specification/cognitiveservices/data-plane/AzureOpenAI/inference/preview/2024-03-01-preview/inference.yaml (5,300 lines of code) (raw):

openapi: 3.0.0 info: title: Azure OpenAI Service API description: Azure OpenAI APIs for completions and search version: 2024-03-01-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: 2023-12-01-preview description: api version requestBody: required: true content: application/json: schema: type: object properties: prompt: description: |- The prompt(s) to generate completions for, encoded as a string or array of strings. 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. Maximum allowed size of string list is 2048. oneOf: - type: string default: '' example: This is a test. nullable: true - type: array items: type: string default: '' example: This is a test. nullable: false description: Array size minimum of 1 and maximum of 2048 max_tokens: description: The token count of your prompt plus max_tokens cannot exceed the model's context length. Most models have a context length of 2048 tokens (except for the newest models, which support 4096). Has minimum of 0. type: integer default: 16 example: 16 nullable: true temperature: description: |- What sampling temperature to use. Higher values means the model will take more risks. Try 0.9 for more creative applications, and 0 (argmax sampling) for ones with a well-defined answer. We generally recommend altering this or top_p but not both. type: number 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 default: 1 example: 1 nullable: true logit_bias: description: Defaults to null. 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 (which works for both GPT-2 and GPT-3) 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" &#58; -100} to prevent the <|endoftext|> token from being generated. type: object nullable: false user: description: A unique identifier representing your end-user, which can help monitoring and detecting abuse type: string nullable: false 'n': description: |- How many completions to generate for each prompt. Minimum of 1 and maximum of 128 allowed. 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. type: integer default: 1 example: 1 nullable: true stream: description: 'Whether to stream back partial progress. If set, 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 logprobs: description: |- Include the log probabilities on the logprobs most likely 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. Minimum of 0 and maximum of 5 allowed. type: integer default: null nullable: true suffix: type: string nullable: true description: The suffix that comes after a completion of inserted text. echo: description: Echo back the prompt in addition to the completion type: boolean default: false nullable: true stop: description: Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence. oneOf: - type: string default: <|endoftext|> example: |+ nullable: true - type: array items: type: string example: |+ nullable: false description: Array minimum size of 1 and maximum of 4 completion_config: type: string 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 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 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. Has maximum value of 128. type: integer 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: type: object properties: id: type: string object: type: string created: type: integer model: type: string prompt_filter_results: $ref: '#/components/schemas/promptFilterResults' choices: type: array items: type: object properties: text: type: string index: type: integer logprobs: type: object properties: tokens: type: array items: type: string token_logprobs: type: array items: type: number top_logprobs: type: array items: type: object additionalProperties: type: number text_offset: type: array items: type: integer nullable: true finish_reason: type: string content_filter_results: $ref: '#/components/schemas/contentFilterChoiceResults' usage: type: object properties: completion_tokens: type: number format: int32 prompt_tokens: type: number format: int32 total_tokens: type: number format: int32 required: - prompt_tokens - total_tokens - completion_tokens required: - id - object - created - model - choices 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: 2024-03-01-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: 2024-03-01-preview description: api version requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/createChatCompletionRequest' responses: '200': description: OK content: application/json: schema: $ref: '#/components/schemas/createChatCompletionResponse' 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 AML index.: $ref: ./examples/chat_completions_aml_index.yaml Creates a completion for the provided Azure Cosmos DB.: $ref: ./examples/chat_completions_cosmos_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: 2024-03-01-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: 2024-03-01-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: 2024-03-01-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: 2024-03-01-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: | 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: | 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: | 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 - in: query name: api-version required: true schema: type: string example: 2024-03-01-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: 2024-03-01-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: 2024-03-01-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: 2024-03-01-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: 2024-03-01-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: 2024-03-01-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: 