• These are built using LanceDB, a free, open-source, serverless vectorDB that requires no setup.
• It integrates into Python data ecosystem so you can simply start using these in your existing data pipelines in pandas, arrow, pydantic etc.
• LanceDB has native Typescript SDK using which you can run vector search in serverless functions!

This repository is divided into 2 sections:

• Examples - Get right into the code with minimal introduction, aimed at getting you from an idea to PoC within minutes!
• Applications - Ready to use Python and web apps using applied LLMs, VectorDB and GenAI tools

Applied examples that get right into the code with minimal introduction, aimed at getting you from an idea to PoC within minutes! Examples are available as:

• Colab notebooks - that builds the application is stages allowing you to investigate results at every intermediate stage.
• Python scripts - for cases where you'd like directly to use the file or snippets to integrate in your application
• JS/TS scripts - Some examples are written using lancedb's native js library! These script/snippets can also be directly integrated in your web applications.

The following examples are organized into different tables to make similar types of examples easily accessible.

Build applications/examples using LanceDB for efficient vector-based document retrieval.

Build from Scratch	Interactive Notebook & Scripts
Build RAG from Scratch
Local RAG from Scratch with Llama3
Multi-Head RAG from Scratch

Create a multimodal search application using LanceDB for efficient vector-based retrieval of text and image data. Input text or image queries to find the most relevant documents and images from your corpus.

Multimodal	Interactive Notebook & Scripts	Blog
Multimodal CLIP: DiffusionDB
Multimodal CLIP: Youtube videos
Multimodal Image + Text Search

Develop a Retrieval-Augmented Generation (RAG) application using LanceDB for efficient vector-based information retrieval. Input text queries to retrieve relevant documents and generate comprehensive answers by combining retrieved information.

RAG	Interactive Notebook & Scripts	Blog
RAG with Matryoshka Embeddings and LlamaIndex
Improve RAG with Re-ranking
Instruct-Multitask
Improve RAG with HyDE
Improve RAG with LOTR
Advanced RAG: Parent Document Retriever
Corrective RAG with Langgraph
Contextual-Compression-with-RAG
Improve RAG with FLARE
Query Expansion and Reranker
RAG Fusion
Agentic RAG

Build a vector search application using LanceDB for efficient vector-based document retrieval. Input text queries to find the most relevant documents from your corpus.

Vector Search	Interactive Notebook & Scripts	Blog
Inbuilt Hybrid Search
Hybrid search BM25 & lancedb
NER powered Semantic Search
Audio Search
Multi-lingual search
Facial Recognition
Sentiment Analysis : Analysing Hotel Reviews
Vector Arithmetic with LanceDB
Imagebind demo app
Search Within Images
Vector Search with TransformersJS
Accelerate Vector Search Applications Using OpenVINO

Create a chatbot application using LanceDB for efficient vector-based response generation. Input user queries to retrieve relevant context and generate coherent, context-aware replies.

Chatbot	Interactive Notebook & Scripts	Blog
Databricks DBRX Website Bot
CLI-based SDK Manual Chatbot with Phidata
Youtube transcript search bot
Langchain: Code Docs QA bot
Context-Aware Chatbot using Llama 2 & LanceDB
Chat with csv using Hybrid Search

Develop an evaluation application. Input reference and candidate texts to measure their performance on various metrics.

Evaluation	Interactive Notebook & Scripts	Blog
Evaluating Prompts with Prompttools
Evaluating RAG with RAGAs

Design an AI agents coordination application with LanceDB for efficient vector-based communication and collaboration. Input queries to enable AI agents to exchange information, coordinate tasks, and achieve shared goals effectively.

AI Agents	Interactive Notebook & Scripts	Blog
AI Agents: Reducing Hallucination
AI Trends Searcher with CrewAI
SuperAgent Autogen

Create a recommender system application with LanceDB for efficient vector-based item recommendation. Input user preferences or item features to generate personalized recommendations and enhance user experience.

Recommender Systems	Interactive Notebook & Scripts	Blog
Movie Recommender
Movie Recommender with Genre
Product Recommender
Arxiv paper recommender

Checkout concepts of LLM applications pipeline to ensures accurate information retrieval.

Concepts	Interactive Notebook	Blog
A Primer on Text Chunking and its Types
Langchain LlamaIndex Chunking
Create structured dataset using Instructor
Comparing Cohere Rerankers with LanceDB
Product Quantization: Compress High Dimensional Vectors
LLMs, RAG, & the missing storage layer for AI
Fine-Tuning LLM using PEFT & QLoRA
Extracting Complex tables-text from PDFs using LlamaParse

These are ready to use applications built using LanceDB serverless vector database. You can explore these open source projects, use parts of them in your projects or build your applications on top of these.

Project Name	Description	Screenshot
YOLOExplorer	Iterate on your YOLO / CV datasets using SQL, Vector semantic search, and more within seconds
Website Chatbot (Deployable Vercel Template)	Create a chatbot from the sitemap of any website/docs of your choice. Built using vectorDB serverless native javascript package.
Chat with multiple URL/website	Conversational AI for Any Website with Mistral,Bge Embedding & LanceDB
Talk with Youtube Video using GPT4 Vision API	Talk with Youtube Video using GPT4 Vision API and Langchain
Talk with Podcast	Talk with Youtube Podcast using Ollama and insanely-fast-whisper
Talk with Wikipedia	Talk with Wikipedia Pages
Talk with Github	Talk with Github Codespaces using Qwen1.5
Document Chat with Langroid	Talk with your Documents using Langroid
Hr chatbot	Hr chatbot - ask your personal query using zero-shot React agent & tools
Advanced Chatbot with Parler TTS	This Chatbot app uses Lancedb Hybrid search, FTS & reranker method with Parlers TTS library.
Multi-Modal Search Engine	Create a Multi-modal search engine app, to search images using both images or text
Multimodal Myntra Fashion Search Engine	This app uses OpenAI's CLIP to make a search engine that can understand and deal with both written words and pictures.
Multilingual-RAG	Multilingual RAG with cohere embedding & support 100+ languages
Fastapi RAG template	FastAPI based RAG template with Websocket support
GTE MLX RAG	mlx based RAG model using lancedb api support
Healthcare Chatbot	Healthcare chatbot using domain specific LLM & Embedding model

🌟 New! 🌟 Applied GenAI and VectorDB course on Udacity Learn about GenAI and vectorDBs using LanceDB in the recently launched Udacity Course

If you're working on some cool applications that you'd like to add to this repo, please open a PR!