LanceDB

REST API

Initializing search

lancedb/lancedb

Home
Quick start
Concepts
Guides
Managing Embeddings
Integrations
Examples
Studies
API reference
LanceDB Cloud

LanceDB

lancedb/lancedb

Home
Home
- LanceDB
- 🏃🏼‍♂️ Quick start
- 📚 Concepts
  📚 Concepts
  - Vector search
  - Indexing
    Indexing
    
    IVFPQ
    
    HNSW
  - Storage
  - Data management
- 🔨 Guides
  🔨 Guides
  - Working with tables
  - Building a vector index
  - Vector Search
  - Full-text search (native)
  - Full-text search (tantivy-based)
  - Building a scalar index
  - Hybrid search
    Hybrid search
    
    Overview
    
    Comparing Rerankers
    
    Airbnb financial data example
  - RAG
    RAG
    
    Vanilla RAG
    
    Multi-head RAG
    
    Corrective RAG
    
    Agentic RAG
    
    Graph RAG
    
    Self RAG
    
    Adaptive RAG
    
    SFR RAG
    
    Advanced Techniques
    Advanced Techniques
    
    HyDE
    
    FLARE
  - Reranking
    Reranking
    
    Quickstart
    
    Cohere Reranker
    
    Linear Combination Reranker
    
    Reciprocal Rank Fusion Reranker
    
    Cross Encoder Reranker
    
    ColBERT Reranker
    
    Jina Reranker
    
    OpenAI Reranker
    
    AnswerDotAi Rerankers
    
    Voyage AI Rerankers
    
    Building Custom Rerankers
    
    Example
  - Filtering
  - Versioning & Reproducibility
  - Configuring Storage
  - Migration Guide
  - Tuning retrieval performance
    Tuning retrieval performance
    
    Choosing right query type
    
    Reranking
    
    Embedding fine-tuning
- 🧬 Managing embeddings
  🧬 Managing embeddings
  - Understand Embeddings
  - Get Started
  - Embedding functions
  - Available models
    Available models
    
    Overview
    
    Text Embedding Functions
    Text Embedding Functions
    
    Sentence Transformers
    
    Huggingface Embedding Models
    
    Ollama Embeddings
    
    OpenAI Embeddings
    
    Instructor Embeddings
    
    Gemini Embeddings
    
    Cohere Embeddings
    
    Jina Embeddings
    
    AWS Bedrock Text Embedding Functions
    
    IBM watsonx.ai Embeddings
    
    Voyage AI Embeddings
    
    Multimodal Embedding Functions
    Multimodal Embedding Functions
    
    OpenClip embeddings
    
    Imagebind embeddings
    
    Jina Embeddings
  - User-defined embedding functions
  - Example: Multi-lingual semantic search
  - Example: MultiModal CLIP Embeddings
- 🔌 Integrations
  🔌 Integrations
  - Tools and data formats
  - Pandas and PyArrow
  - Polars
  - DuckDB
  - LangChain
    LangChain
    
    LangChain 🔗
    
    LangChain demo
    
    LangChain JS/TS 🔗
  - LlamaIndex 🦙
    LlamaIndex 🦙
    
    LlamaIndex docs
    
    LlamaIndex demo
  - Pydantic
  - Voxel51
  - PromptTools
  - dlt
  - phidata
- 🎯 Examples
  🎯 Examples
  - Overview
  - 🐍 Python
    🐍 Python
    
    Overview
    
    Build From Scratch
    
    Multimodal
    
    Rag
    
    Vector Search
    
    Chatbot
    
    Evaluation
    
    AI Agent
    
    Recommender System
    
    Miscellaneous
    Miscellaneous
    
    Serverless QA Bot with S3 and Lambda
    
    Serverless QA Bot with Modal
  - 👾 JavaScript
    👾 JavaScript
    
    Overview
    
    Serverless Website Chatbot
    
    YouTube Transcript Search
    
    TransformersJS Embedding Search
  - 🦀 Rust
    🦀 Rust
    
    Overview
- 📓 Studies
  📓 Studies
  - ↗Improve retrievers with hybrid search and reranking
- 💭 FAQs
- 🔍 Troubleshooting
- ⚙️ API reference
  ⚙️ API reference
- ☁️ LanceDB Cloud
  ☁️ LanceDB Cloud
  - Overview
  - API reference
    API reference
    
    🐍 Python
    
    👾 JavaScript
    
    REST API
Quick start
Concepts
Concepts
- Vector search
- Indexing
  Indexing
  - IVFPQ
  - HNSW
- Storage
- Data management
Guides
Guides
- Working with tables
- Building an ANN index
- Vector Search
- Full-text search (native)
- Full-text search (tantivy-based)
- Building a scalar index
- Hybrid search
  Hybrid search
- RAG
  RAG
  - Vanilla RAG
  - Multi-head RAG
  - Corrective RAG
  - Agentic RAG
  - Graph RAG
  - Self RAG
  - Adaptive RAG
  - SFR RAG
  - Advanced Techniques
    Advanced Techniques
    
    HyDE
    
    FLARE
- Reranking
  Reranking
- Filtering
- Versioning & Reproducibility
- Configuring Storage
- Migration Guide
- Tuning retrieval performance
  Tuning retrieval performance
Managing Embeddings
Managing Embeddings
- Understand Embeddings
- Get Started
- Embedding functions
- Available models
  Available models
  - Overview
  - Text Embedding Functions
    Text Embedding Functions
    
    Sentence Transformers
    
    Huggingface Embedding Models
    
    Ollama Embeddings
    
    OpenAI Embeddings
    
    Instructor Embeddings
    
    Gemini Embeddings
    
    Cohere Embeddings
    
    Jina Embeddings
    
    AWS Bedrock Text Embedding Functions
    
    IBM watsonx.ai Embeddings
  - Multimodal Embedding Functions
    Multimodal Embedding Functions
    
    OpenClip embeddings
    
    Imagebind embeddings
    
    Jina Embeddings
- User-defined embedding functions
- Example - Multi-lingual semantic search
- Example - MultiModal CLIP Embeddings
Integrations
Integrations
Examples
Examples
- Example projects and recipes
- 🐍 Python
  🐍 Python
  - Overview
  - Build From Scratch
  - Multimodal
  - Rag
  - Vector Search
  - Chatbot
  - Evaluation
  - AI Agent
  - Recommender System
  - Miscellaneous
    Miscellaneous
    
    Serverless QA Bot with S3 and Lambda
    
    Serverless QA Bot with Modal
- 👾 JavaScript
  👾 JavaScript
- 🦀 Rust
  🦀 Rust
  - Overview
Studies
Studies
- Overview
- ↗Improve retrievers with hybrid search and reranking
API reference
API reference
LanceDB Cloud
LanceDB Cloud
- Overview
- API reference
  API reference

REST API

Made with Material for MkDocs