A collection of recipes and sample application starter kits to build with LLMs using PostgreSQL and Timescale Vector.
Learn more about Timescale Vector, PostgreSQL++ for AI applications: timescale.com/ai
Sign up for a free cloud PostgreSQL database to use to work thru the examples in this repo. You'll get 90 days free by signing up with the link above.
Timescale Vector enables you to power AI applications using PostgreSQL to store vector, relational and time-series data. It enhances pgvector with faster search, higher recall, and more efficient time-based filtering.
- Overview and Performance Benchmarks
- Timescale Vector LangChain Integration
- Timescale Vector LlamaIndex Integration
- Timescale Vector Python Client Library
- Timescale Vector Python Tutorial
- TSV Time Machine: Chat with git the commit history of any repo. Stack: LlamaIndex, Streamlit, Timescale Vector (PostgreSQL), Python. Live demo
- Create, store and query OpenAI embeddings with PostgreSQL and pgvector
- Nearest Neighbor Indexes: What Are ivfflat Indexes in pgvector and How Do They Work
- Introduction to LangChain for LLM applications using pgvector as a vectorstore
Note: If you need to setup Python, pyenv and Jupyter on your Mac, follow this handy tutorial.