rragundez / chunkdot
Multi-threaded matrix multiplication and cosine similarity calculations for dense and sparse matrices. Appropriate for calculating the K most similar items for a large number of items by chunking the item matrix representation (embeddings) and using Numba to accelerate the calculations.
☆78Updated 3 weeks ago
Alternatives and similar repositories for chunkdot:
Users that are interested in chunkdot are comparing it to the libraries listed below
- Generalist and Lightweight Model for Text Classification☆58Updated 2 weeks ago
- LLM prompt language based on Jinja. Banks provides tools and functions to build prompts text and chat messages from generic blueprints. I…☆72Updated 2 weeks ago
- Check for data drift between two OpenAI multi-turn chat jsonl files.☆37Updated 9 months ago
- ☆76Updated 7 months ago
- ☆119Updated last month
- Lite weight wrapper for the independent implementation of SPLADE++ models for search & retrieval pipelines. Models and Library created by…☆29Updated 4 months ago
- Python API for https://vespa.ai, the open big data serving engine☆110Updated this week
- A Python wrapper around HuggingFace's TGI (text-generation-inference) and TEI (text-embedding-inference) servers.☆34Updated last month
- FastFit ⚡ When LLMs are Unfit Use FastFit ⚡ Fast and Effective Text Classification with Many Classes☆181Updated 3 months ago
- Command Line Interface for Hugging Face Inference Endpoints☆67Updated 9 months ago
- 📝 Reference-Free automatic summarization evaluation with potential hallucination detection☆99Updated last year
- GLiNER model in a FastAPI microservice.☆34Updated last month
- Simply, faster, sentence-transformers☆139Updated 4 months ago
- Machine Learning Serving focused on GenAI with simplicity as the top priority.☆58Updated last week
- Low latency, High Accuracy, Custom Query routers for Humans and Agents. Built by Prithivi Da☆90Updated 3 weeks ago
- Baguetter is a flexible, efficient, and hackable search engine library implemented in Python. It's designed for quickly benchmarking, imp…☆170Updated 4 months ago
- This is the repo for the container that holds the models for the text2vec-transformers module☆43Updated last week
- NLP with Rust for Python 🦀🐍☆60Updated 7 months ago
- Benchmark study on LanceDB, an embedded vector DB, for full-text search and vector search☆22Updated last year
- Notebooks for training universal 0-shot classifiers on many different tasks☆119Updated 3 weeks ago
- 🕹️ Performance Comparison of MLOps Engines, Frameworks, and Languages on Mainstream AI Models.☆138Updated 5 months ago
- Code for evaluating with Flow-Judge-v0.1 - an open-source, lightweight (3.8B) language model optimized for LLM system evaluations. Crafte…☆56Updated 2 months ago
- ☆206Updated 6 months ago
- ☆167Updated this week
- Fast Semantic Text Deduplication☆280Updated this week
- Efficient few-shot learning with cross-encoders.☆42Updated 11 months ago
- Self-host LLMs with vLLM and BentoML☆79Updated this week
- Experimental Code for StructuredRAG: JSON Response Formatting with Large Language Models☆97Updated last month
- TitanML Takeoff Server is an optimization, compression and deployment platform that makes state of the art machine learning models access…☆114Updated 11 months ago
- Late Interaction Models Training & Retrieval☆223Updated this week