Overview

Zep’s Python and Typescript SDKs ship with ZepVectorStore and ZepChatMessageHistory classes that are compatible with Langchain’s JS and Python Expression Languages.

Managing Chat History Memory

Zep’s ZepChatMessageHistory class can be used to provide long-term memory for your LangChain chat apps or agents. Zep will store the entire historical message stream, and automatically enrich chat sessions.

You can also provide your bot or agent with access to relevant messages in long-term storage by using Zep’s built-in search.

Building Retrieval Augmented Generation Apps (Q&A over Docs)

Zep’s ZepVectorStore class can be used to store a collection of documents, metadata, and related embeddings. Retrieval Augmented Generation (RAG) apps can then use Zep’s vector search to surface documents relevant to a prompt.

Zep will automatically embed the documents using low-latency local models, ensuring that your app is fast and responsive.

Using Zep as a VectorStore and Document Retriever

See Python and Typescript examples of how to use ZepVectorStore with LangChain Expression Language in your application.

Using Zep as a LangChain Memory Store

See Python and Typescript examples of how to use ZepChatMessageHistory with LangChain Expression Language in your application.