mixedbread-ai / baguetter
Baguetter is a flexible, efficient, and hackable search engine library implemented in Python. It's designed for quickly benchmarking, implementing, and testing new search methods. Baguetter supports sparse (traditional), dense (semantic), and hybrid retrieval methods.
☆171Updated 6 months ago
Alternatives and similar repositories for baguetter:
Users that are interested in baguetter are comparing it to the libraries listed below
- The Batched API provides a flexible and efficient way to process multiple requests in a batch, with a primary focus on dynamic batching o…☆124Updated 2 months ago
- Late Interaction Models Training & Retrieval☆254Updated this week
- Python API for https://vespa.ai, the open big data serving engine☆116Updated this week
- Generalist and Lightweight Model for Text Classification☆90Updated this week
- Simple replication of [ColBERT-v1](https://arxiv.org/abs/2004.12832).☆80Updated 11 months ago
- FastFit ⚡ When LLMs are Unfit Use FastFit ⚡ Fast and Effective Text Classification with Many Classes☆189Updated 5 months ago
- Efficient vector database for hundred millions of embeddings.☆206Updated 9 months ago
- ☆207Updated 8 months ago
- 📝 Reference-Free automatic summarization evaluation with potential hallucination detection☆100Updated last year
- minimal pytorch implementation of bm25 (with sparse tensors)☆97Updated last year
- code for training & evaluating Contextual Document Embedding models☆176Updated 2 months ago
- ☆113Updated 5 months ago
- Vision Document Retrieval (ViDoRe): Benchmark. Evaluation code for the ColPali paper.☆181Updated last week
- Neural Search☆352Updated this week
- Vector Database with support for late interaction and token level embeddings.☆53Updated 5 months ago
- A large-scale information-rich web dataset, featuring millions of real clicked query-document labels☆316Updated 2 months ago
- ☆149Updated 3 months ago
- 🕹️ Performance Comparison of MLOps Engines, Frameworks, and Languages on Mainstream AI Models.☆136Updated 7 months ago
- A fast, lightweight and easy-to-use Python library for splitting text into semantically meaningful chunks.☆259Updated this week
- ☆62Updated 7 months ago
- High level library for batched embeddings generation, blazingly-fast web-based RAG and quantized indexes processing ⚡☆67Updated 4 months ago
- Pre-train Static Word Embeddings☆48Updated last week
- RAGElo is a set of tools that helps you selecting the best RAG-based LLM agents by using an Elo ranker☆107Updated last month
- Manage scalable open LLM inference endpoints in Slurm clusters☆253Updated 8 months ago
- Lightweight Nearest Neighbors with Flexible Backends☆258Updated last week
- an implementation of Self-Extend, to expand the context window via grouped attention☆118Updated last year
- awesome synthetic (text) datasets☆264Updated 4 months ago
- A stable, fast and easy-to-use inference library with a focus on a sync-to-async API☆45Updated 5 months ago
- ☆63Updated 2 months ago