IuriiD/pinecone-faiss-pgvector

Comparing vector DBs Pinecone, FAISS & pgvector in combination with OpenAI Embeddings for semantic search

29
/ 100
Experimental

This project helps developers and MLOps engineers evaluate different vector databases for semantic search applications. It takes conversation logs and OpenAI embeddings as input, then benchmarks Pinecone, FAISS, and pgvector to help determine which database is best suited for identifying and responding to repetitive questions in chatbots. The output is a performance comparison, enabling informed decisions for chatbot enhancement.

No commits in the last 6 months.

Use this if you are a developer building a chatbot and need to select the most efficient vector database to power automatic semantic search for frequently asked questions.

Not ideal if you are an end-user looking for a ready-to-use chatbot solution, as this project focuses on the underlying database technology.

chatbot-development semantic-search vector-database-evaluation MLOps AI-application-development
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 16 / 25

How are scores calculated?

Stars

9

Forks

7

Language

Jupyter Notebook

License

Last pushed

Jul 24, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/IuriiD/pinecone-faiss-pgvector"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.