madeyexz/markdown-file-query

Semantic QA with a markdown database: Query any markdown file using vector embedding, Pinecone vector database and GPT (langchain). A weaker version of privateGPT

Archived
26
/ 100
Experimental

Chunks markdown files using LangChain's text splitter, embeds them via OpenAI's embedding model, and stores vectors in Pinecone for semantic similarity search. When queried, it retrieves the 3 most relevant chunks by cosine similarity and passes them to GPT-3 for natural language answer generation. Supports direct querying of exported Notion and Obsidian markdown exports without requiring local LLM infrastructure.

No commits in the last 6 months.

Archived No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

32

Forks

4

Language

Python

License

Last pushed

May 27, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/madeyexz/markdown-file-query"

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