open_ai_adapter

OpenAI LLM adapter for Pipecat.

pipecat.adapters.services.open_ai_adapter.is_given(value: _T | NotGiven) → TypeGuard[_T][source]

Check whether a value was explicitly provided.

Typically used when checking whether a parameter or field typed with OpenAI’s NotGiven was set:

if is_given(tool_choice):
    ...

Also acts as a type guard: inside a true branch, the value is narrowed to exclude OpenAINotGiven (e.g. ChatCompletionToolChoiceOptionParam | OpenAINotGiven becomes ChatCompletionToolChoiceOptionParam).

Parameters:: value – The value to check.
Returns:: True if value is anything other than NOT_GIVEN.

class pipecat.adapters.services.open_ai_adapter.OpenAILLMInvocationParams[source]

Bases: TypedDict

Context-based parameters for invoking OpenAI ChatCompletion API.

messages: list[ChatCompletionDeveloperMessageParam | ChatCompletionSystemMessageParam | ChatCompletionUserMessageParam | ChatCompletionAssistantMessageParam | ChatCompletionToolMessageParam | ChatCompletionFunctionMessageParam]

tools: list[ChatCompletionFunctionToolParam] | NotGiven

tool_choice: Literal['none', 'auto', 'required'] | ChatCompletionAllowedToolChoiceParam | ChatCompletionNamedToolChoiceParam | ChatCompletionNamedToolChoiceCustomParam | NotGiven

class pipecat.adapters.services.open_ai_adapter.OpenAILLMAdapter[source]

Bases: BaseLLMAdapter[OpenAILLMInvocationParams]

OpenAI-specific adapter for Pipecat.

Handles:

Extracting parameters for OpenAI’s ChatCompletion API from a universal LLM context
Converting Pipecat’s standardized tools schema to OpenAI’s function-calling format.
Extracting and sanitizing messages from the LLM context for logging about OpenAI.

property id_for_llm_specific_messages: str: Get the identifier used in LLMSpecificMessage instances for OpenAI.

get_llm_invocation_params(context: LLMContext, *, system_instruction: str | None = None, convert_developer_to_user: bool) → OpenAILLMInvocationParams[source]

Get OpenAI-specific LLM invocation parameters from a universal LLM context.

Parameters:

context – The LLM context containing messages, tools, etc.
system_instruction – Optional system instruction from service settings or run_inference. If provided, prepended as a system message.
convert_developer_to_user – If True, convert “developer”-role messages to “user”-role messages. Used by OpenAI-compatible services that don’t support the “developer” role.

Returns:

Dictionary of parameters for OpenAI’s ChatCompletion API.

to_provider_tools_format(tools_schema: ToolsSchema) → list[ChatCompletionFunctionToolParam][source]

Convert function schemas to OpenAI’s function-calling format.

Parameters:: tools_schema – The Pipecat tools schema to convert.
Returns:: List of OpenAI formatted function call definitions ready for use with ChatCompletion API.

get_messages_for_logging(context: LLMContext) → list[dict[str, Any]][source]

Get messages from a universal LLM context in a format ready for logging about OpenAI.

Binary data (images, audio) is replaced with short placeholders.

Parameters:: context – The LLM context containing messages.
Returns:: List of messages in a format ready for logging about OpenAI.