AIbase
Product LibraryTool Navigation

rag-openai-pinecone

Public

The RAG solution extracts text from URLs, generates embeddings, and stores vectors in Pinecone, using an API for semantic searches and answers with GPT-3.5-turbo. Developed in Python, it is containerized with Docker, and managed via GitHub Actions for CI.

Creat2024-06-16T00:17:10
Update2024-10-26T01:36:35
0
Stars
0
Stars Increase