2024-03-01-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: 2024-03-01-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: 2024-03-01-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: | 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: | 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 - in: query name: api-version required: true schema: type: string example: 2024-03-01-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: 2024-03-01-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: 2024-03-01-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: 2024-03-01-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: 2024-03-01-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: | 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: | 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: 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: | 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 - in: query name: api-version required: true schema: type: string example: 2024-03-01-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: 2024-03-01-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: 2024-03-01-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: 2024-03-01-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: 2024-03-01-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: 2024-03-01-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: | 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: | 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: 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: | 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 - in: query name: api-version required: true schema: type: string example: 2024-03-01-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: 2024-03-01-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 /assistants/{assistant_id}/files: get: operationId: List_Assistant_Files tags: - Assistants summary: Returns a list of assistant files. parameters: - name: assistant_id in: path description: The ID of the assistant the file belongs to. required: true schema: type: string - name: limit in: query 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: | 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: ListAssistantFilesOrder 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 - in: query name: api-version required: true schema: type: string example: 2024-03-01-preview description: api version responses: '200': description: OK content: application/json: schema: $ref: '#/components/schemas/listAssistantFilesResponse' x-ms-examples: List assistant files.: $ref: ./examples/list_assistant_files.yaml post: operationId: Create_Assistant_File tags: - Assistants summary: Create an assistant file by attaching a [File](/docs/api-reference/files) to an [assistant](/docs/api-reference/assistants). parameters: - in: path name: assistant_id required: true schema: type: string example: file-AF1WoRqd3aJAHsqc9NY7iL8F description: | The ID of the assistant for which to create a File. - in: query name: api-version required: true schema: type: string example: 2024-03-01-preview description: api version requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/createAssistantFileRequest' responses: '200': description: OK content: application/json: schema: $ref: '#/components/schemas/assistantFileObject' x-ms-examples: Create an assistant file.: $ref: ./examples/create_assistant_file.yaml /assistants/{assistant_id}/files/{file_id}: get: operationId: Get_Assistant_File tags: - Assistants summary: Retrieves an AssistantFile. parameters: - in: path name: assistant_id required: true schema: type: string description: The ID of the assistant who the file belongs to. - in: path name: file_id required: true schema: type: string description: The ID of the file we're getting. - in: query name: api-version required: true schema: type: string example: 2024-03-01-preview description: api version responses: '200': description: OK content: application/json: schema: $ref: '#/components/schemas/assistantFileObject' x-ms-examples: Retrieve an assistant file.: $ref: ./examples/get_assistant_file.yaml delete: operationId: Delete_Assistant_File tags: - Assistants summary: Delete an assistant file. parameters: - in: path name: assistant_id required: true schema: type: string description: The ID of the assistant 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: 2024-03-01-preview description: api version responses: '200': description: OK content: application/json: schema: $ref: '#/components/schemas/deleteAssistantFileResponse' x-ms-examples: Delete an assistant file.: $ref: ./examples/delete_assistant_file.yaml /threads/{thread_id}/messages/{message_id}/files: get: operationId: List_Message_Files tags: - Assistants summary: Returns a list of message files. parameters: - name: thread_id in: path description: The ID of the thread that the message and files belong to. required: true schema: type: string - name: message_id in: path description: The ID of the message that the files belongs to. required: true schema: type: string - name: limit in: query 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: | 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: ListMessageFilesOrder 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 - in: query name: api-version required: true schema: type: string example: 2024-03-01-preview description: api version responses: '200': description: OK content: application/json: schema: $ref: '#/components/schemas/listMessageFilesResponse' x-ms-examples: List message files.: $ref: ./examples/list_message_files.yaml /threads/{thread_id}/messages/{message_id}/files/{file_id}: get: operationId: Get_Message_File tags: - Assistants summary: Retrieves a message file. parameters: - in: path name: thread_id required: true schema: type: string example: thread_AF1WoRqd3aJAHsqc9NY7iL8F description: The ID of the thread to which the message and File belong. - in: path name: message_id required: true schema: type: string example: msg_AF1WoRqd3aJAHsqc9NY7iL8F description: The ID of the message the file belongs to. - in: path name: file_id required: true schema: type: string example: file-AF1WoRqd3aJAHsqc9NY7iL8F description: The ID of the file being retrieved. - in: query name: api-version required: true schema: type: string example: 2024-03-01-preview description: api version responses: '200': description: OK content: application/json: schema: $ref: '#/components/schemas/messageFileObject' x-ms-examples: Retrieve a message file.: $ref: ./examples/get_message_file.