompletionUsage: type: object description: Usage statistics related to the run step. This value will be `null` while the run step's status is `in_progress`. properties: completion_tokens: type: integer description: Number of completion tokens used over the course of the run step. prompt_tokens: type: integer description: Number of prompt tokens used over the course of the run step. total_tokens: type: integer description: Total number of tokens used (prompt + completion). required: - prompt_tokens - completion_tokens - total_tokens nullable: true assistantsApiResponseFormatOption: description: | Specifies the format that the model must output. Compatible with GPT-4 Turbo and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`. Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the message the model generates is valid JSON. **Important:** when using JSON mode, you **must** also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length. oneOf: - type: string description: > `auto` is the default value enum: [none, auto] x-ms-enum: name: AssistantsApiResponseFormatOption modelAsString: true values: - value: none - value: auto - $ref: "#/components/schemas/assistantsApiResponseFormat" assistantsApiResponseFormat: type: object description: | An object describing the expected output of the model. If `json_object` only `function` type `tools` are allowed to be passed to the Run. If `text` the model can return text or any value needed. properties: type: type: string enum: ["text", "json_object"] x-ms-enum: name: AssistantsApiResponseFormat modelAsString: true values: - value: text - value: json_object example: "json_object" default: "text" description: Must be one of `text` or `json_object`. assistantObject: type: object title: Assistant description: Represents an `assistant` that can call the model and use tools. properties: id: description: The identifier, which can be referenced in API endpoints. type: string object: description: The object type, which is always `assistant`. type: string enum: - assistant x-ms-enum: name: AssistantObjectType modelAsString: true values: - value: assistant created_at: type: integer description: The Unix timestamp (in seconds) for when the assistant was created. name: description: &assistant_name_param_description | The name of the assistant. The maximum length is 256 characters. type: string maxLength: 256 nullable: true description: description: &assistant_description_param_description | The description of the assistant. The maximum length is 512 characters. type: string maxLength: 512 nullable: true model: description: | ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models/overview) for descriptions of them. type: string instructions: description: &assistant_instructions_param_description | The system instructions that the assistant uses. The maximum length is 256,000 characters. type: string maxLength: 256000 nullable: true tools: description: &assistant_tools_param_description | A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types `code_interpreter`, `file_search`, or `function`. default: [] type: array maxItems: 128 items: oneOf: - $ref: "#/components/schemas/assistantToolsCode" - $ref: "#/components/schemas/assistantToolsFileSearch" - $ref: "#/components/schemas/assistantToolsFunction" tool_resources: type: object description: | A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs. properties: code_interpreter: type: object properties: file_ids: type: array description: | A list of file IDs made available to the `code_interpreter`` tool. There can be a maximum of 20 files associated with the tool. default: [] maxItems: 20 items: type: string file_search: type: object properties: vector_store_ids: type: array description: | The ID of the vector store attached to this assistant. There can be a maximum of 1 vector store attached to the assistant. maxItems: 1 items: type: string metadata: description: &metadata_description | Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maximum of 512 characters long. type: object nullable: true temperature: description: &run_temperature_description | What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. type: number minimum: 0 maximum: 2 default: 1 example: 1 nullable: true top_p: type: number minimum: 0 maximum: 1 default: 1 example: 1 nullable: true description: &run_top_p_description | An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. response_format: $ref: "#/components/schemas/assistantsApiResponseFormatOption" nullable: true required: - id - object - created_at - name - description - model - instructions - tools - metadata createAssistantRequest: type: object additionalProperties: false properties: model: description: | ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models/overview) for descriptions of them. anyOf: - type: string name: description: *assistant_name_param_description type: string nullable: true maxLength: 256 description: description: *assistant_description_param_description type: string nullable: true maxLength: 512 instructions: description: *assistant_instructions_param_description type: string nullable: true maxLength: 256000 tools: description: *assistant_tools_param_description default: [] type: array maxItems: 128 items: oneOf: - $ref: "#/components/schemas/assistantToolsCode" - $ref: "#/components/schemas/assistantToolsFileSearch" - $ref: "#/components/schemas/assistantToolsFunction" tool_resources: type: object description: | A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs. properties: code_interpreter: type: object properties: file_ids: type: array description: | A list of file IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool. default: [] maxItems: 20 items: type: string file_search: type: object properties: vector_store_ids: type: array description: | The vector store attached to this assistant. There can be a maximum of 1 vector store attached to the assistant. maxItems: 1 items: type: string vector_stores: type: array description: | A helper to create a vector store with file_ids and attach it to this assistant. There can be a maximum of 1 vector store attached to the assistant. maxItems: 1 items: type: object properties: file_ids: type: array description: | A list of file IDs to add to the vector store. There can be a maximum of 10000 files in a vector store. maxItems: 10000 items: type: string chunking_strategy: # Ideally we'd reuse the chunking strategy schema here, but it doesn't expand properly type: object description: The chunking strategy used to chunk the file(s). If not set, will use the `auto` strategy. oneOf: - type: object title: Auto Chunking Strategy description: The default strategy. This strategy currently uses a `max_chunk_size_tokens` of `800` and `chunk_overlap_tokens` of `400`. additionalProperties: false properties: type: type: string description: Always `auto`. enum: ["auto"] x-ms-enum: name: AutoChunkingStrategyType modelAsString: true values: - value: auto required: - type - type: object title: Static Chunking Strategy additionalProperties: false properties: type: type: string description: Always `static`. enum: ["static"] x-ms-enum: name: StaticChunkingStrategyType modelAsString: true values: - value: static static: type: object additionalProperties: false properties: max_chunk_size_tokens: type: integer minimum: 100 maximum: 4096 description: The maximum number of tokens in each chunk. The default value is `800`. The minimum value is `100` and the maximum value is `4096`. chunk_overlap_tokens: type: integer description: | The number of tokens that overlap between chunks. The default value is `400`. Note that the overlap must not exceed half of `max_chunk_size_tokens`. required: - max_chunk_size_tokens - chunk_overlap_tokens required: - type - static metadata: type: object description: | Set of 16 key-value pairs that can be attached to a vector store. This can be useful for storing additional information about the vector store in a structured format. Keys can be a maximum of 64 characters long and values can be a maximum of 512 characters long. oneOf: - required: [vector_store_ids] - required: [vector_stores] nullable: true metadata: description: *metadata_description type: object nullable: true temperature: description: *run_temperature_description type: number minimum: 0 maximum: 2 default: 1 example: 1 nullable: true top_p: type: number minimum: 0 maximum: 1 default: 1 example: 1 nullable: true description: *run_top_p_description response_format: $ref: "#/components/schemas/assistantsApiResponseFormatOption" nullable: true required: - model modifyAssistantRequest: type: object additionalProperties: false properties: model: description: | ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models/overview) for descriptions of them. anyOf: - type: string name: description: | The name of the assistant. The maximum length is 256 characters. type: string nullable: true maxLength: 256 description: description: | The description of the assistant. The maximum length is 512 characters. type: string nullable: true maxLength: 512 instructions: description: | The system instructions that the assistant uses. The maximum length is 32768 characters. type: string nullable: true maxLength: 32768 tools: description: | A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types `code_interpreter`, `retrieval`, or `function`. default: [] type: array maxItems: 128 items: oneOf: - $ref: "#/components/schemas/assistantToolsCode" - $ref: "#/components/schemas/assistantToolsFileSearch" - $ref: "#/components/schemas/assistantToolsFunction" tool_resources: type: object description: | A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs. properties: code_interpreter: type: object properties: file_ids: type: array description: | Overrides the list of file IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool. default: [] maxItems: 20 items: type: string file_search: type: object properties: vector_store_ids: type: array description: | Overrides the vector store attached to this assistant. There can be a maximum of 1 vector store attached to the assistant. maxItems: 1 items: type: string metadata: