rragundez / chunkdotLinks
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.
☆82Updated 5 months ago
Alternatives and similar repositories for chunkdot
Users that are interested in chunkdot are comparing it to the libraries listed below
Sorting:
- A Python wrapper around HuggingFace's TGI (text-generation-inference) and TEI (text-embedding-inference) servers.☆33Updated last month
- Simply, faster, sentence-transformers☆143Updated 9 months ago
- Lite weight wrapper for the independent implementation of SPLADE++ models for search & retrieval pipelines. Models and Library created by…☆31Updated 9 months ago
- The Batched API provides a flexible and efficient way to process multiple requests in a batch, with a primary focus on dynamic batching o…☆137Updated last month
- experiments with inference on llama☆104Updated last year
- Generalist and Lightweight Model for Text Classification☆133Updated last week
- Command Line Interface for Hugging Face Inference Endpoints☆66Updated last year
- Efficient few-shot learning with cross-encoders.☆52Updated last year
- Machine Learning Serving focused on GenAI with simplicity as the top priority.☆59Updated 2 months ago
- Check for data drift between two OpenAI multi-turn chat jsonl files.☆37Updated last year
- 📝 Reference-Free automatic summarization evaluation with potential hallucination detection☆100Updated last year
- Pre-train Static Word Embeddings☆79Updated 3 weeks ago
- FastFit ⚡ When LLMs are Unfit Use FastFit ⚡ Fast and Effective Text Classification with Many Classes☆207Updated last month
- Python API for https://vespa.ai, the open big data serving engine☆127Updated this week
- ☆77Updated last year
- 🕹️ Performance Comparison of MLOps Engines, Frameworks, and Languages on Mainstream AI Models.☆137Updated 10 months ago
- ☆60Updated this week
- High level library for batched embeddings generation, blazingly-fast web-based RAG and quantized indexes processing ⚡☆66Updated 7 months ago
- ☆72Updated 7 months ago
- Dataset Viber is your chill repo for data collection, annotation and vibe checks.☆47Updated 9 months ago
- 🤝 Trade any tensors over the network☆30Updated last year
- Plug-and-play document processing pipelines with zero-shot models.☆67Updated last month
- NLP with Rust for Python 🦀🐍☆62Updated last month
- Evaluation of bm42 sparse indexing algorithm☆68Updated 11 months ago
- Trully flash implementation of DeBERTa disentangled attention mechanism.☆58Updated last month
- Baguetter is a flexible, efficient, and hackable search engine library implemented in Python. It's designed for quickly benchmarking, imp…☆180Updated 9 months ago
- 🔢 Work with static vector models☆28Updated 2 months ago
- A stable, fast and easy-to-use inference library with a focus on a sync-to-async API☆45Updated 8 months ago
- ☆78Updated last year
- GLiNER model in a FastAPI microservice.☆44Updated 6 months ago