raphaelsty/neural-tree
Tree-based indexes for neural-search
This project helps information retrieval specialists and search engineers build faster neural search systems. It takes your existing documents and a fine-tuned search model (like ColBERT or Sentence Transformers), then creates a hierarchical tree index. The output is a significantly accelerated search process for your queries, without sacrificing the quality of your search results.
No commits in the last 6 months. Available on PyPI.
Use this if you need to speed up the retrieval time of your neural search application while maintaining the accuracy of your current model.
Not ideal if you don't already have an existing neural search model fine-tuned for your specific data, as this tool optimizes search speed rather than model training.
Stars
31
Forks
2
Language
Python
License
MIT
Category
Last pushed
Mar 04, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/raphaelsty/neural-tree"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
deepset-ai/haystack-tutorials
Here you can find all the Tutorials for Haystack 📓
aryn-ai/sycamore
🍁 Sycamore is an LLM-powered search and analytics platform for unstructured data.
MaartenGr/PolyFuzz
Fuzzy string matching, grouping, and evaluation.
unum-cloud/USearch
Fast Open-Source Search & Clustering engine × for Vectors & Arbitrary Objects × in C++, C,...
towhee-io/towhee
Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.