description: *metadata_description type: object nullable: true temperature: description: *run_temperature_description type: number minimum: 0 maximum: 2 default: 1 example: 1 nullable: true top_p: type: number minimum: 0 maximum: 1 default: 1 example: 1 nullable: true description: *run_top_p_description response_format: $ref: "#/components/schemas/assistantsApiResponseFormatOption" nullable: true deleteAssistantResponse: type: object properties: id: type: string deleted: type: boolean object: type: string enum: - assistant.deleted x-ms-enum: name: DeleteAssistantResponseState modelAsString: true values: - value: assistant.deleted required: - id - object - deleted listAssistantsResponse: type: object properties: object: type: string example: list data: type: array items: $ref: "#/components/schemas/assistantObject" first_id: type: string example: asst_hLBK7PXBv5Lr2NQT7KLY0ag1 last_id: type: string example: asst_QLoItBbqwyAJEzlTy4y9kOMM has_more: type: boolean example: false required: - object - data - first_id - last_id - has_more assistantToolsCode: type: object title: Code interpreter tool properties: type: type: string description: "The type of tool being defined: `code_interpreter`" enum: - code_interpreter x-ms-enum: name: assistantToolsCodeType modelAsString: true values: - value: code_interpreter required: - type assistantToolsFileSearch: type: object title: FileSearch tool properties: type: type: string description: "The type of tool being defined: `file_search`" enum: - file_search x-ms-enum: name: assistantToolsFileSearchType modelAsString: true values: - value: file_search file_search: type: object description: Overrides for the file search tool. properties: max_num_results: type: integer minimum: 1 maximum: 50 description: | The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive. Note that the file search tool may output fewer than `max_num_results` results. See the [file search tool documentation](/docs/assistants/tools/file-search/number-of-chunks-returned) for more information. required: - type assistantToolsFileSearchTypeOnly: type: object title: FileSearch tool properties: type: type: string description: "The type of tool being defined: `file_search`" enum: - file_search x-ms-enum: name: assistantToolsFileSearchType modelAsString: true values: - value: file_search required: - type assistantToolsFunction: type: object title: Function tool properties: type: type: string description: "The type of tool being defined: `function`" enum: - function x-ms-enum: name: assistantToolsFunction modelAsString: true values: - value: function function: type: object description: The function definition. properties: description: type: string description: A description of what the function does, used by the model to choose when and how to call the function. name: type: string description: The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. parameters: $ref: "#/components/schemas/chatCompletionFunctionParameters" required: - name - parameters - description required: - type - function truncationObject: type: object title: Thread Truncation Controls description: Controls for how a thread will be truncated prior to the run. Use this to control the intial context window of the run. properties: type: type: string description: The truncation strategy to use for the thread. The default is `auto`. If set to `last_messages`, the thread will be truncated to the n most recent messages in the thread. When set to `auto`, messages in the middle of the thread will be dropped to fit the context length of the model, `max_prompt_tokens`. enum: ["auto", "last_messages"] x-ms-enum: name: TruncationType modelAsString: true values: - value: auto - value: last_messages last_messages: type: integer description: The number of most recent messages from the thread when constructing the context for the run. minimum: 1 nullable: true required: - type assistantsApiToolChoiceOption: description: | Controls which (if any) tool is called by the model. `none` means the model will not call any tools and instead generates a message. `auto` is the default value and means the model can pick between generating a message or calling a tool. Specifying a particular tool like `{"type": "file_search"}` or `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that tool. oneOf: - type: string description: > `none` means the model will not call a function and instead generates a message. `auto` means the model can pick between generating a message or calling a function. enum: [none, auto] x-ms-enum: name: AssistantsApiToolChoiceOption modelAsString: true values: - value: none - value: auto - $ref: "#/components/schemas/assistantsNamedToolChoice" assistantsNamedToolChoice: type: object description: Specifies a tool the model should use. Use to force the model to call a specific tool. properties: type: type: string enum: ["function", "code_interpreter", "file_search"] description: The type of the tool. If type is `function`, the function name must be set x-ms-enum: name: AssistantsNamedToolChoiceType modelAsString: true values: - value: function - value: code_interpreter - value: file_search function: type: object properties: name: type: string description: The name of the function to call. required: - name required: - type runObject: type: object title: A run on a thread description: Represents an execution run on a [thread](/docs/api-reference/threads). properties: id: description: The identifier, which can be referenced in API endpoints. type: string object: description: The object type, which is always `thread.run`. type: string enum: - thread.run x-ms-enum: name: runObjectType modelAsString: true values: - value: thread.run description: The run object type which is always thread.run created_at: description: The Unix timestamp (in seconds) for when the run was created. type: integer thread_id: description: The ID of the [thread](/docs/api-reference/threads) that was executed on as a part of this run. type: string assistant_id: description: The ID of the assistant used for execution of this run. type: string status: description: The status of the run, which can be either `queued`, `in_progress`, `requires_action`, `cancelling`, `cancelled`, `failed`, `completed`, or `expired`. type: string enum: - queued - in_progress - requires_action - cancelling - cancelled - failed - completed - expired x-ms-enum: name: RunObjectStatus modelAsString: true values: - value: queued description: The queued state - value: in_progress description: The in_progress state - value: requires_action description: The required_action state - value: cancelling description: The cancelling state - value: cancelled description: The cancelled state - value: failed description: The failed state - value: completed description: The completed state - value: expired description: The expired state required_action: type: object description: Details on the action required to continue the run. Will be `null` if no action is required. nullable: true properties: type: description: For now, this is always `submit_tool_outputs`. type: string enum: - submit_tool_outputs submit_tool_outputs: type: object description: Details on the tool outputs needed for this run to continue. properties: tool_calls: type: array description: A list of the relevant tool calls. items: $ref: "#/components/schemas/runToolCallObject" required: - tool_calls required: - type - submit_tool_outputs last_error: type: object description: The last error associated with this run. Will be `null` if there are no errors. nullable: true properties: code: type: string description: One of `server_error` or `rate_limit_exceeded`. enum: - server_error - rate_limit_exceeded x-ms-enum: name: LastErrorCode modelAsString: true values: - value: server_error description: The server failed to respond to request due to server error - value: rate_limit_exceeded description: The server failed to respond to request due to rate limit exceeded message: type: string description: A human-readable description of the error. required: - code - message expires_at: description: The Unix timestamp (in seconds) for when the run will expire. type: integer started_at: description: The Unix timestamp (in seconds) for when the run was started. type: integer nullable: true cancelled_at: description: The Unix timestamp (in seconds) for when the run was cancelled. type: integer nullable: true failed_at: description: The Unix timestamp (in seconds) for when the run failed. type: integer nullable: true completed_at: description: The Unix timestamp (in seconds) for when the run was completed. type: integer nullable: true incomplete_details: description: Details on why the run is incomplete. Will be `null` if the run is not incomplete. type: object nullable: true properties: reason: description: The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run. type: string enum: ["max_completion_tokens", "max_prompt_tokens"] x-ms-enum: name: IncompleteDetailsReason modelAsString: true values: - value: max_completion_tokens - value: max_prompt_tokens model: description: The model that the assistant used for this run. type: string instructions: description: The instructions that the assistant used for this run. type: string tools: description: The list of tools that the assistant used for this run. default: [] type: array maxItems: 20 items: oneOf: - $ref: "#/components/schemas/assistantToolsCode" - $ref: "#/components/schemas/assistantToolsFileSearch" - $ref: "#/components/schemas/assistantToolsFunction" metadata: description: *metadata_description type: object nullable: true usage: $ref: "#/components/schemas/runCompletionUsage" temperature: description: The sampling temperature used for this run. If not set, defaults to 1. type: number nullable: true top_p: description: The nucleus sampling value used for this run. If not set, defaults to 1. type: number nullable: true max_prompt_tokens: type: integer nullable: true description: | The maximum number of prompt tokens specified to have been used over the course of the run. minimum: 256 max_completion_tokens: type: integer nullable: true description: | The maximum