> ## Documentation Index
> Fetch the complete documentation index at: https://daily-ms-ws-body-url-encode.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# LLM Frames

> LLM frame reference for Pipecat: context frames and the function calling helper dataclasses passed through pipelines.

This page documents LLM-specific types that don't belong on a base-type page: `LLMContextFrame` (which inherits directly from `Frame`) and the helper dataclasses used by function calling frames. All other LLM-related frames are documented on their base-type pages. See [Related Frames](#related-frames) below for links.

## LLMContextFrame

Contains a complete LLM context. Acts as a signal to LLM services to ingest the provided context and generate a response.

Inherits directly from `Frame` (not `DataFrame`, `ControlFrame`, or `SystemFrame`).

<ParamField path="context" type="LLMContext" required>
  The LLM context containing messages, tools, and configuration.
</ParamField>

<ParamField path="speculation" type="bool" default="False">
  Whether this inference is speculative, run from a provisional context that is
  not part of the conversation. Its response must not reach the user or the
  context until the turn is confirmed, and the service must not execute tool
  calls for it.
</ParamField>

## Function Calling Helper Dataclasses

These are plain dataclasses used as fields within function calling frames, not frames themselves.

### FunctionCallFromLLM

Represents a function call returned by the LLM, ready for execution.

<ParamField path="function_name" type="str" required>
  The name of the function to call.
</ParamField>

<ParamField path="tool_call_id" type="str" required>
  A unique identifier for the function call.
</ParamField>

<ParamField path="arguments" type="Mapping[str, Any]" required>
  The arguments to pass to the function.
</ParamField>

<ParamField path="context" type="Any" required>
  The LLM context at the time the function call was made.
</ParamField>

### FunctionCallResultProperties

Configures how a function call result is handled after execution.

<ParamField path="run_llm" type="bool | None" default="None">
  Whether to run the LLM after receiving this result.
</ParamField>

<ParamField path="on_context_updated" type="Callable[[], Awaitable[None]] | None" default="None">
  Async callback to execute when the context is updated with the result.
</ParamField>

<ParamField path="is_final" type="bool" default="True">
  Whether this is the final result for the function call. Set to `False` to send
  an intermediate update from an async function call registered with
  `cancel_on_interruption=False`.
</ParamField>

## Related Frames

LLM-related frames organized by base type:

* **Data Frames**: [Context Management](/api-reference/server/frames/data-frames#llm-context-management), [Thinking](/api-reference/server/frames/data-frames#llm-thinking), [Tool Configuration](/api-reference/server/frames/data-frames#llm-tool-configuration), [Function Call Results](/api-reference/server/frames/data-frames#function-call-results)
* **Control Frames**: [Response Boundaries](/api-reference/server/frames/control-frames#llm-response-boundaries), [Context Summarization](/api-reference/server/frames/control-frames#llm-context-summarization), [Thought Frames](/api-reference/server/frames/control-frames#llm-thought-frames), [Function Calling](/api-reference/server/frames/control-frames#function-calling), [Service Settings](/api-reference/server/frames/control-frames#service-settings)
* **System Frames**: [Function Calling](/api-reference/server/frames/system-frames#function-calling)