> ## Documentation Index > Fetch the complete documentation index at: https://phidatainc-agui.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Vector Databases > Store embeddings and search for similar content. Vector databases store content as embeddings and enable similarity search. When an agent searches the knowledge base, the query is converted to an embedding and matched against stored vectors to find relevant content. ## How It Works Documents are split into smaller pieces for more precise retrieval. Each chunk is converted to a vector embedding and stored in the database. Queries are embedded and matched against stored vectors to find similar content. ## Hybrid Search Many vector databases support hybrid search, combining vector similarity with keyword matching. This improves results for queries that benefit from both semantic understanding and exact term matching. Hybrid search works by: 1. Finding semantically similar content via vector search 2. Finding keyword matches via full-text search 3. Combining results using ranked fusion ## Supported Databases MongoDB vCore vector search Distributed database with vector search Open-source embedding database Analytical database with vector search NoSQL with vector search Local, serverless, hybrid search Use any LangChain vector store Graph-based RAG Scalable vector database Atlas vector search PostgreSQL extension, hybrid search Managed vector database High-performance vector search In-memory with vector search Real-time analytics with vectors Multi-model database Serverless vector search Vector search with modules ## Choosing a Database **LanceDB** or **ChromaDB** for zero-setup local development **PgVector** if you already use PostgreSQL **Pinecone** or **Weaviate Cloud** for no-ops deployment **Qdrant** or **Milvus** for large-scale search ## Async Support Vector databases with async support enable non-blocking operations for better performance in production. Use `ainsert` and `asearch` methods when building async agents. ```python theme={null} # Async insert await knowledge.ainsert(url="https://example.com/docs.pdf") # Async search results = await knowledge.asearch(query="How do I configure X?") ```