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.
☆75Updated 4 months ago
Related projects ⓘ
Alternatives and complementary repositories for chunkdot
- Generalist and Lightweight Model for Text Classification☆49Updated last week
- Check for data drift between two OpenAI multi-turn chat jsonl files.☆36Updated 7 months ago
- FastFit ⚡ When LLMs are Unfit Use FastFit ⚡ Fast and Effective Text Classification with Many Classes☆183Updated last month
- 📝 Reference-Free automatic summarization evaluation with potential hallucination detection☆98Updated 10 months ago
- Python API for https://vespa.ai, the open big data serving engine☆103Updated this week
- ☆108Updated this week
- Notebooks for training universal 0-shot classifiers on many different tasks☆106Updated 7 months ago
- Machine Learning Serving focused on GenAI with simplicity as the top priority.☆57Updated 4 months ago
- Lite weight wrapper for the independent implementation of SPLADE++ models for search & retrieval pipelines. Models and Library created by…☆27Updated 2 months ago
- ☆75Updated 5 months ago
- LLM prompt language based on Jinja. Banks provides tools and functions to build prompts text and chat messages from generic blueprints. I…☆64Updated last week
- Simply, faster, sentence-transformers☆140Updated 2 months ago
- Command Line Interface for Hugging Face Inference Endpoints☆66Updated 7 months ago
- Dataset Viber is your chill repo for data collection, annotation and vibe checks.☆43Updated 2 months ago
- Completion After Prompt Probability. Make your LLM make a choice☆69Updated 2 weeks ago
- ☆44Updated last week
- GLiNER model in a FastAPI microservice.☆29Updated 3 weeks ago
- 🤝 Trade any tensors over the network☆30Updated last year
- Late Interaction Models Training & Retrieval☆165Updated this week
- A Python wrapper around HuggingFace's TGI (text-generation-inference) and TEI (text-embedding-inference) servers.☆32Updated 2 months ago
- Self-host LLMs with vLLM and BentoML☆74Updated this week
- Build reliable, secure, and production-ready AI apps easily.☆46Updated 2 weeks ago
- 🕹️ Performance Comparison of MLOps Engines, Frameworks, and Languages on Mainstream AI Models.☆134Updated 3 months ago
- Baguetter is a flexible, efficient, and hackable search engine library implemented in Python. It's designed for quickly benchmarking, imp…☆162Updated 2 months ago
- NLP with Rust for Python 🦀🐍☆59Updated 5 months ago
- Low latency, High Accuracy, Custom Query routers for Co-pilots and Agents. Built by Prithivi Da☆31Updated this week
- ☆75Updated 5 months ago
- A framework for evaluating function calls made by LLMs☆35Updated 3 months ago
- Client Code Examples, Use Cases and Benchmarks for Enterprise h2oGPTe RAG-Based GenAI Platform☆81Updated this week
- A stable, fast and easy-to-use inference library with a focus on a sync-to-async API☆45Updated last month