Documentation

Community

Guides

News

Letta

API reference

Python SDK

View on GitHub

Support

Attach a data source to an existing agent.

Attach Source To Agent

Embedding model configuration. This object specifies all the information necessary to access an embedding model to usage with Letta, except for secret keys.

Attributes:
    embedding_endpoint_type (str): The endpoint type for the model.
    embedding_endpoint (str): The endpoint for the model.
    embedding_model (str): The model for the embedding.
    embedding_dim (int): The dimension of the embedding.
    embedding_chunk_size (int): The chunk size of the embedding.
    azure_endpoint (:obj:`str`, optional): The Azure endpoint for the model (Azure only).
    azure_version (str): The Azure version for the model (Azure only).
    azure_deployment (str): The Azure deployment for the model (Azure only).

Azure Deployment

Azure Endpoint

Azure Version

Embedding Chunk Size

Embedding Dim

The endpoint for the model (`None` if local).

Embedding Endpoint

Embedding Endpoint Type

Embedding Model

EmbeddingConfig

Location

Message

Error Type

ValidationError

bearerAuth

Representation of a source, which is a collection of documents and passages.

Parameters:
    id (str): The ID of the source
    name (str): The name of the source.
    embedding_config (EmbeddingConfig): The embedding configuration used by the source.
    created_at (datetime): The creation date of the source.
    user_id (str): The ID of the user that created the source.
    metadata_ (dict): Metadata associated with the source.
    description (str): The description of the source.

Source

HTTPValidationError

Letta is an AI platform for building stateful LLM applications.

Overview

Welcome to Letta

Quickstart

Developer quickstart

Install and setup Letta to run the server & ADE

Installation

OpenAI

Ollama

Anthropic

vLLM

Cohere

Letta concepts

Key concepts

MemGPT concepts

MemGPT

Tools

Memory

Messaging agents

Running the Letta Server

Understanding the concept of LLM memory management introduced in MemGPT

Memory management

Understanding memory management

Learn how to create custom memory classes

Custom memory

Creating custom memory classes

Get Tool

Delete Tool

Update Tool

Get Tool Id

Get a list of all tools available to agents created by a user

List All Tools

Create Tool

Get Source

Delete Source

Update the name or documentation of an existing data source.

Update Source

Get Source Id By Name

List Sources

Create Source

Detach a data source from an existing agent.

Detach Source From Agent

Upload File To Source

List all passages associated with a data source.

List Passages

List all documents associated with a data source.

List Documents

List all agents associated with a given user.
This endpoint retrieves a list of all agents and their configurations associated with the specified user ID.

List Agents

Create a new agent with the specified configuration.

Create Agent

Get Agent State

Delete Agent

Update Agent

Get the sources associated with an agent.

Get Agent Sources

Retrieve the messages in the context of a specific agent.

Get Agent In Context Messages

Retrieve the memory state of a specific agent.
This endpoint fetches the current memory state of the agent identified by the user ID and agent ID.

Get Agent Memory

Update the core memory of a specific agent.
This endpoint accepts new memory contents (human and persona) and updates the core memory of the agent identified by the user ID and agent ID.

Update Agent Memory

Retrieve the summary of the recall memory of a specific agent.

Get Agent Recall Memory Summary

Retrieve the summary of the archival memory of a specific agent.

Get Agent Archival Memory Summary

Retrieve the memories in an agent's archival memory store (paginated query).

Get Agent Archival Memory

Insert a memory into an agent's archival memory store.

Insert Agent Archival Memory

Delete a memory from an agent's archival memory store.

Delete Agent Archival Memory

Get Agent Messages

Process a user message and return the agent's response.
This endpoint accepts a message from a user and processes it through the agent.
It can optionally stream the response if 'stream_steps' or 'stream_tokens' is set to True.

Send Message

Update the details of a message associated with an agent.

Update Message

List Llm Backends

List Embedding Backends

List Blocks

Create Block

Get Block

Delete Block

Update Block

List Jobs

List Active Jobs

Get Job

Query deployed agents

Create deployed agent

Chat with deployed agent

Get deployed agent SDK ID

Migrate your deployed agent to a new source agent. This will overwrite the current agent's datasources, tools, and core memories. Archival and messages will be preserved.

tools

sources

agents

models

blocks

jobs

deployment

Attach Source To Agent

Authorizations

Path Parameters

Query Parameters

Response