lightonai / ducksearchLinks
Efficient BM25 with DuckDB 🦆
☆55Updated 8 months ago
Alternatives and similar repositories for ducksearch
Users that are interested in ducksearch are comparing it to the libraries listed below
Sorting:
- NLP with Rust for Python 🦀🐍☆64Updated 4 months ago
- ☆76Updated 8 months ago
- Plug-and-play document processing pipelines with zero-shot models.☆97Updated 3 weeks ago
- ☆69Updated 2 months ago
- Pre-train Static Word Embeddings☆85Updated last week
- Baguetter is a flexible, efficient, and hackable search engine library implemented in Python. It's designed for quickly benchmarking, imp…☆189Updated last year
- PyLate efficient inference engine☆64Updated last month
- A library to use `modal` as a backend for `joblib`.☆31Updated 7 months ago
- Tree-based indexes for neural-search☆32Updated last year
- UniSim is a package for efficient similarity computation, fuzzy matching, and clustering of data.☆141Updated 5 months ago
- spaCy entry points for Curated Transformers☆32Updated 3 months ago
- Optimizing bit-level Jaccard Index and Population Counts for large-scale quantized Vector Search via Harley-Seal CSA and Lookup Tables☆21Updated 3 months ago
- Multi-threaded matrix multiplication and cosine similarity calculations for dense and sparse matrices. Appropriate for calculating the K …☆83Updated 8 months ago
- Embedding Vector Oriented Clustering☆153Updated 2 weeks ago
- Benchmark study on LanceDB, an embedded vector DB, for full-text search and vector search☆27Updated last year
- Datamodels for hugging face tokenizers☆47Updated this week
- Neural Solr = Solr 9 + Mighty Inference + Node☆18Updated 3 years ago
- Graph Engine for Exploration and Search☆42Updated last year
- ☆30Updated 3 years ago
- minimal pytorch implementation of bm25 (with sparse tensors)☆104Updated last year
- hnsw implemented by python☆20Updated 5 years ago
- My personal frontpage app☆97Updated this week
- Small python package to measure OCR quality and other related metrics.☆25Updated last year
- Playing with Python Bluesky SDK☆15Updated 9 months ago
- [EMNLP 2023 Demo] fabricator - annotating and generating datasets with large language models.☆110Updated last year
- The Batched API provides a flexible and efficient way to process multiple requests in a batch, with a primary focus on dynamic batching o…☆147Updated 2 months ago
- Generalist and Lightweight Model for Text Classification☆157Updated 3 months ago
- High-Performance Engine for Multi-Vector Search☆155Updated this week
- Use sync mode Playwright interactively, inside a Jupyter notebook☆15Updated 5 months ago
- It's a cooler way to store simple linear models.☆27Updated last year