number of completion tokens specified to have been used over the course of the run. minimum: 256 truncation_strategy: $ref: "#/components/schemas/truncationObject" nullable: true tool_choice: $ref: "#/components/schemas/assistantsApiToolChoiceOption" nullable: true parallel_tool_calls: $ref: "#/components/schemas/ParallelToolCalls" response_format: $ref: "#/components/schemas/assistantsApiResponseFormatOption" nullable: true required: - id - object - created_at - thread_id - assistant_id - status - required_action - last_error - expires_at - started_at - cancelled_at - failed_at - completed_at - model - instructions - tools - metadata - usage - incomplete_details - max_prompt_tokens - max_completion_tokens - truncation_strategy - tool_choice - response_format createRunRequest: type: object additionalProperties: false properties: assistant_id: description: The ID of the assistant to use to execute this run. type: string model: description: The ID of the Model to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used. type: string nullable: true instructions: description: Override the default system message of the assistant. This is useful for modifying the behavior on a per-run basis. type: string nullable: true additional_instructions: description: Appends additional instructions at the end of the instructions for the run. This is useful for modifying the behavior on a per-run basis without overriding other instructions. type: string nullable: true additional_messages: description: Adds additional messages to the thread before creating the run. type: array items: $ref: "#/components/schemas/createMessageRequest" nullable: true tools: description: Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis. nullable: true type: array maxItems: 20 items: oneOf: - $ref: "#/components/schemas/assistantToolsCode" - $ref: "#/components/schemas/assistantToolsFileSearch" - $ref: "#/components/schemas/assistantToolsFunction" metadata: description: *metadata_description type: object nullable: true temperature: type: number minimum: 0 maximum: 2 default: 1 example: 1 nullable: true description: *run_temperature_description top_p: type: number minimum: 0 maximum: 1 default: 1 example: 1 nullable: true description: *run_top_p_description stream: type: boolean nullable: true description: | If `true`, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a `data: [DONE]` message. max_prompt_tokens: type: integer nullable: true description: | The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status `incomplete`. See `incomplete_details` for more info. minimum: 256 max_completion_tokens: type: integer nullable: true description: | The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status `incomplete`. See `incomplete_details` for more info. minimum: 256 truncation_strategy: $ref: "#/components/schemas/truncationObject" nullable: true tool_choice: $ref: "#/components/schemas/assistantsApiToolChoiceOption" nullable: true parallel_tool_calls: $ref: "#/components/schemas/ParallelToolCalls" response_format: $ref: "#/components/schemas/assistantsApiResponseFormatOption" nullable: true required: - thread_id - assistant_id listRunsResponse: type: object properties: object: type: string example: list data: type: array items: $ref: "#/components/schemas/runObject" first_id: type: string example: run_hLBK7PXBv5Lr2NQT7KLY0ag1 last_id: type: string example: run_QLoItBbqwyAJEzlTy4y9kOMM has_more: type: boolean example: false required: - object - data - first_id - last_id - has_more modifyRunRequest: type: object additionalProperties: false properties: metadata: description: *metadata_description type: object nullable: true submitToolOutputsRunRequest: type: object additionalProperties: false properties: tool_outputs: description: A list of tools for which the outputs are being submitted. type: array items: type: object properties: tool_call_id: type: string description: The ID of the tool call in the `required_action` object within the run object the output is being submitted for. output: type: string description: The output of the tool call to be submitted to continue the run. stream: type: boolean nullable: true description: | If `true`, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a `data: [DONE]` message. required: - tool_outputs runToolCallObject: type: object description: Tool call objects properties: id: type: string description: The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the [Submit tool outputs to run](/docs/api-reference/runs/submitToolOutputs) endpoint. type: type: string description: The type of tool call the output is required for. For now, this is always `function`. enum: - function x-ms-enum: name: RunToolCallObjectType modelAsString: true values: - value: function function: type: object description: The function definition. properties: name: type: string description: The name of the function. arguments: type: string description: The arguments that the model expects you to pass to the function. required: - name - arguments required: - id - type - function createThreadAndRunRequest: type: object additionalProperties: false properties: assistant_id: description: The ID of the assistant to use to execute this run. type: string thread: $ref: "#/components/schemas/createThreadRequest" description: If no thread is provided, an empty thread will be created. model: description: The ID of the [Model](/docs/api-reference/models) to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used. type: string nullable: true instructions: description: Override the default system message of the assistant. This is useful for modifying the behavior on a per-run basis. type: string nullable: true tools: description: Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis. nullable: true type: array maxItems: 20 items: oneOf: - $ref: "#/components/schemas/assistantToolsCode" - $ref: "#/components/schemas/assistantToolsFileSearch" - $ref: "#/components/schemas/assistantToolsFunction" tool_resources: type: object description: | A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs. properties: code_interpreter: type: object properties: file_ids: type: array description: | A list of file IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool. default: [] maxItems: 20 items: type: string file_search: type: object properties: vector_store_ids: type: array description: | The ID of the vector store attached to this assistant. There can be a maximum of 1 vector store attached to the assistant. maxItems: 1 items: type: string nullable: true metadata: description: *metadata_description type: object nullable: true temperature: type: number minimum: 0 maximum: 2 default: 1 example: 1 nullable: true description: *run_temperature_description top_p: type: number minimum: 0 maximum: 1 default: 1 example: 1 nullable: true description: *run_top_p_description stream: type: boolean nullable: true description: | If `true`, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a `data: [DONE]` message. max_prompt_tokens: type: integer nullable: true description: | The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status `incomplete`. See `incomplete_details` for more info. minimum: 256 max_completion_tokens: type: integer nullable: true description: | The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status `incomplete`. See `incomplete_details` for more info. minimum: 256 truncation_strategy: $ref: "#/components/schemas/truncationObject" nullable: true tool_choice: $ref: "#/components/schemas/assistantsApiToolChoiceOption" nullable: true parallel_tool_calls: $ref: "#/components/schemas/ParallelToolCalls" response_format: $ref: "#/components/schemas/assistantsApiResponseFormatOption" nullable: true required: - thread_id - assistant_id threadObject: type: object title: Thread description: Represents a thread that contains [messages](/docs/api-reference/messages). properties: id: description: The identifier, which can be referenced in API endpoints. type: string object: description: The object type, which is always `thread`. type: string enum: - thread x-ms-enum: name: ThreadObjectType modelAsString: true values: - value: thread description: The type of thread object which is always `thread` created_at: description: The Unix timestamp (in seconds) for when the thread was created. type: integer tool_resources: type: object description: | A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs. properties: code_interpreter: type: object properties: file_ids: type: array description: | A list of file IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool. default: [] maxItems: 20 items: type: string file_search: type: object properties: vector_store_ids: type: array description: | The vector store attached to this thread. There can be a maximum of 1 vector store attached to the thread. maxItems: 1 items: type: string nullable: true metadata: description: *metadata_description type: object nullable: true required: - id - object - created_at - tool_resources - metadata createThreadRequest: type: object additionalProperties: false properties: messages: description: A list of messages to start the thread with. type: array items: $ref: "#/components/schemas/createMessageRequest" tool_resources: type: object description: | A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs. properties: code_interpreter: type: object properties: file_ids: type: array description: | A list of file IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool. default: [] maxItems: 20 items: type: string file_search: type: object properties: vector_store_ids: type: array description: | The vector store attached to this thread. There can be a maximum of 1 vector store attached to the thread. maxItems: 1 items: type: string vector_stores: type: array description: | A helper to create a vector store with file_ids and attach it to this thread. There can be a maximum of 1 vector store attached to the thread. maxItems: 1 items: type: object properties: file_ids: type: array description: | A list of file IDs to add to the vector store. There can be a maximum of 10000 files in a vector store. maxItems: 10000 items: type: string chunking_strategy: # Ideally we'd reuse the chunking strategy schema here, but it doesn't expand properly type: object description: The chunking strategy used to chunk the file(s). If not set, will use the `auto` strategy. oneOf: - type: object title: Auto Chunking Strategy description: The default strategy. This strategy currently uses a `max_chunk_size_tokens` of `800` and `chunk_overlap_tokens` of `400`. additionalProperties: false properties: type: type: string description: Always `auto`. enum: ["auto"] x-ms-enum: name: AutoChunkingStrategyType modelAsString: true values: - value: auto required: - type - type: object title: Static Chunking Strategy additionalProperties: false properties: type: type: string description: Always `static`. enum: ["static"] x-ms-enum: name: StaticChunkingStrategyType modelAsString: true values: - value: static static: type: object additionalProperties: false properties: max_chunk_size_tokens: type: integer minimum: 100 maximum: 4096 description: The maximum number of tokens in each chunk. The default value is `800`. The minimum value is `100` and the maximum value is `4096`. chunk_overlap_tokens: type: integer description: | The number of tokens that overlap between chunks. The default value is `400`. Note that the overlap must not exceed half of `max_chunk_size_tokens`. required: - max_chunk_size_tokens - chunk_overlap_tokens required: - type - static metadata: type: object description: | Set of 16 key-value pairs that can be attached to a vector store. This can be useful for storing additional information about the vector store in a structured format. Keys can be a maximum of 64 characters long and values can be a maximum of 512 characters long. oneOf: - required: [vector_store_ids] - required: [vector_stores] nullable: true metadata: description: *metadata_description type: object nullable: true modifyThreadRequest: type: object additionalProperties: false properties: tool_resources: type: object description: | A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs. properties: code_interpreter: type: object properties: file_ids: type: array description: | A list of File IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool. default: [] maxItems: 20 items: type: string file_search: type: object properties: vector_store_ids: type: array description: | The vector store attached to this thread. There can be a maximum of 1 vector store attached to the thread. maxItems: 1 items: type: string nullable: true metadata: description: *metadata_description type: object nullable: true deleteThreadResponse: type: object properties: id: type: string deleted: type: boolean object: type: string enum: - thread.deleted x-ms-enum: name: DeleteThreadResponseObjectState modelAsString: true values: - value: thread.deleted description: The delete thread response object state which is `thread.deleted` required: - id - object - deleted listThreadsResponse: properties: object: type: string example: list data: type: array items: $ref: "#/components/schemas/threadObject" first_id: type: string example: asst_hLBK7PXBv5Lr2NQT7KLY0ag1 last_id: type: string example: asst_QLoItBbqwyAJEzlTy4y9kOMM has_more: type: boolean example: false required: - object - data - first_id - last_id - has_more messageObject: type: object title: The message object description: Represents a message within a [thread](/docs/api-reference/threads). properties: id: description: The identifier, which can be referenced in API endpoints. type: string object: description: The object type, which is always `thread.message`. type: string enum: - thread.message x-ms-enum: name: MessageObjectType modelAsString: true values: - value: thread.message description: The message object type which is `thread.message` created_at: description: The Unix timestamp (in seconds) for when the message was created. type: integer thread_id: description: The [thread](/docs/api-reference/threads) ID that this message belongs to. type: string status: description: The status of the message, which can be either `in_progress`, `incomplete`, or `completed`. type: string enum: ["in_progress", "incomplete", "completed"] x-ms-enum: name: MessageObjectStatus modelAsString: true values: - value: in_progress - value: incomplete - value: completed incomplete_details: description: On an incomplete message, details about why the message is incomplete. type: object properties: reason: type: string description: The reason the message is incomplete. enum: [ "content_filter", "max_tokens", "run_cancelled", "run_expired", "run_failed", ] x-ms-enum: name: MessageObjectIncompleteReason modelAsString: true values: - value: content_filter - value: max_tokens - value: run_cancelled - value: run_expired - value: run_failed nullable: true required: - reason completed_at: description: The Unix timestamp (in seconds) for when the message was completed. type: integer nullable: true incomplete_at: description: The Unix timestamp (in seconds) for when the message was marked as incomplete. type: integer nullable: true role: description: The entity that produced the message. One of `user` or `assistant`. type: string enum: - user - assistant x-ms-enum: name: MessageObjectRole modelAsString: true values: - value: user - value: assistant content: description: The content of the message in array of text and/or images. type: array items: oneOf: - $ref: "#/components/schemas/messageContentImageFileObject" - $ref: "#/components/schemas/messageContentTextObject" assistant_id: description: If applicable, the ID of the assistant that authored this message. type: string nullable: true run_id: description: If applicable, the ID of the [run](/docs/api-reference/runs) associated with the authoring of this message. type: string nullable: true attachments: type: array items: type: object properties: file_id: type: string description: The ID of the file to attach to the message. tools: description: The tools to add this file to. type: array items: oneOf: - $ref: "#/components/schemas/assistantToolsCode" - $ref: "#/components/schemas/assistantToolsFileSearchTypeOnly" description: A list of files attached to the message, and the tools they were added to. nullable: true metadata: description: *metadata_description type: object nullable: true required: - id - object - created_at - thread_id - status - incomplete_details - completed_at - incomplete_at - role - content - assistant_id - run_id - attachments - metadata messageDeltaObject: type: object title: Message delta object description: | Represents a message delta i.e. any changed fields on a message during streaming. properties: id: description: The identifier of the message, which can be referenced in API endpoints. type: string object: description: The object type, which is always `thread.message.delta`. type: string enum: ["thread.message.delta"] x-ms-enum: name: MessageDeltaObjectType modelAsString: true values: - value: thread.message.delta delta: description: The delta containing the fields that have changed on the Message. type: object properties: role: description: The entity that produced the message. One of `user` or `assistant`. type: string enum: ["user", "assistant"] x-ms-enum: name: MessageDeltaObjectDeltaRole modelAsString: true values: - value: user - value: assistant content: description: The content of the message in array of text and/or images. type: array items: oneOf: - $ref: "#/components/schemas/messageDeltaContentImageFileObject" - $ref: "#/components/schemas/messageDeltaContentTextObject" required: - id - object - delta createMessageRequest: type: object additionalProperties: false required: - role - content properties: role: type: string enum: - user - assistant x-ms-enum: name: CreateMessageRequestRole modelAsString: true values: - value: user - value: assistant description: | The role of the entity that is creating the message. Allowed values include: - `user`: Indicates the message is sent by an actual user and should be used in most cases to represent user-generated messages. - `assistant`: Indicates the message is generated by the assistant. Use this value to insert messages from the assistant into the conversation. content: type: string minLength: 1 maxLength: 256000 description: The content of the message. attachments: type: array items: type: object properties: file_id: type: string description: The ID of the file to attach to the message. tools: description: The tools to add this file to. type: array items: oneOf: - $ref: "#/components/schemas/assistantToolsCode" - $ref: "#/components/schemas/assistantToolsFileSearchTypeOnly" x-oaiExpandable: true description: A list of files attached to the message, and the tools they should be added to. required: - file_id - tools nullable: true metadata: description: *metadata_description type: object nullable: true modifyMessageRequest: type: object additionalProperties: false properties: metadata: description: *metadata_description type: object nullable: true deleteMessageResponse: type: object properties: id: type: string deleted: type: boolean object: type: string enum: - thread.message.deleted x-ms-enum: name: DeleteMessageResponseObject modelAsString: true values: - value: thread.message.deleted description: The delete message response object state required: - id - object - deleted listMessagesResponse: properties: object: type: string example: list data: type: array items: $ref: "#/components/schemas/messageObject" first_id: type: string example: msg_hLBK7PXBv5Lr2NQT7KLY0ag1 last_id: type: string example: msg_QLoItBbqwyAJEzlTy4y9kOMM has_more: type: boolean example: false required: - object - data - first_id - last_id - has_more messageContentImageFileObject: title: Image file type: object description: References an image file in the content of a message. properties: type: description: Always `image_file`. type: string enum: - image_file x-ms-enum: name: MessageContentImageFileObjectType modelAsString: true values: - value: image_file description: The message content image file type image_file: type: object properties: file_id: description: The file ID of the image in the message content. type: string required: - file_id required: - type - image_file messageContentTextObject: title: Text type: object description: The text content that is part of a message. properties: type: description: Always `text`. type: string enum: - text x-ms-enum: name: messageContentTextObjectType modelAsString: true values: - value: text description: The message content text Object type text: type: object properties: value: description: The data that makes up the text. type: string annotations: type: array items: oneOf: - $ref: "#/components/schemas/messageContentTextAnnotationsFileCitationObject" - $ref: "#/components/schemas/messageContentTextAnnotationsFilePathObject" required: - value - annotations required: - type - text messageContentTextAnnotationsFileCitationObject: title: File citation type: object description: A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the "retrieval" tool to search files. properties: type: description: Always `file_citation`. type: string enum: - file_citation x-ms-enum: name: FileCitationObjectType modelAsString: true values: - value: file_citation description: The file citation object type text: description: The text in the message content that needs to be replaced. type: string file_citation: type: object properties: file_id: description: The ID of the specific File the citation is from. type: string required: - file_id start_index: type: integer minimum: 0 end_index: type: integer minimum: 0 required: - type - text - file_citation - start_index - end_index messageContentTextAnnotationsFilePathObject: title: File path type: object description: A URL for the file that's generated when the assistant used the `code_interpreter` tool to generate a file. properties: type: description: Always `file_path`. type: string enum: - file_path x-ms-enum: name: FilePathObjectType modelAsString: true values: - value: file_path description: The file path object type text: description: The text in the message content that needs to be replaced. type: string file_path: type: object properties: file_id: description: The ID of the file that was generated. type: string required: - file_id start_index: type: integer minimum: 0 end_index: type: integer minimum: 0 required: - type - text - file_path - start_index - end_index messageDeltaContentImageFileObject: title: Image file type: object description: References an image File in the content of a message. properties: index: type: integer description: The index of the content part in the message. type: description: Always `image_file`. type: string enum: ["image_file"] x-ms-enum: name: MessageDeltaContentImageFileObjectType modelAsString: true values: - value: image_file image_file: type: object properties: file_id: description: The File ID of the image in the message content. type: string required: - index - type messageDeltaContentTextObject: title: Text type: object description: The text content that is part of a message. properties: index: type: integer description: The index of the content part in the message. type: description: Always `text`. type: string enum: ["text"] x-ms-enum: name: MessageDeltaContentTextObjectType modelAsString: true values: - value: text text: type: object properties: value: description: The data that makes up the text. type: string annotations: type: array items: oneOf: - $ref: "#/components/schemas/messageDeltaContentTextAnnotationsFileCitationObject" - $ref: "#/components/schemas/messageDeltaContentTextAnnotationsFilePathObject" required: - index - type messageDeltaContentTextAnnotationsFileCitationObject: title: File citation type: object description: A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the "file_search" tool to search files. properties: index: type: integer description: The index of the annotation in the text content part. type: description: Always `file_citation`. type: string enum: ["file_citation"] x-ms-enum: name: MessageDeltaContentTextAnnotationsFileCitationObjectType modelAsString: true values: - value: file_citation text: description: The text in the message content that needs to be replaced. type: string file_citation: type: object properties: file_id: description: The ID of the specific File the citation is from. type: string quote: description: The specific quote in the file. type: string start_index: type: integer minimum: 0 end_index: type: integer minimum: 0 required: - index - type messageDeltaContentTextAnnotationsFilePathObject: title: File path type: object description: A URL for the file that's generated when the assistant used the `code_interpreter` tool to generate a file. properties: index: type: integer description: The index of the annotation in the text content part. type: description: Always `file_path`. type: string enum: ["file_path"] x-ms-enum: name: MessageDeltaContentTextAnnotationsFilePathObjectType modelAsString: true values: - value: file_path text: description: The text in the message content that needs to be replaced. type: string file_path: type: object properties: file_id: description: The ID of the file that was generated. type: string start_index: type: integer minimum: 0 end_index: type: integer minimum: 0 required: - index - type runStepObject: type: object title: Run steps description: | Represents a step in execution of a run. properties: id: description: The identifier of the run step, which can be referenced in API endpoints. type: string object: description: The object type, which is always `assistant.run.step``. type: string enum: - assistant.run.step x-ms-enum: name: RunStepObjectType modelAsString: true values: - value: assistant.run.step description: The object type, which is always `assistant.run.step` created_at: description: The Unix timestamp (in seconds) for when the run step was created. type: integer assistant_id: description: The ID of the assistant associated with the run step. type: string thread_id: description: The ID of the [thread](/docs/api-reference/threads) that was run. type: string run_id: description: The ID of the [run](/docs/api-reference/runs) that this run step is a part of. type: string type: description: The type of run step, which can be either `message_creation` or `tool_calls`. type: string enum: - message_creation - tool_calls x-ms-enum: name: RunStepObjectType modelAsString: true values: - value: message_creation description: The message_creation run step - value: tool_calls description: The tool_calls run step status: description: The status of the run, which can be either `in_progress`, `cancelled`, `failed`, `completed`, or `expired`. type: string enum: - in_progress - cancelled - failed - completed - expired x-ms-enum: name: RunStepObjectStatus modelAsString: true values: - value: in_progress description: The in_progress run status - value: cancelled description: The cancelled run status - value: failed description: The cancelled run status - value: completed description: The cancelled run status - value: expired description: The cancelled run status step_details: type: object description: The details of the run step. oneOf: - $ref: "#/components/schemas/runStepDetailsMessageCreationObject" - $ref: "#/components/schemas/runStepDetailsToolCallsObject" last_error: type: object description: The last error associated with this run step. Will be `null` if there are no errors. nullable: true properties: code: type: string description: One of `server_error` or `rate_limit_exceeded`. enum: - server_error - rate_limit_exceeded x-ms-enum: name: LastErrorCode modelAsString: true values: - value: server_error description: The server_error - value: rate_limit_exceeded description: The rate_limit_exceeded status message: type: string description: A human-readable description of the error. required: - code - message expired_at: description: The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired. type: integer nullable: true cancelled_at: description: The Unix timestamp (in seconds) for when the run step was cancelled. type: integer nullable: true failed_at: description: The Unix timestamp (in seconds) for when the run step failed. type: integer nullable: true completed_at: description: The Unix timestamp (in seconds) for when the run step completed. type: integer nullable: true metadata: description: *metadata_description type: object nullable: true required: - id - object - created_at - assistant_id - thread_id - run_id - type - status - step_details - last_error - expired_at - cancelled_at - failed_at - completed_at - metadata runStepDeltaObject: type: object title: Run step delta object description: | Represents a run step delta i.e. any changed fields on a run step during streaming. properties: id: description: The identifier of the run step, which can be referenced in API endpoints. type: string object: description: The object type, which is always `thread.run.step.delta`. type: string enum: ["thread.run.step.delta"] x-ms-enum: name: RunStepDeltaObjectType modelAsString: true values: - value: thread.run.step.delta delta: description: The delta containing the fields that have changed on the run step. type: object properties: step_details: type: object description: The details of the run step. oneOf: - $ref: "#/components/schemas/runStepDeltaStepDetailsMessageCreationObject" - $ref: "#/components/schemas/runStepDeltaStepDetailsToolCallsObject" required: - id - object - delta listRunStepsResponse: properties: object: type: string example: list data: type: array items: $ref: "#/components/schemas/runStepObject" first_id: type: string example: step_hLBK7PXBv5Lr2NQT7KLY0ag1 last_id: type: string example: step_QLoItBbqwyAJEzlTy4y9kOMM has_more: type: boolean example: false required: - object - data - first_id - last_id - has_more runStepDetailsMessageCreationObject: title: Message creation type: object description: Details of the message creation by the run step. properties: type: description: Always `message_creation``. type: string enum: - message_creation x-ms-enum: name: RunStepDetailsMessageCreationObjectType modelAsString: true values: - value: message_creation message_creation: type: object properties: message_id: type: string description: The ID of the message that was created by this run