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: items: $ref: '#/components/schemas/contentFilterIdResult' type: array 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' 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' 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' 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). type: integer default: 4096 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 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' enhancements: type: object description: The type of enhancements needed. properties: grounding: type: object description: Request object to specify if grounding enhancement is needed. properties: enabled: type: boolean default: false ocr: type: object description: Request object to specify if ocr enhancement is needed. properties: enabled: type: boolean default: false '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. seed: type: integer minimum: -9223372036854775808 maximum: 9223372036854775807 default: 0 example: 1 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. 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`. This option is currently not available on the `gpt-4-vision-preview` model. type: boolean default: false nullable: true top_logprobs: description: An integer between 0 and 5 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: 5 nullable: true response_format: type: object description: An object specifying the format that the model must output. Used to enable JSON mode. properties: type: $ref: '#/components/schemas/chatCompletionResponseFormat' tools: 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. type: array minItems: 1 items: $ref: '#/components/schemas/chatCompletionTool' tool_choice: $ref: '#/components/schemas/chatCompletionToolChoiceOption' functions: 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/chatCompletionFunction' function_call: description: Deprecated in favor of `tool_choice`. Controls how the model responds to function calls. "none" means the model does not call a function, and responds to the end-user. "auto" means the model can pick between an end-user 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 enum: - none - auto 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.' - 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 required: - messages chatCompletionResponseFormat: type: string enum: - text - json_object default: text example: json_object nullable: true description: Setting to `json_object` enables JSON mode. This guarantees that the message the model generates is valid JSON. x-ms-enum: name: ChatCompletionResponseFormat modelAsString: true values: - value: text description: Response format is a plain text string. - value: json_object description: Response format is a JSON object. chatCompletionFunction: type: object properties: 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. description: type: string description: The description of what the function does. parameters: $ref: '#/components/schemas/chatCompletionFunctionParameters' required: - name chatCompletionFunctionParameters: type: object description: The parameters the functions accepts, described as a JSON Schema object. See the [guide](/docs/guides/gpt/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema/) for documentation about the format. additionalProperties: true chatCompletionRequestMessage: type: object properties: role: $ref: '#/components/schemas/chatCompletionRequestMessageRole' discriminator: propertyName: role mapping: system: '#/components/schemas/chatCompletionRequestMessageSystem' user: '#/components/schemas/chatCompletionRequestMessageUser' assistant: '#/components/schemas/chatCompletionRequestMessageAssistant' tool: '#/components/schemas/chatCompletionRequestMessageTool' function: '#/components/schemas/chatCompletionRequestMessageFunction' required: - role chatCompletionRequestMessageRole: type: string enum: - system - user - assistant - tool - function description: The role of the messages author. x-ms-enum: name: ChatCompletionRequestMessageRole modelAsString: true values: - value: system description: The message author role is system. - value: user description: The message author role is user. - value: assistant description: The message author role is assistant. - value: tool description: The message author role is tool. - value: function description: Deprecated. The message author role is function. chatCompletionRequestMessageSystem: allOf: - $ref: '#/components/schemas/chatCompletionRequestMessage' - type: object properties: content: type: string description: The contents of the message. nullable: true required: - content chatCompletionRequestMessageUser: allOf: - $ref: '#/components/schemas/chatCompletionRequestMessage' - type: object properties: content: oneOf: - type: string description: The contents of the message. - 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-4-visual-preview` model. minimum: 1 items: $ref: '#/components/schemas/chatCompletionRequestMessageContentPart' nullable: true