src/openai/resources/embeddings.py [48:126]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self,
        *,
        input: Union[str, List[str], Iterable[int], Iterable[Iterable[int]]],
        model: Union[str, EmbeddingModel],
        dimensions: int | NotGiven = NOT_GIVEN,
        encoding_format: Literal["float", "base64"] | NotGiven = NOT_GIVEN,
        user: str | NotGiven = NOT_GIVEN,
        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
        # The extra values given here take precedence over values defined on the client or passed to this method.
        extra_headers: Headers | None = None,
        extra_query: Query | None = None,
        extra_body: Body | None = None,
        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
    ) -> CreateEmbeddingResponse:
        """
        Creates an embedding vector representing the input text.

        Args:
          input: Input text to embed, encoded as a string or array of tokens. To embed multiple
              inputs in a single request, pass an array of strings or array of token arrays.
              The input must not exceed the max input tokens for the model (8192 tokens for
              `text-embedding-ada-002`), cannot be an empty string, and any array must be 2048
              dimensions or less.
              [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken)
              for counting tokens. Some models may also impose a limit on total number of
              tokens summed across inputs.

          model: ID of the model to use. You can use the
              [List models](https://platform.openai.com/docs/api-reference/models/list) API to
              see all of your available models, or see our
              [Model overview](https://platform.openai.com/docs/models) for descriptions of
              them.

          dimensions: The number of dimensions the resulting output embeddings should have. Only
              supported in `text-embedding-3` and later models.

          encoding_format: The format to return the embeddings in. Can be either `float` or
              [`base64`](https://pypi.org/project/pybase64/).

          user: A unique identifier representing your end-user, which can help OpenAI to monitor
              and detect abuse.
              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).

          extra_headers: Send extra headers

          extra_query: Add additional query parameters to the request

          extra_body: Add additional JSON properties to the request

          timeout: Override the client-level default timeout for this request, in seconds
        """
        params = {
            "input": input,
            "model": model,
            "user": user,
            "dimensions": dimensions,
            "encoding_format": encoding_format,
        }
        if not is_given(encoding_format):
            params["encoding_format"] = "base64"

        def parser(obj: CreateEmbeddingResponse) -> CreateEmbeddingResponse:
            if is_given(encoding_format):
                # don't modify the response object if a user explicitly asked for a format
                return obj

            for embedding in obj.data:
                data = cast(object, embedding.embedding)
                if not isinstance(data, str):
                    continue
                if not has_numpy():
                    # use array for base64 optimisation
                    embedding.embedding = array.array("f", base64.b64decode(data)).tolist()
                else:
                    embedding.embedding = np.frombuffer(  # type: ignore[no-untyped-call]
                        base64.b64decode(data), dtype="float32"
                    ).tolist()

            return obj
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/openai/resources/embeddings.py [163:241]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self,
        *,
        input: Union[str, List[str], Iterable[int], Iterable[Iterable[int]]],
        model: Union[str, EmbeddingModel],
        dimensions: int | NotGiven = NOT_GIVEN,
        encoding_format: Literal["float", "base64"] | NotGiven = NOT_GIVEN,
        user: str | NotGiven = NOT_GIVEN,
        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
        # The extra values given here take precedence over values defined on the client or passed to this method.
        extra_headers: Headers | None = None,
        extra_query: Query | None = None,
        extra_body: Body | None = None,
        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
    ) -> CreateEmbeddingResponse:
        """
        Creates an embedding vector representing the input text.

        Args:
          input: Input text to embed, encoded as a string or array of tokens. To embed multiple
              inputs in a single request, pass an array of strings or array of token arrays.
              The input must not exceed the max input tokens for the model (8192 tokens for
              `text-embedding-ada-002`), cannot be an empty string, and any array must be 2048
              dimensions or less.
              [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken)
              for counting tokens. Some models may also impose a limit on total number of
              tokens summed across inputs.

          model: ID of the model to use. You can use the
              [List models](https://platform.openai.com/docs/api-reference/models/list) API to
              see all of your available models, or see our
              [Model overview](https://platform.openai.com/docs/models) for descriptions of
              them.

          dimensions: The number of dimensions the resulting output embeddings should have. Only
              supported in `text-embedding-3` and later models.

          encoding_format: The format to return the embeddings in. Can be either `float` or
              [`base64`](https://pypi.org/project/pybase64/).

          user: A unique identifier representing your end-user, which can help OpenAI to monitor
              and detect abuse.
              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).

          extra_headers: Send extra headers

          extra_query: Add additional query parameters to the request

          extra_body: Add additional JSON properties to the request

          timeout: Override the client-level default timeout for this request, in seconds
        """
        params = {
            "input": input,
            "model": model,
            "user": user,
            "dimensions": dimensions,
            "encoding_format": encoding_format,
        }
        if not is_given(encoding_format):
            params["encoding_format"] = "base64"

        def parser(obj: CreateEmbeddingResponse) -> CreateEmbeddingResponse:
            if is_given(encoding_format):
                # don't modify the response object if a user explicitly asked for a format
                return obj

            for embedding in obj.data:
                data = cast(object, embedding.embedding)
                if not isinstance(data, str):
                    continue
                if not has_numpy():
                    # use array for base64 optimisation
                    embedding.embedding = array.array("f", base64.b64decode(data)).tolist()
                else:
                    embedding.embedding = np.frombuffer(  # type: ignore[no-untyped-call]
                        base64.b64decode(data), dtype="float32"
                    ).tolist()

            return obj
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -