Retrieval Agent
Facilitates the development of retrieval agents using LangGraph for question answering.
About
This starter project provides a foundation for building retrieval-based question answering systems using LangGraph and LangGraph Studio. It includes pre-built graphs for indexing documents and managing chat history to provide personalized responses based on retrieved context. The template supports various vector stores, embedding models, and language models, allowing for extensive customization and experimentation.
Key Features
- Includes an index graph for document processing and indexing.
- Compatible with OpenAI and Cohere embedding models.
- 87 GitHub stars
- Supports multiple vector stores: Elasticsearch, MongoDB Atlas, Pinecone.
- Manages chat history for context-aware responses.
- Offers customizable response generation with Anthropic models.
Use Cases
- Indexing and searching documents within a chat bot.
- Creating a retrieval agent for knowledge base management.
- Building a personalized question answering system.
Sponsored