# VectorDB

## Docs

- [Agentic RAG](https://mintlify.wiki/avnlp/vectordb/advanced/agentic-rag.md): LLM-driven retrieval loop with tool routing and self-reflection
- [Contextual compression](https://mintlify.wiki/avnlp/vectordb/advanced/contextual-compression.md): Reduce retrieved context to only relevant passages before generation
- [Cost optimization](https://mintlify.wiki/avnlp/vectordb/advanced/cost-optimization.md): Budget-aware retrieval and generation strategies for production RAG
- [Parent document retrieval](https://mintlify.wiki/avnlp/vectordb/advanced/parent-document-retrieval.md): Index small chunks but return full parent documents for richer context
- [Query enhancement](https://mintlify.wiki/avnlp/vectordb/advanced/query-enhancement.md): Improve retrieval recall with multi-query, HyDE, and step-back prompting
- [Database wrappers](https://mintlify.wiki/avnlp/vectordb/api/databases.md): Core vector database wrapper APIs for Chroma, Milvus, Pinecone, Qdrant, and Weaviate
- [Dataloaders](https://mintlify.wiki/avnlp/vectordb/api/dataloaders.md): Dataset loading and conversion utilities for evaluation and indexing
- [Haystack components](https://mintlify.wiki/avnlp/vectordb/api/haystack/components.md): Reusable component APIs for Haystack RAG pipelines
- [Haystack pipelines](https://mintlify.wiki/avnlp/vectordb/api/haystack/pipelines.md): Pre-built RAG pipeline APIs for Haystack integration
- [LangChain chains](https://mintlify.wiki/avnlp/vectordb/api/langchain/chains.md): Pre-built retrieval chain APIs for LangChain integration
- [LangChain components](https://mintlify.wiki/avnlp/vectordb/api/langchain/components.md): Reusable component APIs for LangChain RAG pipelines
- [Utilities](https://mintlify.wiki/avnlp/vectordb/api/utils.md): Shared utility APIs for evaluation, sparse embeddings, and document conversion
- [Architecture](https://mintlify.wiki/avnlp/vectordb/core/architecture.md): Overall package architecture and module boundaries
- [Dataloaders](https://mintlify.wiki/avnlp/vectordb/core/dataloaders.md): Dataset loading and normalization system
- [Evaluation](https://mintlify.wiki/avnlp/vectordb/core/evaluation.md): Evaluation metrics and benchmarking for retrieval pipelines
- [Vector databases](https://mintlify.wiki/avnlp/vectordb/core/vector-databases.md): Overview of supported vector databases
- [JSON indexing](https://mintlify.wiki/avnlp/vectordb/data/json-indexing.md): Index and filter structured JSON documents with nested field support
- [Metadata filtering](https://mintlify.wiki/avnlp/vectordb/data/metadata-filtering.md): Filter search results using structured document attributes
- [Multi-tenancy](https://mintlify.wiki/avnlp/vectordb/data/multi-tenancy.md): Tenant-isolated indexing and retrieval at scale
- [Namespaces](https://mintlify.wiki/avnlp/vectordb/data/namespaces.md): Logical data partitioning within a single index
- [Chroma](https://mintlify.wiki/avnlp/vectordb/databases/chroma.md): Lightweight vector database for local development and rapid prototyping
- [Milvus](https://mintlify.wiki/avnlp/vectordb/databases/milvus.md): Scalable vector database with partition-key isolation and hybrid retrieval
- [Vector databases overview](https://mintlify.wiki/avnlp/vectordb/databases/overview.md): Compare and select the right vector database for your RAG pipeline
- [Pinecone](https://mintlify.wiki/avnlp/vectordb/databases/pinecone.md): Managed vector database with native sparse-dense hybrid retrieval
- [Qdrant](https://mintlify.wiki/avnlp/vectordb/databases/qdrant.md): High-performance vector database with quantization and MMR diversity
- [Weaviate](https://mintlify.wiki/avnlp/vectordb/databases/weaviate.md): Open-source vector database with native BM25 and generative search
- [Diversity filtering](https://mintlify.wiki/avnlp/vectordb/features/diversity-filtering.md): Post-retrieval redundancy reduction using MMR or clustering
