stephantul/reach
Load embeddings and featurize your sentences.
Reach helps developers quickly find the most relevant pieces of text for a given query in a RAG (Retrieval Augmented Generation) system. You input a collection of text snippets and their numerical representations (vectors), then query it with new text to retrieve similar content. It's designed for machine learning engineers and developers building AI applications.
No commits in the last 6 months. Available on PyPI.
Use this if you need a lightweight, fast, and easy-to-integrate vector store for RAG projects with up to 1 million vectors, especially for just-in-time querying.
Not ideal if your RAG system requires persistent, large-scale vector storage beyond 1 million entries or advanced vector database features like filtering and distributed deployment.
Stars
31
Forks
7
Language
Python
License
MIT
Category
Last pushed
Oct 23, 2024
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/stephantul/reach"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
shibing624/text2vec
text2vec, text to vector....
predict-idlab/pyRDF2Vec
đ Python Implementation and Extension of RDF2Vec
IntuitionEngineeringTeam/chars2vec
Character-based word embeddings model based on RNN for handling real world texts
IITH-Compilers/IR2Vec
Implementation of IR2Vec, LLVM IR Based Scalable Program Embeddings
ddangelov/Top2Vec
Top2Vec learns jointly embedded topic, document and word vectors.