OpenAI

pydantic model llama_index.multi_modal_llms.openai.OpenAIMultiModal

Show JSON schema

{
   "title": "OpenAIMultiModal",
   "description": "Multi-Modal LLM interface.",
   "type": "object",
   "properties": {
      "model": {
         "title": "Model",
         "description": "The Multi-Modal model to use from OpenAI.",
         "type": "string"
      },
      "temperature": {
         "title": "Temperature",
         "description": "The temperature to use for sampling.",
         "type": "number"
      },
      "max_new_tokens": {
         "title": "Max New Tokens",
         "description": " The maximum numbers of tokens to generate, ignoring the number of tokens in the prompt",
         "exclusiveMinimum": 0,
         "type": "integer"
      },
      "context_window": {
         "title": "Context Window",
         "description": "The maximum number of context tokens for the model.",
         "exclusiveMinimum": 0,
         "type": "integer"
      },
      "image_detail": {
         "title": "Image Detail",
         "description": "The level of details for image in API calls. Can be low, high, or auto",
         "type": "string"
      },
      "max_retries": {
         "title": "Max Retries",
         "description": "Maximum number of retries.",
         "default": 3,
         "gte": 0,
         "type": "integer"
      },
      "timeout": {
         "title": "Timeout",
         "description": "The timeout, in seconds, for API requests.",
         "default": 60.0,
         "gte": 0,
         "type": "number"
      },
      "api_key": {
         "title": "Api Key",
         "description": "The OpenAI API key.",
         "type": "string"
      },
      "api_base": {
         "title": "Api Base",
         "description": "The base URL for OpenAI API.",
         "type": "string"
      },
      "api_version": {
         "title": "Api Version",
         "description": "The API version for OpenAI API.",
         "type": "string"
      },
      "additional_kwargs": {
         "title": "Additional Kwargs",
         "description": "Additional kwargs for the OpenAI API.",
         "type": "object"
      },
      "default_headers": {
         "title": "Default Headers",
         "description": "The default headers for API requests.",
         "type": "object",
         "additionalProperties": {
            "type": "string"
         }
      },
      "class_name": {
         "title": "Class Name",
         "type": "string",
         "default": "openai_multi_modal_llm"
      }
   },
   "required": [
      "model",
      "temperature",
      "image_detail",
      "api_version"
   ]
}

Config

• arbitrary_types_allowed: bool = True

Fields

• additional_kwargs (Dict[str, Any])

• api_base (str)

• api_key (str)

• api_version (str)

• context_window (Optional[int])

• default_headers (Dict[str, str])

• image_detail (str)

• max_new_tokens (Optional[int])

• max_retries (int)

• model (str)

• temperature (float)

• timeout (float)

field additional_kwargs: Dict[str, Any] [Optional]

Additional kwargs for the OpenAI API.

field api_base: str = None

The base URL for OpenAI API.

field api_key: str = None

The OpenAI API key.

field api_version: str [Required]

The API version for OpenAI API.

field context_window: Optional[int] = None

The maximum number of context tokens for the model.

Constraints

• exclusiveMinimum = 0

field default_headers: Dict[str, str] = None

The default headers for API requests.

field image_detail: str [Required]

The level of details for image in API calls. Can be low, high, or auto

field max_new_tokens: Optional[int] = None

The maximum numbers of tokens to generate, ignoring the number of tokens in the prompt

Constraints

• exclusiveMinimum = 0

field max_retries: int = 3

Maximum number of retries.

field model: str [Required]

The Multi-Modal model to use from OpenAI.

field temperature: float [Required]

The temperature to use for sampling.

field timeout: float = 60.0

The timeout, in seconds, for API requests.

async achat(messages: Sequence[ChatMessage], **kwargs: Any) → ChatResponse

Async chat endpoint for Multi-Modal LLM.

async acomplete(prompt: str, image_documents: Sequence[ImageDocument], **kwargs: Any) → CompletionResponse

Async completion endpoint for Multi-Modal LLM.

async astream_chat(messages: Sequence[ChatMessage], **kwargs: Any) → AsyncGenerator[ChatResponse, None]

Async streaming chat endpoint for Multi-Modal LLM.

async astream_complete(prompt: str, image_documents: Sequence[ImageDocument], **kwargs: Any) → AsyncGenerator[CompletionResponse, None]

Async streaming completion endpoint for Multi-Modal LLM.

chat(messages: Sequence[ChatMessage], **kwargs: Any) → ChatResponse

Chat endpoint for Multi-Modal LLM.

classmethod class_name() → str

Get the class name, used as a unique ID in serialization.

This provides a key that makes serialization robust against actual class name changes.

complete(prompt: str, image_documents: Sequence[ImageDocument], **kwargs: Any) → CompletionResponse

Completion endpoint for Multi-Modal LLM.

stream_chat(messages: Sequence[ChatMessage], **kwargs: Any) → Generator[ChatResponse, None, None]

Stream chat endpoint for Multi-Modal LLM.

stream_complete(prompt: str, image_documents: Sequence[ImageDocument], **kwargs: Any) → Generator[CompletionResponse, None, None]

Streaming completion endpoint for Multi-Modal LLM.

property metadata: MultiModalLLMMetadata

Multi Modal LLM metadata.