pgvector
PostgreSQL extension for vector similarity search
About
Adds vector similarity search to PostgreSQL. Perfect for teams already on Postgres who don't want to manage a separate vector DB.
Choose pgvector when…
- •You're already on PostgreSQL
- •You want vector search without a separate database
- •SQL queries combined with embedding search are needed
Builder Slot
The memory layer — stores and retrieves vector embeddings for RAG and semantic search
Other tools in this slot:
Stack Genome Detection
AIchitect's Genome scanner detects pgvector in your project via these signals:
pgvectorIntegrates with (3)
LangGraph retrieval nodes query pgvector via psycopg2 or SQLAlchemy, keeping vector search within the existing Postgres database.
→ Enterprise RAG with no separate vector DB — LangGraph agents retrieve from the same Postgres instance the rest of the app uses.
LangChain's pgvector integration stores and retrieves embeddings from Postgres via the pgvector extension using standard SQL.
→ RAG without a separate vector database — the app's existing Postgres becomes the retrieval layer.
LlamaIndex stores embeddings in Postgres via its PGVectorStore adapter, colocating vector and relational queries.
→ RAG on top of an existing Postgres database — no separate vector DB, structured and vector queries in the same store.
Alternatives to consider (4)
Pricing
In 2 stacks
Ruled out by 3 stacks
Badge
Add to your GitHub README
[](https://aichitect.dev/tool/pgvector)Explore the full AI landscape
See how pgvector fits into the bigger picture — browse all 207 tools and their relationships.