step. required: - message_id required: - type - message_creation runStepDeltaStepDetailsMessageCreationObject: title: Message creation type: object description: Details of the message creation by the run step. properties: type: description: Always `message_creation`. type: string enum: ["message_creation"] x-ms-enum: name: RunStepDeltaStepDetailsMessageCreationObjectType modelAsString: true values: - value: message_creation message_creation: type: object properties: message_id: type: string description: The ID of the message that was created by this run step. required: - type runStepDetailsToolCallsObject: title: Tool calls type: object description: Details of the tool call. properties: type: description: Always `tool_calls`. type: string enum: - tool_calls x-ms-enum: name: RunStepDetailsToolCallsObjectType modelAsString: true values: - value: tool_calls tool_calls: type: array description: | An array of tool calls the run step was involved in. These can be associated with one of three types of tools: `code_interpreter`, `retrieval` or `function`. items: type: object oneOf: - $ref: "#/components/schemas/runStepDetailsToolCallsCodeObject" - $ref: "#/components/schemas/runStepDetailsToolCallsFileSearchObject" - $ref: "#/components/schemas/runStepDetailsToolCallsFunctionObject" required: - type - tool_calls runStepDeltaStepDetailsToolCallsObject: title: Tool calls type: object description: Details of the tool call. properties: type: description: Always `tool_calls`. type: string enum: ["tool_calls"] x-ms-enum: name: RunStepDeltaStepDetailsToolCallsObjectType modelAsString: true values: - value: tool_calls tool_calls: type: array description: | An array of tool calls the run step was involved in. These can be associated with one of three types of tools: `code_interpreter`, `file_search` or `function`. items: oneOf: - $ref: "#/components/schemas/runStepDeltaStepDetailsToolCallsCodeObject" - $ref: "#/components/schemas/runStepDeltaStepDetailsToolCallsFileSearchObject" - $ref: "#/components/schemas/runStepDeltaStepDetailsToolCallsFunctionObject" required: - type runStepDetailsToolCallsCodeObject: title: Code interpreter tool call type: object description: Details of the Code Interpreter tool call the run step was involved in. properties: id: type: string description: The ID of the tool call. type: type: string description: The type of tool call. This is always going to be `code_interpreter` for this type of tool call. enum: - code_interpreter x-ms-enum: name: RunStepDetailsToolCallsCodeObjectType modelAsString: true values: - value: code_interpreter code_interpreter: type: object description: The Code Interpreter tool call definition. required: - input - outputs properties: input: type: string description: The input to the Code Interpreter tool call. outputs: type: array description: The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (`logs`) or images (`image`). Each of these are represented by a different object type. items: type: object oneOf: - $ref: "#/components/schemas/runStepDetailsToolCallsCodeOutputLogsObject" - $ref: "#/components/schemas/runStepDetailsToolCallsCodeOutputImageObject" required: - id - type - code_interpreter runStepDeltaStepDetailsToolCallsCodeObject: title: Code interpreter tool call type: object description: Details of the Code Interpreter tool call the run step was involved in. properties: index: type: integer description: The index of the tool call in the tool calls array. id: type: string description: The ID of the tool call. type: type: string description: The type of tool call. This is always going to be `code_interpreter` for this type of tool call. enum: ["code_interpreter"] x-ms-enum: name: RunStepDeltaStepDetailsToolCallsCodeObjectType modelAsString: true values: - value: code_interpreter code_interpreter: type: object description: The Code Interpreter tool call definition. properties: input: type: string description: The input to the Code Interpreter tool call. outputs: type: array description: The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (`logs`) or images (`image`). Each of these are represented by a different object type. items: type: object oneOf: - $ref: "#/components/schemas/runStepDeltaStepDetailsToolCallsCodeOutputLogsObject" - $ref: "#/components/schemas/runStepDeltaStepDetailsToolCallsCodeOutputImageObject" required: - index - type runStepDetailsToolCallsCodeOutputLogsObject: title: Code interpreter log output type: object description: Text output from the Code Interpreter tool call as part of a run step. properties: type: description: Always `logs`. type: string enum: - logs x-ms-enum: name: RunStepDetailsToolCallsCodeOutputLogsObjectType modelAsString: true values: - value: logs logs: type: string description: The text output from the Code Interpreter tool call. required: - type - logs runStepDeltaStepDetailsToolCallsCodeOutputLogsObject: title: Code interpreter log output type: object description: Text output from the Code Interpreter tool call as part of a run step. properties: index: type: integer description: The index of the output in the outputs array. type: description: Always `logs`. type: string enum: ["logs"] x-ms-enum: name: RunStepDeltaStepDetailsToolCallsCodeOutputLogsObjectType modelAsString: true values: - value: logs logs: type: string description: The text output from the Code Interpreter tool call. required: - index - type runStepDetailsToolCallsCodeOutputImageObject: title: Code interpreter image output type: object properties: type: description: Always `image`. type: string enum: - image x-ms-enum: name: RunStepDetailsToolCallsCodeOutputImageObjectType modelAsString: true values: - value: image image: type: object properties: file_id: description: The file ID of the image. type: string required: - file_id required: - type - image runStepDeltaStepDetailsToolCallsCodeOutputImageObject: title: Code interpreter image output type: object properties: index: type: integer description: The index of the output in the outputs array. type: description: Always `image`. type: string enum: ["image"] x-ms-enum: name: RunStepDeltaStepDetailsToolCallsCodeOutputImageObject modelAsString: true values: - value: image image: type: object properties: file_id: description: The file ID of the image. type: string required: - index - type runStepDetailsToolCallsFileSearchObject: title: File search tool call type: object properties: id: type: string description: The ID of the tool call object. type: type: string description: The type of tool call. This is always going to be `file_search` for this type of tool call. enum: ["file_search"] x-ms-enum: name: RunStepDetailsToolCallsFileSearchObjectType modelAsString: true values: - value: file_search file_search: type: object description: For now, this is always going to be an empty object. required: - id - type - file_search runStepDeltaStepDetailsToolCallsFileSearchObject: title: File search tool call type: object properties: index: type: integer description: The index of the tool call in the tool calls array. id: type: string description: The ID of the tool call object. type: type: string description: The type of tool call. This is always going to be `retrieval` for this type of tool call. enum: - file_search x-ms-enum: name: RunStepDeltaStepDetailsToolCallsFileSearchObjectType modelAsString: true values: - value: file_search file_search: type: object description: For now, this is always going to be an empty object. required: - index - type - file_search runStepDetailsToolCallsFunctionObject: type: object title: Function tool call properties: id: type: string description: The ID of the tool call object. type: type: string description: The type of tool call. This is always going to be `function` for this type of tool call. enum: - function x-ms-enum: name: RunStepDetailsToolCallsFunctionObjectType modelAsString: true values: - value: function function: type: object description: The definition of the function that was called. properties: name: type: string description: The name of the function. arguments: type: string description: The arguments passed to the function. output: type: string description: The output of the function. This will be `null` if the outputs have not been [submitted](/docs/api-reference/runs/submitToolOutputs) yet. nullable: true required: - name - arguments - output required: - id - type - function runStepDeltaStepDetailsToolCallsFunctionObject: type: object title: Function tool call properties: index: type: integer description: The index of the tool call in the tool calls array. id: type: string description: The ID of the tool call object. type: type: string description: The type of tool call. This is always going to be `function` for this type of tool call. enum: ["function"] x-ms-enum: name: RunStepDetailsToolCallsFunctionObjectType modelAsString: true values: - value: function function: type: object description: The definition of the function that was called. properties: name: type: string description: The name of the function. arguments: type: string description: The arguments passed to the function. output: type: string description: The output of the function. This will be `null` if the outputs have not been submitted yet. nullable: true required: - index - type vectorStoreExpirationAfter: type: object title: Vector store expiration policy description: The expiration policy for a vector store. properties: anchor: description: "Anchor timestamp after which the expiration policy applies. Supported anchors: `last_active_at`." type: string enum: ["last_active_at"] x-ms-enum: name: VectorStoreExpirationAfterAnchor modelAsString: true values: - value: last_active_at description: The anchor timestamp after which the expiration policy applies. days: description: The number of days after the anchor time that the vector store will expire. type: integer minimum: 1 maximum: 365 required: - anchor - days vectorStoreObject: type: object title: Vector store description: A vector store is a collection of processed files can be used by the `file_search` tool. properties: id: description: The identifier, which can be referenced in API endpoints. type: string object: description: The object type, which is always `vector_store`. type: string enum: ["vector_store"] created_at: description: The Unix timestamp (in seconds) for when the vector store was created. type: integer name: description: The name of the vector store. type: string usage_bytes: description: The total number of bytes used by the files in the vector store. type: integer file_counts: type: object properties: in_progress: description: The number of files that are currently being processed. type: integer completed: description: The number of files that have been successfully processed. type: integer failed: description: The number of files that have failed to process. type: integer cancelled: description: The number of files that were cancelled. type: integer total: description: The total number of files. type: integer required: - in_progress - completed - failed - cancelled - total status: description: The status of the vector store, which can be either `expired`, `in_progress`, or `completed`. A status of `completed` indicates that the vector store is ready for use. type: string enum: ["expired", "in_progress", "completed"] x-ms-enum: name: VectorStoreObjectStatus modelAsString: true values: - value: expired - value: in_progress - value: completed expires_after: $ref: "#/components/schemas/vectorStoreExpirationAfter" expires_at: description: The Unix timestamp (in seconds) for when the vector store will expire. type: integer nullable: true last_active_at: description: The Unix timestamp (in seconds) for when the vector store was last active. type: integer nullable: true metadata: description: *metadata_description type: object nullable: true required: - id - object - usage_bytes - created_at - status - last_active_at - name - bytes - file_counts - metadata createVectorStoreRequest: type: object additionalProperties: false properties: file_ids: description: A list of file IDs that the vector store should use. Useful for tools like `file_search` that can access files. type: array maxItems: 500 items: type: string name: description: The name of the vector store. type: string expires_after: $ref: "#/components/schemas/vectorStoreExpirationAfter" chunking_strategy: type: object description: >- The chunking strategy used to chunk the file(s). If not set, will use the `auto` strategy. Only applicable if `file_ids` is non-empty. oneOf: - $ref: "#/components/schemas/autoChunkingStrategyRequestParam" - $ref: "#/components/schemas/staticChunkingStrategyRequestParam" metadata: description: *metadata_description type: object nullable: true updateVectorStoreRequest: type: object additionalProperties: false properties: name: description: The name of the vector store. type: string nullable: true expires_after: $ref: "#/components/schemas/vectorStoreExpirationAfter" nullable: true metadata: description: *metadata_description type: object nullable: true listVectorStoresResponse: properties: object: type: string example: "list" data: type: array items: $ref: "#/components/schemas/vectorStoreObject" first_id: type: string example: "vs_abc123" last_id: type: string example: "vs_abc456" has_more: type: boolean example: false required: - object - data - first_id - last_id - has_more deleteVectorStoreResponse: type: object properties: id: type: string deleted: type: boolean object: type: string enum: [vector_store.deleted] x-ms-enum: name: DeleteVectorStoreResponseObject modelAsString: true values: - value: vector_store.deleted description: The delete vector store response object state required: - id - object - deleted vectorStoreFileObject: type: object title: Vector store files description: A list of files attached to a vector store. properties: id: description: The identifier, which can be referenced in API endpoints. type: string object: description: The object type, which is always `vector_store.file`. type: string enum: ["vector_store.file"] x-ms-enum: name: VectorStoreFileObjectType modelAsString: true values: - value: vector_store.file usage_bytes: description: The total vector store usage in bytes. Note that this may be different from the original file size. type: integer created_at: description: The Unix timestamp (in seconds) for when the vector store file was created. type: integer vector_store_id: description: The ID of the vector store that the file is attached to. type: string status: description: The status of the vector store file, which can be either `in_progress`, `completed`, `cancelled`, or `failed`. The status `completed` indicates that the vector store file is ready for use. type: string enum: ["in_progress", "completed", "cancelled", "failed"] x-ms-enum: name: VectorStoreFileObjectStatus modelAsString: true values: - value: in_progress - value: completed - value: cancelled - value: failed last_error: type: object description: The last error associated with this vector store file. Will be `null` if there are no errors. nullable: true properties: code: type: string description: One of `server_error` or `rate_limit_exceeded`. enum: [ "internal_error", "file_not_found", "parsing_error", "unhandled_mime_type", ] x-ms-enum: name: VectorStoreFileObjectLastErrorCode modelAsString: true values: - value: internal_error - value: file_not_found - value: parsing_error - value: unhandled_mime_type message: type: string description: A human-readable description of the error. required: - code - message chunking_strategy: type: object description: | The chunking strategy used to chunk the file(s). If not set, will use the `auto` strategy. Only applicable if `file_ids` is non-empty. oneOf: - $ref: "#/components/schemas/autoChunkingStrategyRequestParam" - $ref: "#/components/schemas/staticChunkingStrategyRequestParam" required: - id - object - usage_bytes - created_at - vector_store_id - status - last_error otherChunkingStrategyResponseParam: type: object title: Other Chunking Strategy description: | This is returned when the chunking strategy is unknown. Typically, this is because the file was indexed before the `chunking_strategy` concept was introduced in the API. additionalProperties: false properties: type: type: string description: Always `other`. enum: - other x-ms-enum: name: OtherChunkingStrategyResponseParamType modelAsString: true values: - value: other required: - type staticChunkingStrategyResponseParam: type: object title: Static Chunking Strategy additionalProperties: false properties: type: type: string description: Always `static`. enum: - static x-ms-enum: name: StaticChunkingStrategyResponseParamType modelAsString: true values: - value: static static: $ref: "#/components/schemas/staticChunkingStrategy" required: - type - static staticChunkingStrategy: type: object additionalProperties: false properties: max_chunk_size_tokens: type: integer minimum: 100 maximum: 4096 description: | The maximum number of tokens in each chunk. The default value is `800`. The minimum value is `100` and the maximum value is `4096`. chunk_overlap_tokens: type: integer description: > The number of tokens that overlap between chunks. The default value is `400`. Note that the overlap must not exceed half of `max_chunk_size_tokens`. required: - max_chunk_size_tokens - chunk_overlap_tokens autoChunkingStrategyRequestParam: type: object title: Auto Chunking Strategy description: | The default strategy. This strategy currently uses a `max_chunk_size_tokens` of `800` and `chunk_overlap_tokens` of `400`. additionalProperties: false properties: type: type: string description: Always `auto`. enum: - auto required: - type staticChunkingStrategyRequestParam: type: object title: Static Chunking Strategy additionalProperties: false properties: type: type: string description: Always `static`. enum: - static static: $ref: "#/components/schemas/staticChunkingStrategy" required: - type - static chunkingStrategyRequestParam: type: object description: >- The chunking strategy used to chunk the file(s). If not set, will use the `auto` strategy. oneOf: - $ref: "#/components/schemas/autoChunkingStrategyRequestParam" - $ref: "#/components/schemas/staticChunkingStrategyRequestParam" createVectorStoreFileRequest: type: object additionalProperties: false properties: file_id: description: A File ID that the vector store should use. Useful for tools like `file_search` that can access files. type: string chunking_strategy: $ref: "#/components/schemas/chunkingStrategyRequestParam" required: - file_id listVectorStoreFilesResponse: properties: object: type: string example: "list" data: type: array items: $ref: "#/components/schemas/vectorStoreFileObject" first_id: type: string example: "file-abc123" last_id: type: string example: "file-abc456" has_more: type: boolean example: false required: - object - data - first_id - last_id - has_more deleteVectorStoreFileResponse: type: object properties: id: type: string deleted: type: boolean object: type: string enum: [vector_store.file.deleted] x-ms-enum: name: DeleteVectorStoreFileResponseObject modelAsString: true values: - value: vector_store.file.deleted required: - id - object - deleted vectorStoreFileBatchObject: type: object title: Vector store file batch description: A batch of files attached to a vector store. properties: id: description: The identifier, which can be referenced in API endpoints. type: string object: description: The object type, which is always `vector_store.file_batch`. type: string enum: ["vector_store.files_batch"] x-ms-enum: name: VectorStoreFileBatchObjectType modelAsString: true values: - value: vector_store.files_batch created_at: description: The Unix timestamp (in seconds) for when the vector store files batch was created. type: integer vector_store_id: description: The ID of the vector store that the File is attached to. type: string status: description: The status of the vector store files batch, which can be either `in_progress`, `completed`, `cancelled` or `failed`. type: string enum: ["in_progress", "completed", "cancelled", "failed"] x-ms-enum: name: VectorStoreFileBatchObjectStatus modelAsString: true values: - value: in_progress - value: completed - value: cancelled - value: failed file_counts: type: object properties: in_progress: description: The number of files that are currently being processed. type: integer completed: description: The number of files that have been processed. type: integer failed: description: The number of files that have failed to process. type: integer cancelled: description: The number of files that where cancelled. type: integer total: description: The total number of files. type: integer required: - in_progress - completed - cancelled - failed - total required: - id - object - created_at - vector_store_id - status - file_counts createVectorStoreFileBatchRequest: type: object additionalProperties: false properties: file_ids: description: A list of File IDs that the vector store should use. Useful for tools like `file_search` that can access files. type: array minItems: 1 maxItems: 500 items: type: string chunking_strategy: $ref: "#/components/schemas/chunkingStrategyRequestParam" required: - file_ids assistantStreamEvent: description: | Represents an event emitted when streaming a Run. Each event in a server-sent events stream has an `event` and `data` property: ``` event: thread.created data: {"id": "thread_123", "object": "thread", ...