required: - content chatCompletionRequestMessageContentPart: type: object properties: type: $ref: '#/components/schemas/chatCompletionRequestMessageContentPartType' discriminator: propertyName: type mapping: text: '#/components/schemas/chatCompletionRequestMessageContentPartText' image_url: '#/components/schemas/chatCompletionRequestMessageContentPartImage' required: - type chatCompletionRequestMessageContentPartType: type: string enum: - text - image_url description: The type of the content part. x-ms-enum: name: ChatCompletionRequestMessageContentPartType modelAsString: true values: - value: text description: The content part type is text. - value: image_url description: The content part type is image_url. chatCompletionRequestMessageContentPartText: allOf: - $ref: '#/components/schemas/chatCompletionRequestMessageContentPart' - type: object properties: text: type: string description: The text content. required: - text chatCompletionRequestMessageContentPartImage: allOf: - $ref: '#/components/schemas/chatCompletionRequestMessageContentPart' - type: object properties: url: type: string description: Either a URL of the image or the base64 encoded image data. format: uri detail: $ref: '#/components/schemas/imageDetailLevel' required: - url imageDetailLevel: type: string description: Specifies the detail level of the image. enum: - auto - low - high default: auto x-ms-enum: name: ImageDetailLevel modelAsString: true values: - value: auto description: The image detail level is auto. - value: low description: The image detail level is low. - value: high description: The image detail level is high. chatCompletionRequestMessageAssistant: allOf: - $ref: '#/components/schemas/chatCompletionRequestMessage' - type: object properties: 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' context: $ref: '#/components/schemas/azureChatExtensionsMessageContext' required: - content 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_ml_index: '#/components/schemas/azureMachineLearningIndexChatExtensionConfiguration' azure_cosmos_db: '#/components/schemas/azureCosmosDBChatExtensionConfiguration' elasticsearch: '#/components/schemas/elasticsearchChatExtensionConfiguration' 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_ml_index - azure_cosmos_db - elasticsearch - 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: azureMachineLearningIndex value: azure_ml_index description: Represents the use of Azure Machine Learning index 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: 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' top_n_documents: type: integer description: The configured top number of documents to feature for the configured query. format: int32 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 role_information: type: string description: Give the model instructions about how it should behave and any context it should reference when generating a response. You can describe the assistant's personality and tell it how to format responses. There's a 100 token limit for it, and it counts against the overall token limit. 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' 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. azureMachineLearningIndexChatExtensionConfiguration: required: - parameters description: |- A specific representation of configurable options for Azure Machine Learning vector index when using it as an Azure OpenAI chat extension. allOf: - $ref: '#/components/schemas/azureChatExtensionConfiguration' - properties: parameters: $ref: '#/components/schemas/azureMachineLearningIndexChatExtensionParameters' x-ms-discriminator-value: azure_ml_index azureMachineLearningIndexChatExtensionParameters: required: - authentication - name - project_resource_id - version type: object properties: authentication: oneOf: - $ref: '#/components/schemas/onYourDataAccessTokenAuthenticationOptions' - $ref: '#/components/schemas/onYourDataSystemAssignedManagedIdentityAuthenticationOptions' - $ref: '#/components/schemas/onYourDataUserAssignedManagedIdentityAuthenticationOptions' top_n_documents: type: integer description: The configured top number of documents to feature for the configured query. format: int32 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 role_information: type: string description: Give the model instructions about how it should behave and any context it should reference when generating a response. You can describe the assistant's personality and tell it how to format responses. There's a 100 token limit for it, and it counts against the overall token limit. project_resource_id: type: string description: The resource ID of the Azure Machine Learning project. name: type: string description: The Azure Machine Learning vector index name. version: type: string description: The version of the Azure Machine Learning vector index. filter: type: string description: Search filter. Only supported if the Azure Machine Learning vector index is of type AzureSearch. description: Parameters for the Azure Machine Learning vector index chat extension. 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 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 role_information: type: string description: Give the model instructions about how it should behave and any context it should reference when generating a response. You can describe the assistant's personality and tell it how to format responses. There's a 100 token limit for it, and it counts against the overall token limit. 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' 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 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 role_information: type: string description: Give the model instructions about how it should behave and any context it should reference when generating a response. You can describe the assistant's personality and tell it how to format responses. There's a 100 token limit for it, and it counts against the overall token limit. 