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.
☆73Updated 2 months ago
Related projects: ⓘ
- Python API for https://vespa.ai, the open big data serving engine☆89Updated this week
- ☆58Updated 3 weeks ago
- Check for data drift between two OpenAI multi-turn chat jsonl files.☆33Updated 5 months ago
- ☆71Updated 3 months ago
- Lite weight wrapper for the independent implementation of SPLADE++ models for search & retrieval pipelines. Models and Library created by…☆27Updated 3 weeks ago
- Late Interaction Models Training & Retrieval☆130Updated this week
- Baguetter is a flexible, efficient, and hackable search engine library implemented in Python. It's designed for quickly benchmarking, imp…☆136Updated 2 weeks ago
- Machine Learning Serving focused on GenAI with simplicity as the top priority.☆55Updated last month
- Benchmark various LLM Structured Output frameworks: Instructor, Mirascope, Langchain, LlamaIndex, Fructose, Marvin, Outlines, etc on task…☆117Updated 3 weeks ago
- FastFit ⚡ When LLMs are Unfit Use FastFit ⚡ Fast and Effective Text Classification with Many Classes☆180Updated 3 weeks ago
- 📝 Reference-Free automatic summarization evaluation with potential hallucination detection☆99Updated 8 months ago
- Dataset Viber is your chill repo for data collection, annotation and vibe checks.☆39Updated 2 weeks ago
- High level library for batched embeddings generation, blazingly-fast web-based RAG and quantized indexes processing ⚡☆58Updated 2 weeks ago
- experiments with inference on llama☆106Updated 3 months ago
- ☆72Updated 3 months ago
- Chunk your text using gpt4o-mini more accurately☆37Updated last month
- LLM prompt language based on Jinja☆52Updated last week
- ☆203Updated 2 months ago
- Iterate fast on your RAG pipelines☆14Updated 2 weeks ago
- TitanML Takeoff Server is an optimization, compression and deployment platform that makes state of the art machine learning models access…☆113Updated 7 months ago
- 🕹️ Performance Comparison of MLOps Engines, Frameworks, and Languages on Mainstream AI Models.☆129Updated last month
- Simply, faster, sentence-transformers☆127Updated 3 weeks ago
- Generalist and Lightweight Model for Text Classification☆29Updated last week
- Notebooks for training universal 0-shot classifiers on many different tasks☆100Updated 5 months ago
- [EMNLP 2023 Demo] fabricator - annotating and generating datasets with large language models.☆99Updated 4 months ago
- Self-host LLMs with vLLM and BentoML☆62Updated this week
- Evaluation of bm42 sparse indexing algorithm☆60Updated 2 months ago
- This is the repo for the container that holds the models for the text2vec-transformers module☆38Updated 3 weeks ago
- Leverage your LangChain trace data for fine tuning☆36Updated last month
- Voyage AI Official Python Library☆37Updated 3 months ago