sujee/mongodb-atlas-vector-search

Using MongDB Atlas with embedding models and LLMs to do vector search and RAG applications

41
/ 100
Emerging

This helps developers build applications that can understand and answer questions about large collections of documents. It takes raw text or PDF documents, processes them to create numerical representations (embeddings), and stores them in MongoDB Atlas. The output is a system that can intelligently retrieve relevant information and generate answers using large language models, useful for creating smart search or Q&A features.

No commits in the last 6 months.

Use this if you are a developer looking for practical examples and code to implement vector search and RAG capabilities using MongoDB Atlas.

Not ideal if you are an end-user without programming knowledge, as this project provides developer-focused code samples, not a ready-to-use application.

information-retrieval application-development database-management AI-powered-search knowledge-base-systems
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

25

Forks

16

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Aug 23, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/sujee/mongodb-atlas-vector-search"

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