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' 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. 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 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 role_information: type: string description: Give the model instructions about how it should behave and any context it should reference when generating a response. You can describe the assistant's personality and tell it how to format responses. There's a 100 token limit for it, and it counts against the overall token limit. 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' 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' 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 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. 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 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' 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 - 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: 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: $ref: '#/components/schemas/onYourDataApiKeyAuthenticationOptions' 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. x-ms-discriminator-value: deployment_name 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. 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. description: citation information for a chat completions response message. 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 allOf: - $ref: '#/components/schemas/chatCompletionsResponseCommon' - properties: prompt_filter_results: $ref: '#/components/schemas/promptFilterResults' choices: type: array items: type: object allOf: - $ref: '#/components/schemas/chatCompletionChoiceCommon' - properties: message: $ref: '#/components/schemas/chatCompletionResponseMessage' content_filter_results: $ref: '#/components/schemas/contentFilterChoiceResults' logprobs: $ref: '#/components/schemas/chatCompletionChoiceLogProbs' enhancements: $ref: '#/components/schemas/enhancement' description: The enhancement results returned by the service. required: - id - object - created - model - choices 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 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' 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' chatCompletionResponseMessageRole: type: string enum: - assistant description: The role of the author of the response message. chatCompletionToolChoiceOption: description: '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 `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that function.' 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/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 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 chatCompletionsResponseCommon: type: object properties: id: type: string description: A unique identifier for the chat completion. object: $ref: '#/components/schemas/chatCompletionResponseObject' created: type: integer format: unixtime description: The Unix timestamp (in seconds) of when the chat completion was created. model: type: string description: The model used for the chat completion. usage: $ref: '#/components/schemas/completionUsage' system_fingerprint: type: string description: Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism. required: - id - object - created - model chatCompletionResponseObject: type: string description: The object type. enum: - chat.completion x-ms-enum: name: ChatCompletionResponseObject modelAsString: true values: - value: chat.completion description: The object type is chat completion. 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). required: - prompt_tokens - completion_tokens - total_tokens chatCompletionTool: type: object properties: type: $ref: '#/components/schemas/chatCompletionToolType' function: 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/chatCompletionFunctionParameters' required: - name - parameters required: - type - function chatCompletionToolType: type: string enum: - function description: The type of the tool. Currently, only `function` is supported. x-ms-enum: name: ChatCompletionToolType modelAsString: true values: - value: function description: The tool type is function. 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' 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. 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'. 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 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: - 1792x1024 - 1024x1792 - 1024x1024 default: 1024x1024 x-ms-enum: name: Size modelAsString: true values: - value: 1792x1024 description: The desired size of the generated image is 1792x1024 pixels. name: Size1792x1024 - value: 1024x1792 description: The desired size of the generated image is 1024x1792 pixels. 