} ``` We emit events whenever a new object is created, transitions to a new state, or is being streamed in parts (deltas). For example, we emit `thread.run.created` when a new run is created, `thread.run.completed` when a run completes, and so on. When an Assistant chooses to create a message during a run, we emit a `thread.message.created event`, a `thread.message.in_progress` event, many `thread.message.delta` events, and finally a `thread.message.completed` event. We may add additional events over time, so we recommend handling unknown events gracefully in your code. See the [Assistants API quickstart](/docs/assistants/overview) to learn how to integrate the Assistants API with streaming. oneOf: - $ref: "#/components/schemas/threadStreamEvent" - $ref: "#/components/schemas/runStreamEvent" - $ref: "#/components/schemas/runStepStreamEvent" - $ref: "#/components/schemas/messageStreamEvent" - $ref: "#/components/schemas/errorEvent" - $ref: "#/components/schemas/doneEvent" threadStreamEvent: oneOf: - type: object properties: event: type: string enum: ["thread.created"] x-ms-enum: name: ThreadStreamEventEnum modelAsString: true values: - value: thread.created description: The thread created event data: $ref: "#/components/schemas/threadObject" required: - event - data description: Occurs when a new thread is created. runStreamEvent: oneOf: - type: object properties: event: type: string enum: ["thread.run.created"] x-ms-enum: name: RunStreamEventCreated modelAsString: true values: - value: thread.run.created data: $ref: "#/components/schemas/runObject" required: - event - data description: Occurs when a new run is created. - type: object properties: event: type: string enum: ["thread.run.queued"] x-ms-enum: name: RunStreamEventQueued modelAsString: true values: - value: thread.run.queued data: $ref: "#/components/schemas/runObject" required: - event - data description: Occurs when a run moves to a `queued` status. - type: object properties: event: type: string enum: ["thread.run.in_progress"] x-ms-enum: name: RunStreamEventInProgress modelAsString: true values: - value: thread.run.in_progress data: $ref: "#/components/schemas/runObject" required: - event - data description: Occurs when a run moves to an `in_progress` status. - type: object properties: event: type: string enum: ["thread.run.requires_action"] x-ms-enum: name: RunStreamEventRequiresAction modelAsString: true values: - value: thread.run.requires_action data: $ref: "#/components/schemas/runObject" required: - event - data description: Occurs when a run moves to a `requires_action` status. - type: object properties: event: type: string enum: ["thread.run.completed"] x-ms-enum: name: RunStreamEventCompleted modelAsString: true values: - value: thread.run.completed data: $ref: "#/components/schemas/runObject" required: - event - data description: Occurs when a run is completed. - type: object properties: event: type: string enum: ["thread.run.failed"] x-ms-enum: name: RunStreamEventFailed modelAsString: true values: - value: thread.run.failed data: $ref: "#/components/schemas/runObject" required: - event - data description: Occurs when a run fails. - type: object properties: event: type: string enum: ["thread.run.cancelling"] x-ms-enum: name: RunStreamEventCancelling modelAsString: true values: - value: thread.run.cancelling data: $ref: "#/components/schemas/runObject" required: - event - data description: Occurs when a run moves to a `cancelling` status. - type: object properties: event: type: string enum: ["thread.run.cancelled"] x-ms-enum: name: RunStreamEventCancelled modelAsString: true values: - value: thread.run.cancelled data: $ref: "#/components/schemas/runObject" required: - event - data description: Occurs when a run is cancelled. - type: object properties: event: type: string enum: ["thread.run.expired"] x-ms-enum: name: RunStreamEventExpired modelAsString: true values: - value: thread.run.expired data: $ref: "#/components/schemas/runObject" required: - event - data description: Occurs when a run expires. runStepStreamEvent: oneOf: - type: object properties: event: type: string enum: ["thread.run.step.created"] x-ms-enum: name: RunStepStreamEventCreated modelAsString: true values: - value: thread.run.step.created data: $ref: "#/components/schemas/runStepObject" required: - event - data description: Occurs when a run step is created. - type: object properties: event: type: string enum: ["thread.run.step.in_progress"] x-ms-enum: name: RunStepStreamEventInProgress modelAsString: true values: - value: thread.run.step.in_progress data: $ref: "#/components/schemas/runStepObject" required: - event - data description: Occurs when a run step moves to an `in_progress` state. - type: object properties: event: type: string enum: ["thread.run.step.delta"] x-ms-enum: name: RunStepStreamEventDelta modelAsString: true values: - value: thread.run.step.delta data: $ref: "#/components/schemas/runStepDeltaObject" required: - event - data description: Occurs when parts of a run step are being streamed. - type: object properties: event: type: string enum: ["thread.run.step.completed"] x-ms-enum: name: RunStepStreamEventCompleted modelAsString: true values: - value: thread.run.step.completed data: $ref: "#/components/schemas/runStepObject" required: - event - data description: Occurs when a run step is completed. - type: object properties: event: type: string enum: ["thread.run.step.failed"] x-ms-enum: name: RunStepStreamEventFailed modelAsString: true values: - value: thread.run.step.failed data: $ref: "#/components/schemas/runStepObject" required: - event - data description: Occurs when a run step fails. - type: object properties: event: type: string enum: ["thread.run.step.cancelled"] x-ms-enum: name: RunStepStreamEventCancelled modelAsString: true values: - value: thread.run.step.cancelled data: $ref: "#/components/schemas/runStepObject" required: - event - data description: Occurs when a run step is cancelled. - type: object properties: event: type: string enum: ["thread.run.step.expired"] x-ms-enum: name: RunStepStreamEventExpired modelAsString: true values: - value: thread.run.step.expired data: $ref: "#/components/schemas/runStepObject" required: - event - data description: Occurs when a run step expires. messageStreamEvent: oneOf: - type: object properties: event: type: string enum: ["thread.message.created"] x-ms-enum: name: MessageStreamEventCreated modelAsString: true values: - value: thread.message.created data: $ref: "#/components/schemas/messageObject" required: - event - data description: Occurs when a message is created. - type: object properties: event: type: string enum: ["thread.message.in_progress"] x-ms-enum: name: MessageStreamEventInProgress modelAsString: true values: - value: thread.message.in_progress data: $ref: "#/components/schemas/messageObject" required: - event - data description: Occurs when a message moves to an `in_progress` state. - type: object properties: event: type: string enum: ["thread.message.delta"] x-ms-enum: name: MessageStreamEventDelta modelAsString: true values: - value: thread.message.delta data: $ref: "#/components/schemas/messageDeltaObject" required: - event - data description: Occurs when parts of a message are being streamed. - type: object properties: event: type: string enum: ["thread.message.completed"] x-ms-enum: name: MessageStreamEventCompleted modelAsString: true values: - value: thread.message.completed data: $ref: "#/components/schemas/messageObject" required: - event - data description: Occurs when a message is completed. - type: object properties: event: type: string enum: ["thread.message.incomplete"] x-ms-enum: name: MessageStreamEventIncomplete modelAsString: true values: - value: thread.message.incomplete data: $ref: "#/components/schemas/messageObject" required: - event - data description: Occurs when a message ends before it is completed. errorEvent: type: object properties: event: type: string enum: ["error"] x-ms-enum: name: ErrorEventEnum modelAsString: true values: - value: error data: $ref: "#/components/schemas/error" required: - event - data description: Occurs when an error occurs. This can happen due to an internal server error or a timeout. doneEvent: type: object properties: event: type: string enum: ["done"] x-ms-enum: name: DoneEventEnum modelAsString: true values: - value: done data: type: string enum: ["[DONE]"] x-ms-enum: name: DoneEventDataEnum modelAsString: true values: - value: "[DONE]" required: - event - data description: Occurs when a stream ends. securitySchemes: bearer: type: oauth2 flows: implicit: authorizationUrl: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scopes: {} x-tokenInfoFunc: api.middleware.auth.bearer_auth x-scopeValidateFunc: api.middleware.auth.validate_scopes apiKey: type: apiKey name: api-key in: header

specification/cognitiveservices/data-plane/AzureOpenAI/inference/preview/2024-09-01-preview/inference.yaml (6,603 lines of code) (raw):