Skip to main content

​
Vector Store

Vector Store integration is coming soon. This page will be updated when the feature is available.
The Vector Store node will allow you to connect a vector database to your agent for retrieval-augmented generation (RAG). Your agent will be able to search a knowledge base during a conversation and use the retrieved content to inform its responses.

​
Planned capabilities

  • Connect to popular vector databases (Pinecone, Weaviate, Chroma, etc.)
  • Configure collection name, top-K results, and similarity threshold
  • Automatically inject retrieved context into the LLM’s prompt
  • Use in combination with MCP servers and Exa search

​
Parameters (planned)

ParameterTypeDescription
collectionNamestringThe vector database collection to query
topKenumNumber of results to retrieve: 1, 3, 5, or 10
similarityThresholdstringMinimum similarity score for results