BaseLiteralClient
Base class for LiteralClient and AsyncLiteralClient.
Example:
Attributes:
api
Union[LiteralAPI, AsyncLiteralAPI]
The API client used for communication with Literal AI.
Flag indicating whether the client is disabled.
Processor for handling events.
instrument_openai
Instruments the OpenAI SDK so that all LLM calls are logged to Literal AI.
instrument_mistralai
Instruments the Mistral AI SDK so that all LLM calls are logged to Literal AI.
instrument_llamaindex
Instruments the Llama Index framework so that all RAG & LLM calls are logged to Literal AI.
langchain_callback
Creates a Callback for Langchain that logs all LLM calls to Literal AI.
Arguments:
Runs to ignore to declutter logging.
Runs to keep within ignored runs.
Returns:
The callback to use in Langchain’s invoke methods.
start_step
Creates a step and starts it in the current context. To log it on Literal AI use .end().
This is used to create Agent steps. For conversational messages use message instead.
Arguments:
The name of the step to create.
The type of the step. Must be one of the following :
“run”, “tool”, “llm”, “embedding”, “retrieval”,“rerank”, “undefined”.
The id of the step to create.
The id of the parent step.
The id of the parent thread.
Returns:
get_current_step
Gets the current step from the context.
get_current_thread
Gets the current thread from the context.
get_current_root_run
Gets the current root run from the context.
reset_context
Resets the context, forgetting active steps & setting current thread to None.
flush_and_stop
Sends all threads and steps to the Literal AI API. Waits synchronously for all API calls to be done.
LiteralClient
Synchronous client for interacting with the Literal AI API.
Example:
AsyncLiteralClient
Asynchronous client for interacting with the Literal AI API.
Example: