model_client¶
Submodules¶
- anthropic_client
- azureai_client
AzureAIClient
AzureAIClient.init_sync_client()
AzureAIClient.init_async_client()
AzureAIClient.parse_chat_completion()
AzureAIClient.track_completion_usage()
AzureAIClient.parse_embedding_response()
AzureAIClient.convert_inputs_to_api_kwargs()
AzureAIClient.call()
AzureAIClient.acall()
AzureAIClient.from_dict()
AzureAIClient.to_dict()
- bedrock_client
- chat_completion_to_response_converter
- cohere_client
- deepseek_client
- fireworks_client
- google_client
- groq_client
GroqAPIClient
GroqAPIClient.init_sync_client()
GroqAPIClient.init_async_client()
GroqAPIClient.parse_chat_completion()
GroqAPIClient.track_completion_usage()
GroqAPIClient.convert_inputs_to_api_kwargs()
GroqAPIClient.call()
GroqAPIClient.acall()
GroqAPIClient.from_dict()
GroqAPIClient.to_dict()
GroqAPIClient.list_models()
- mistral_client
- ollama_client
- openai_client
ParsedResponseContent
ParsedResponseContent.text
ParsedResponseContent.images
ParsedResponseContent.tool_calls
ParsedResponseContent.reasoning
ParsedResponseContent.code_outputs
ParsedResponseContent.raw_output
ParsedResponseContent.text
ParsedResponseContent.images
ParsedResponseContent.tool_calls
ParsedResponseContent.reasoning
ParsedResponseContent.code_outputs
ParsedResponseContent.raw_output
get_response_output_text()
parse_response_output()
estimate_token_count()
handle_streaming_response()
handle_streaming_response_sync()
OpenAIClient
OpenAIClient.init_sync_client()
OpenAIClient.init_async_client()
OpenAIClient.parse_chat_completion()
OpenAIClient.track_completion_usage()
OpenAIClient.parse_embedding_response()
OpenAIClient.convert_inputs_to_api_kwargs()
OpenAIClient.parse_image_generation_response()
OpenAIClient.call()
OpenAIClient.acall()
OpenAIClient.from_dict()
OpenAIClient.to_dict()
- sambanova_client
- together_client
- transformers_client
average_pool()
TransformerEmbedder
get_device()
clean_device_cache()
TransformerReranker
TransformerLLM
TransformersClient
TransformersClient.support_models
TransformersClient.init_sync_client()
TransformersClient.init_reranker_client()
TransformersClient.init_llm_client()
TransformersClient.set_llm_client()
TransformersClient.parse_embedding_response()
TransformersClient.parse_chat_completion()
TransformersClient.call()
TransformersClient.convert_inputs_to_api_kwargs()
- utils
- xai_client
We let users install the required SDKs conditionally for our integrated model providers.
- process_images_for_response_api(images: str | Dict | List[str | Dict], encode_local_images: bool = True) List[Dict[str, Any]] [source]¶
Process and validate images for OpenAI’s responses.create API.
This function handles various image input formats and converts them to the expected format for the responses.create API.
- Parameters:
images – Can be: - A single image URL (str) - A single local file path (str) - A pre-formatted image dict with type=’input_image’ - A list containing any combination of the above
encode_local_images – Whether to encode local image files to base64
- Returns:
type: “input_image”
image_url: Either a URL or base64-encoded data URI
- Return type:
List of formatted image dicts ready for the API, each containing
- Raises:
ValueError – If image dict format is invalid
FileNotFoundError – If local image file doesn’t exist
Examples
>>> # Single URL >>> process_images_for_response_api("https://example.com/image.jpg") [{"type": "input_image", "image_url": "https://example.com/image.jpg"}]
>>> # Local file >>> process_images_for_response_api("/path/to/image.jpg") [{"type": "input_image", "image_url": "data:image/jpeg;base64,..."}]
>>> # Multiple mixed sources >>> process_images_for_response_api([ ... "https://example.com/img.jpg", ... "/local/img.png", ... {"type": "input_image", "image_url": "..."} ... ]) [...]
- format_content_for_response_api(text: str, images: str | Dict | List[str | Dict] | None = None) List[Dict[str, Any]] [source]¶
Format text and optional images into content array for responses.create API.
- Parameters:
text – The text prompt/question
images – Optional images in various formats (see process_images_for_response_api)
- Returns:
List of content items formatted for the API
Examples
>>> # Text only >>> format_content_for_response_api("What is this?") [{"type": "input_text", "text": "What is this?"}]
>>> # Text with image >>> format_content_for_response_api( ... "What's in this image?", ... "https://example.com/img.jpg" ... ) [ {"type": "input_text", "text": "What's in this image?"}, {"type": "input_image", "image_url": "https://example.com/img.jpg"} ]