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' enhancement: type: object properties: grounding: type: object description: The grounding enhancement that returns the bounding box of the objects detected in the image. properties: lines: type: array items: $ref: '#/components/schemas/line' required: - lines 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 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 description: The object type, which is always assistant created_at: description: The Unix timestamp (in seconds) for when the assistant was created. type: integer name: description: | The name of the assistant. The maximum length is 256 characters. type: string maxLength: 256 nullable: true description: 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: | The system instructions that the assistant uses. The maximum length is 32768 characters. type: string maxLength: 32768 nullable: true 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/assistantToolsRetrieval' - $ref: '#/components/schemas/assistantToolsFunction' file_ids: description: | A list of [file](/docs/api-reference/files) IDs attached to this assistant. There can be a maximum of 20 files attached to the assistant. Files are ordered by their creation date in ascending order. default: [] type: array maxItems: 20 items: type: string 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 required: - id - object - created_at - name - description - model - instructions - tools - file_ids - 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: | 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/assistantToolsRetrieval' - $ref: '#/components/schemas/assistantToolsFunction' file_ids: description: | A list of [file](/docs/api-reference/files) IDs attached to this assistant. There can be a maximum of 20 files attached to the assistant. Files are ordered by their creation date in ascending order. default: [] maxItems: 20 type: array items: type: string 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 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/assistantToolsRetrieval' - $ref: '#/components/schemas/assistantToolsFunction' file_ids: description: | A list of [File](/docs/api-reference/files) IDs attached to this assistant. There can be a maximum of 20 files attached to the assistant. Files are ordered by their creation date in ascending order. If a file was previously attached to the list but does not show up in the list, it will be deleted from the assistant. default: [] type: array maxItems: 20 items: type: string 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 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 description: The assistant is 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 description: code_interpreter as type of tool being defined required: - type assistantToolsRetrieval: type: object title: Retrieval tool properties: type: type: string description: 'The type of tool being defined: `retrieval`' enum: - retrieval x-ms-enum: name: assistantToolsRetrievalType modelAsString: true values: - value: retrieval description: retrieval as type of tool being defined 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: retrieval description: retrieval as type of tool being defined 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 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](/docs/api-reference/assistants) 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 model: description: The model that the [assistant](/docs/api-reference/assistants) used for this run. type: string instructions: description: The instructions that the [assistant](/docs/api-reference/assistants) used for this run. type: string tools: description: The list of tools that the [assistant](/docs/api-reference/assistants) used for this run. default: [] type: array maxItems: 20 items: oneOf: - $ref: '#/components/schemas/assistantToolsCode' - $ref: '#/components/schemas/assistantToolsRetrieval' - $ref: '#/components/schemas/assistantToolsFunction' file_ids: description: The list of [File](/docs/api-reference/files) IDs the [assistant](/docs/api-reference/assistants) used for this run. default: [] type: array items: type: string 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 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 - file_ids - metadata createRunRequest: type: object additionalProperties: false properties: assistant_id: description: The ID of the [assistant](/docs/api-reference/assistants) to use to execute this run. type: string 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/assistantToolsRetrieval' - $ref: '#/components/schemas/assistantToolsFunction' 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 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: | 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 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. 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 description: The type of tool call the output is required for which is always `function` for now - value: rate_limit_exceeded description: The server failed to respond to request due to rate limit exceeded 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](/docs/api-reference/assistants) 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/assistantToolsRetrieval' - $ref: '#/components/schemas/assistantToolsFunction' 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 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 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 required: - id - object - created_at - metadata createThreadRequest: type: object additionalProperties: false properties: messages: description: A list of [messages](/docs/api-reference/messages) to start the thread with. type: array items: $ref: '#/components/schemas/createMessageRequest' 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 modifyThreadRequest: type: object additionalProperties: false properties: 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 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 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 description: Message object role as `user` - value: assistant description: Message object role as `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](/docs/api-reference/assistants) 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 file_ids: description: A list of [file](/docs/api-reference/files) IDs that the assistant should use. Useful for tools like retrieval and code_interpreter that can access files. A maximum of 10 files can be attached to a message. default: [] maxItems: 10 type: array items: type: string 