retrieval-agent-template

Dependency freshness

Declared = lowest version the kit's dependency file (package.json, pyproject.toml or requirements.txt) allows. Latest = the npm "latest" tag or the newest PyPI release. TypeScript, the Stripe SDK, FastAPI and other 0.x packages are shown but not counted in the verdict.

What's in the stack

AI

LangChain, LangGraph

Detected from declared dependencies. A listed package means it's installed, not necessarily fully wired up.

What the README says you get

• AI
  Anthropic chat modelsTo use Anthropic's chat models
• AI
  OpenAI chat modelsTo use OpenAI's chat models
• AI
  OpenAI embeddingsTo use OpenAI's embeddings
• AI
  Cohere embeddingsTo use Cohere's embeddings
• AI
  Index graphThe index graph takes in document objects and strings, and it indexes them
• AI
  Retrieval chat botThe retrieval chat bot manages a chat history and responds based on fetched context
• AI
  User ID filteringfiltered by the user's ID for personalized responses
• AI
  Configurable search parametersAdjust search parameters
• AI
  Customizable response promptCustomize the response generation
• AI
  Configurable language modelChange the language model
• AI
  Extend graph nodesExtend the graph
• Data
  Elasticsearch retrieverElasticsearch can be configured as the knowledge base provider
• Data
  MongoDB Atlas retrieverMongoDB Atlas is a fully-managed cloud database that includes vector search
• Data
  Pinecone Serverless retrieverPinecone is a managed, cloud-native vector database

Extracted from the kit's README by a local AI model (deepseek-flash) on Sep 29, 2026. Every item is checked against an exact README quote. A README claim is the maker's description, not something we tested.