openai_client#

OpenAI ModelClient integration.

Functions

`get_all_messages_content`(completion)	When the n > 1, get all the messages content.
`get_first_message_content`(completion)	When we only need the content of the first message.
`get_probabilities`(completion)	Get the probabilities of each token in the completion.
`handle_streaming_response`(generator)	Handle the streaming response.
`parse_stream_response`(completion)	Parse the response of the stream API.

Classes

OpenAIClient([api_key, ...])

A component wrapper for the OpenAI API client.

get_first_message_content(completion: ChatCompletion) → str[source]#: When we only need the content of the first message. It is the default parser for chat completion.

parse_stream_response(completion: ChatCompletionChunk) → str[source]#: Parse the response of the stream API.

handle_streaming_response(generator: Stream[ChatCompletionChunk])[source]#: Handle the streaming response.

get_all_messages_content(completion: ChatCompletion) → List[str][source]#: When the n > 1, get all the messages content.

get_probabilities(completion: ChatCompletion) → List[List[TokenLogProb]][source]#: Get the probabilities of each token in the completion.

class OpenAIClient(api_key: str | None = None, chat_completion_parser: Callable[[Completion], Any] = None, input_type: Literal['text', 'messages'] = 'text')[source]#

Bases: ModelClient

A component wrapper for the OpenAI API client.

Support both embedding and chat completion API, including multimodal capabilities.

Users (1) simplify use Embedder and Generator components by passing OpenAIClient() as the model_client. (2) can use this as an example to create their own API client or extend this class(copying and modifing the code) in their own project.

Note

We suggest users not to use response_format to enforce output data type or tools and tool_choice in your model_kwargs when calling the API. We do not know how OpenAI is doing the formating or what prompt they have added. Instead - use OutputParser for response parsing and formating.

For multimodal inputs, provide images in model_kwargs[“images”] as a path, URL, or list of them. The model must support vision capabilities (e.g., gpt-4o, gpt-4o-mini, o1, o1-mini).

For image generation, use model_type=ModelType.IMAGE_GENERATION and provide: - model: “dall-e-3” or “dall-e-2” - prompt: Text description of the image to generate - size: “1024x1024”, “1024x1792”, or “1792x1024” for DALL-E 3; “256x256”, “512x512”, or “1024x1024” for DALL-E 2 - quality: “standard” or “hd” (DALL-E 3 only) - n: Number of images to generate (1 for DALL-E 3, 1-10 for DALL-E 2) - response_format: “url” or “b64_json”

Parameters:

api_key (Optional[str], optional) – OpenAI API key. Defaults to None.
chat_completion_parser (Callable[[Completion], Any], optional) – A function to parse the chat completion to a str. Defaults to None. Default is get_first_message_content.

References

Embeddings models: https://platform.openai.com/docs/guides/embeddings
Chat models: https://platform.openai.com/docs/guides/text-generation
Vision models: https://platform.openai.com/docs/guides/vision
Image models: https://platform.openai.com/docs/guides/images
OpenAI docs: https://platform.openai.com/docs/introduction

init_sync_client()[source]#

init_async_client()[source]#

parse_chat_completion(completion: ChatCompletion | Generator[ChatCompletionChunk, None, None]) → GeneratorOutput[source]#: Parse the completion, and put it into the raw_response.

track_completion_usage(completion: ChatCompletion | Generator[ChatCompletionChunk, None, None]) → CompletionUsage[source]#: Track the chat completion usage. Use OpenAI standard API for tracking.

parse_embedding_response(response: CreateEmbeddingResponse) → EmbedderOutput[source]#

Parse the embedding response to a structure Adalflow components can understand.

Should be called in Embedder.

convert_inputs_to_api_kwargs(input: Any | None = None, model_kwargs: Dict = {}, model_type: ModelType = ModelType.UNDEFINED) → Dict[source]#

Specify the API input type and output api_kwargs that will be used in _call and _acall methods. Convert the Component’s standard input, and system_input(chat model) and model_kwargs into API-specific format. For multimodal inputs, images can be provided in model_kwargs[“images”] as a string path, URL, or list of them. The model specified in model_kwargs[“model”] must support multimodal capabilities when using images.

Parameters:

input – The input text or messages to process
model_kwargs – Additional parameters including: - images: Optional image source(s) as path, URL, or list of them - detail: Image detail level (‘auto’, ‘low’, or ‘high’), defaults to ‘auto’ - model: The model to use (must support multimodal inputs if images are provided)
model_type – The type of model (EMBEDDER or LLM)

Returns:

API-specific kwargs for the model call

Return type:

Dict

parse_image_generation_response(response: List[Image]) → GeneratorOutput[source]#: Parse the image generation response into a GeneratorOutput.

call(api_kwargs: Dict = {}, model_type: ModelType = ModelType.UNDEFINED)[source]#: kwargs is the combined input and model_kwargs. Support streaming call.

async acall(api_kwargs: Dict = {}, model_type: ModelType = ModelType.UNDEFINED)[source]#: kwargs is the combined input and model_kwargs

classmethod from_dict(data: Dict[str, Any]) → T[source]#: Create an instance from previously serialized data using to_dict() method.

to_dict() → Dict[str, Any][source]#: Convert the component to a dictionary.