This template demonstrates building a RAG conversation app using Zep.
Included in this template:
- Populating a Zep Document Collection with a set of documents (a Collection is analogous to an index in other Vector Databases).
- Using Zep's integrated embedding functionality to embed the documents as vectors.
- Configuring a LangChain ZepVectorStore Retriever to retrieve documents using Zep's built, hardware accelerated in Maximal Marginal Relevance (MMR) re-ranking.
- Prompts, a simple chat history data structure, and other components required to build a RAG conversation app.
- The RAG conversation chain.
Zep is an open source platform for productionizing LLM apps. Go from a prototype built in LangChain or LlamaIndex, or a custom app, to production in minutes without rewriting code.
- Fast! Zep’s async extractors operate independently of the your chat loop, ensuring a snappy user experience.
- Long-term memory persistence, with access to historical messages irrespective of your summarization strategy.
- Auto-summarization of memory messages based on a configurable message window. A series of summaries are stored, providing flexibility for future summarization strategies.
- Hybrid search over memories and metadata, with messages automatically embedded on creation.
- Entity Extractor that automatically extracts named entities from messages and stores them in the message metadata.
- Auto-token counting of memories and summaries, allowing finer-grained control over prompt assembly.
Set up a Zep service by following the Quick Start Guide.
Ingesting Documents into a Zep Collection
python ingest.py to ingest the test documents into a Zep Collection. Review the file to modify the Collection name and document source.
To use this package, you should first have the LangChain CLI installed:
pip install -U "langchain-cli[serve]"
To create a new LangChain project and install this as the only package, you can do:
langchain app new my-app --package rag-conversation-zep
If you want to add this to an existing project, you can just run:
langchain app add rag-conversation-zep
And add the following code to your
from rag_conversation_zep import chain as rag_conversation_zep_chain
add_routes(app, rag_conversation_zep_chain, path="/rag-conversation-zep")
(Optional) Let's now configure LangSmith. LangSmith will help us trace, monitor and debug LangChain applications. LangSmith is currently in private beta, you can sign up here. If you don't have access, you can skip this section
export LANGCHAIN_PROJECT=<your-project> # if not specified, defaults to "default"
If you are inside this directory, then you can spin up a LangServe instance directly by:
This will start the FastAPI app with a server is running locally at http://localhost:8000
We can see all templates at http://127.0.0.1:8000/docs We can access the playground at http://127.0.0.1:8000/rag-conversation-zep/playground
We can access the template from code with:
from langserve.client import RemoteRunnable
runnable = RemoteRunnable("http://localhost:8000/rag-conversation-zep")