- [Hybrid search](https://mintlify.wiki/avnlp/vectordb/features/hybrid-search.md): Combine dense and sparse retrieval with fusion for best-of-both-worlds search
- [Maximal marginal relevance](https://mintlify.wiki/avnlp/vectordb/features/mmr.md): Balance relevance and diversity to reduce redundancy in search results
- [Reranking](https://mintlify.wiki/avnlp/vectordb/features/reranking.md): Cross-encoder second-stage scoring for higher precision retrieval
- [Semantic search](https://mintlify.wiki/avnlp/vectordb/features/semantic-search.md): Dense vector similarity search for conceptual matching
- [Sparse search](https://mintlify.wiki/avnlp/vectordb/features/sparse-search.md): Keyword and lexical matching with SPLADE or BM25 for exact terminology
- [Benchmarking retrieval quality](https://mintlify.wiki/avnlp/vectordb/guides/benchmarking.md): Guide to evaluating and comparing retrieval quality across vector databases and configurations
- [Building a RAG pipeline](https://mintlify.wiki/avnlp/vectordb/guides/building-rag-pipeline.md): Step-by-step tutorial for building a complete RAG pipeline from scratch
- [Configuration reference](https://mintlify.wiki/avnlp/vectordb/guides/configuration.md): Complete guide to YAML configuration file format and all available options
- [Environment variables](https://mintlify.wiki/avnlp/vectordb/guides/environment-variables.md): Complete reference for environment variables used in VectorDB configurations
- [Production deployment](https://mintlify.wiki/avnlp/vectordb/guides/production-deployment.md): Best practices for deploying RAG pipelines to production environments
- [Haystack reusable components](https://mintlify.wiki/avnlp/vectordb/haystack/components.md): Reusable pipeline components for routing, compression, query enhancement, and result fusion
- [Haystack hybrid search](https://mintlify.wiki/avnlp/vectordb/haystack/hybrid-search.md): Combine dense semantic embeddings with sparse lexical embeddings using Reciprocal Rank Fusion
- [Haystack integration overview](https://mintlify.wiki/avnlp/vectordb/haystack/overview.md): Learn about Haystack-based retrieval and RAG pipeline implementations for vector databases
- [Haystack pipeline architecture](https://mintlify.wiki/avnlp/vectordb/haystack/pipelines.md): Pipeline architecture patterns and component composition for production RAG systems
- [Haystack semantic search](https://mintlify.wiki/avnlp/vectordb/haystack/semantic-search.md): Dense vector similarity search using Haystack pipelines
- [Installation](https://mintlify.wiki/avnlp/vectordb/installation.md): Install VectorDB using uv package manager
- [Introduction](https://mintlify.wiki/avnlp/vectordb/introduction.md): Production-ready RAG pipelines and vector database toolkit for Haystack and LangChain
- [Chain architecture and patterns](https://mintlify.wiki/avnlp/vectordb/langchain/chains.md): Agentic RAG with multi-step iterative retrieval, reflection, and routing
- [Reusable LangChain components](https://mintlify.wiki/avnlp/vectordb/langchain/components.md): Self-contained building blocks for routing, query enhancement, and context compression
- [Hybrid search implementation](https://mintlify.wiki/avnlp/vectordb/langchain/hybrid-search.md): Combine dense semantic embeddings with sparse lexical embeddings using Reciprocal Rank Fusion
- [LangChain integration overview](https://mintlify.wiki/avnlp/vectordb/langchain/overview.md): Build RAG pipelines with LangChain's retriever, chain, and document store abstractions
- [Semantic search pipelines](https://mintlify.wiki/avnlp/vectordb/langchain/semantic-search.md): Dense vector similarity search with HuggingFace embeddings and LangChain retrievers
- [Quickstart](https://mintlify.wiki/avnlp/vectordb/quickstart.md): Build your first RAG pipeline with VectorDB in minutes