thijse/MemoryVectorStore

Sample of implementing a simple in-memory vector store

34
/ 100
Emerging

This project helps you find specific information buried in your PDF documents by creating a searchable index. You input PDF files, and it allows you to ask questions in plain language, returning relevant sections and a summarized answer. It's designed for anyone who needs to quickly extract precise answers from their document collections.

No commits in the last 6 months.

Use this if you need to build a system that can answer questions based on the content of your PDF documents.

Not ideal if you need to search extremely large collections of documents efficiently, as this version doesn't use advanced indexing for speed.

document-search information-retrieval PDF-analysis knowledge-base Q&A-system
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

9

Forks

2

Language

C#

License

MIT

Last pushed

Dec 02, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/thijse/MemoryVectorStore"

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