Skip to main content
Findable provides two paths for querying external vector stores:
  1. Vector Retriever data source (type: 'vectorretriever' in dataSources[]) — configure directly on a chat to query a vector store as part of multi-source RAG
  2. Flow Designer tool nodes (integrationType: 'vector_store') — use a vector store as a tool inside a Flow Designer workflow
Both approaches share the same IDataConnection registry for managing credentials and endpoints.

​
Supported Providers

Tier 1 — High Priority (DataPlatformType values in IDataConnection):
ProviderPlatform TypeDescription
PineconepineconeManaged vector database
pgvectorpgvectorPostgreSQL vector extension
WeaviateweaviateOpen-source vector database
QdrantqdrantHigh-performance vector similarity engine
ChromachromaOpen-source embedding database
ElasticsearchelasticsearchFull-text + vector search
OpenSearchopensearchAWS-managed search and analytics
RedisredisIn-memory vector search
Tier 2 — Enterprise/Cloud (VECTOR_STORE_PROVIDER in Flow Designer): Oracle Vector, IBM watsonx, AWS Kendra, Vertex AI Search, Milvus, MongoDB Atlas Tier 3 — Specialized: Vespa, LanceDB, FAISS, Marqo

​
Data Connection Fields (Vector Stores)

Vector store connections are managed via the unified IDataConnection interface in the dataconnections Cosmos container. When type is a vector store platform, these additional fields apply:
FieldTypeDescription
indexstring?Index / collection / class name (Pinecone index, Weaviate class, Qdrant collection)
namespacestring?Namespace / partition (Pinecone namespace, Redis prefix)
verifySSLboolean?Verify SSL certificates (default: true)
maxRetriesnumber?Maximum retry attempts
connectionStringstring?Full connection string (alternative to individual fields)
Authentication types vary by provider — see getAuthTypesForPlatform() in dataConnectionTypes.ts.

​
Vector Retriever Data Source

To query a vector store directly from a chat’s RAG pipeline, add a vectorretriever entry to the chat’s dataSources[]:
FieldTypeDescription
type'vectorretriever'Identifies this as a vector retriever source
vectorConnectionIdstringFK to IDataConnection in the data connections registry
vectorTopKnumber?Number of results (default: 5)
vectorSearchType'vector' | 'semantic' | 'hybrid' | 'keyword'Search strategy
vectorMinScorenumber?Minimum similarity score (0–1)
The orchestrator queries the vector store in parallel with other data sources and merges results into the RAG context.

​
Flow Designer Vector Store Config (IVectorStoreConfig)

For Flow Designer tool nodes with integrationType: 'vector_store', the configuration has three parts: Connection (IVectorStoreConnectionConfig):
  • endpoint, apiKey, index, environment, projectId, region
  • SSL/TLS, connection pool settings
Search (IVectorStoreSearchConfig):
  • topK, minScore, searchType (vector / semantic / hybrid / keyword)
  • similarityMetric (cosine / euclidean / dotProduct / l2)
  • Metadata filters, namespace filters
  • Reranking support (enableReranking, rerankingModel)
  • Query expansion (enableQueryExpansion, expansionPrompt)
  • Hybrid weights (keywordWeight, vectorWeight)
Embedding (optional):
  • modelEndpointId — FK to AI model endpoint for query vectorization
  • embeddingDimensions, batchSize
See Vector Store Quick Reference and Provider Template for detailed setup.