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 required: - id - object - created_at - thread_id - role - content - assistant_id - run_id - file_ids - metadata createMessageRequest: type: object additionalProperties: false required: - role - content properties: role: type: string enum: - user x-ms-enum: name: CreateMessageRequestRole modelAsString: true values: - value: user description: The create message role as `user` description: The role of the entity that is creating the message. Currently only `user` is supported. content: type: string minLength: 1 maxLength: 32768 description: The content of the message. file_ids: description: A list of [File](/docs/api-reference/files) IDs that the message should use. There can be a maximum of 10 files attached to a message. Useful for tools like `retrieval` and `code_interpreter` that can access and use files. default: [] type: array minItems: 1 maxItems: 10 items: type: string 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 modifyMessageRequest: type: object additionalProperties: false properties: 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 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](/docs/api-reference/files) 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](/docs/api-reference/files) 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 quote: description: The specific quote in the file. type: string required: - file_id - quote 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 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](/docs/api-reference/assistants) 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: | 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 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 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 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/runStepDetailsToolCallsRetrievalObject' - $ref: '#/components/schemas/runStepDetailsToolCallsFunctionObject' required: - type - tool_calls 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 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: code_interpreter logs: type: string description: The text output from the Code Interpreter tool call. required: - type - logs 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](/docs/api-reference/files) ID of the image. type: string required: - file_id required: - type - image runStepDetailsToolCallsRetrievalObject: title: Retrieval 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 `retrieval` for this type of tool call. enum: - retrieval x-ms-enum: name: RunStepDetailsToolCallsRetrievalObjectType modelAsString: true values: - value: retrieval retrieval: type: object description: For now, this is always going to be an empty object. required: - id - type - retrieval 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 assistantFileObject: type: object title: Assistant files description: A list of [Files](/docs/api-reference/files) attached to an `assistant`. properties: id: description: The identifier, which can be referenced in API endpoints. type: string object: description: The object type, which is always `assistant.file`. type: string enum: - assistant.file x-ms-enum: name: AssistantFileObjectType modelAsString: true values: - value: assistant.file created_at: description: The Unix timestamp (in seconds) for when the assistant file was created. type: integer assistant_id: description: The assistant ID that the file is attached to. type: string required: - id - object - created_at - assistant_id createAssistantFileRequest: type: object additionalProperties: false properties: file_id: description: A [File](/docs/api-reference/files) ID (with `purpose="assistants"`) that the assistant should use. Useful for tools like `retrieval` and `code_interpreter` that can access files. type: string required: - file_id deleteAssistantFileResponse: type: object description: Deletes the association between the assistant and the file, but does not delete the [File](/docs/api-reference/files) object itself. properties: id: type: string deleted: type: boolean object: type: string enum: - assistant.file.deleted x-ms-enum: name: DeleteAssistantFileResponseType modelAsString: true values: - value: assistant.file.deleted required: - id - object - deleted listAssistantFilesResponse: properties: object: type: string example: list data: type: array items: $ref: '#/components/schemas/assistantFileObject' first_id: type: string example: file-hLBK7PXBv5Lr2NQT7KLY0ag1 last_id: type: string example: file-QLoItBbqwyAJEzlTy4y9kOMM has_more: type: boolean example: false required: - object - data - items - first_id - last_id - has_more messageFileObject: type: object title: Message files description: A list of files attached to a `message`. properties: id: description: The identifier, which can be referenced in API endpoints. type: string object: description: The object type, which is always `thread.message.file`. type: string enum: - thread.message.file x-ms-enum: name: MessageFileObjectType modelAsString: true values: - value: thread.message.file created_at: description: The Unix timestamp (in seconds) for when the message file was created. type: integer message_id: description: The ID of the [message](/docs/api-reference/messages) that the [File](/docs/api-reference/files) is attached to. type: string required: - id - object - created_at - message_id listMessageFilesResponse: properties: object: type: string example: list data: type: array items: $ref: '#/components/schemas/messageFileObject' first_id: type: string example: file-hLBK7PXBv5Lr2NQT7KLY0ag1 last_id: type: string example: file-QLoItBbqwyAJEzlTy4y9kOMM has_more: type: boolean example: false required: - object - data - items - first_id - last_id - has_more 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