analyticsinmotion/symrank
🐍📦 High-performance cosine similarity ranking for Retrieval-Augmented Generation (RAG) pipelines.
This project helps quickly find the most relevant documents or passages from a large collection based on their meaning. You provide a question or reference text and a set of candidate documents, each represented as an 'embedding' (a numerical vector). It efficiently ranks these candidates by how similar their embeddings are to your query, outputting the top-K most relevant documents. This is ideal for anyone building AI applications that need to retrieve information quickly and accurately, such as chatbot developers or data scientists working with semantic search.
Available on PyPI.
Use this if you need to rapidly identify the most semantically similar documents or text snippets from a large dataset to a given query, especially in applications like advanced search or question-answering systems.
Not ideal if your application requires extremely high-dimensional vectors (beyond ~1500 dimensions) or if you are not working with embedding-based semantic similarity.
Stars
9
Forks
—
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/analyticsinmotion/symrank"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
xhluca/bm25s
Fast lexical search implementing BM25 in Python
ALucek/QuicKB
Optimize Document Retrieval with Fine-Tuned KnowledgeBases
Rohith-2/bm25-fusion
An ultra-fast BM25 retriever with support for multiple variants and meta-data filtering.
MukundaKatta/HybridFind
Hybrid semantic + keyword search — BM25 and vector similarity with Reciprocal Rank Fusion
JhaAyush01/Embedding-Quantization-for-Significantly-Faster-Cheaper-Retrieval
Unofficial Implementation of Binary and Scalar Embedding Quantization for Significantly Faster &...