CustomOpenAIChatContentFormatter

class langchain_community.chat_models.azureml_endpoint.CustomOpenAIChatContentFormatter

Chat Content formatter for models with OpenAI like API scheme.

Attributes

SUPPORTED_ROLES
accepts	The MIME type of the response data returned from the endpoint
content_type	The MIME type of the input data passed to the endpoint
format_error_msg
supported_api_types	Supported APIs for the given formatter.

Methods

__init__()
escape_special_characters(prompt)	Escapes any special characters in prompt
format_messages_request_payload(messages, ...)	Formats the request according to the chosen api
format_request_payload(prompt, model_kwargs)	Formats the request body according to the input schema of the model.
format_response_payload(output[, api_type])	Formats response

__init__()

static escape_special_characters(prompt: str) → str

Escapes any special characters in prompt

Parameters:

prompt (str) –

Return type:

str

format_messages_request_payload(messages: List[BaseMessage], model_kwargs: Dict, api_type: AzureMLEndpointApiType) → bytes

Formats the request according to the chosen api

Parameters:

• messages (List[BaseMessage]) –

• model_kwargs (Dict) –

• api_type (AzureMLEndpointApiType) –

Return type:

bytes

format_request_payload(prompt: str, model_kwargs: Dict, api_type: AzureMLEndpointApiType = AzureMLEndpointApiType.dedicated) → Any

Formats the request body according to the input schema of the model. Returns bytes or seekable file like object in the format specified in the content_type request header.

Parameters:

• prompt (str) –

• model_kwargs (Dict) –

• api_type (AzureMLEndpointApiType) –

Return type:

Any

format_response_payload(output: bytes, api_type: AzureMLEndpointApiType = AzureMLEndpointApiType.dedicated) → ChatGeneration

Formats response

Parameters:

• output (bytes) –

• api_type (AzureMLEndpointApiType) –

Return type:

ChatGeneration

Examples using CustomOpenAIChatContentFormatter

• AzureMLChatOnlineEndpoint