Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, Llava, GLM4v, Phi4, ...) (AAAI 2025).

AdalFlow: The library to build & auto-optimize LLM applications.

Rust library for generating vector embeddings, reranking. Re-write of qdrant/fastembed.

Train embedding and reranker models for retrieval tasks on Apple Silicon with MLX

An easy-to-use python toolkit for flexibly adapting various neural ranking models to target domain.

A library integrating embedding and reranker models from OpenAI, SentenceTransformers etc for semantic search in vector database.

1st Place Solution for Eedi - Mining Misconceptions in Mathematics Kaggle Competition

Testing speed and accuracy of RAG with, and without Cross Encoder Reranker.

An OpenAI Compatible API which integrates LLM, Embedding and Reranker. 一个集成 LLM、Embedding 和 Reranker 的 OpenAI 兼容 API

Free Web Search API, Free Rerank API, The World Engine For AGI.

NeuralCache is a drop-in reranker for Retrieval-Augmented Generation (RAG) that learns which context the model actually uses.

How Good are LLM-based Rerankers? Accepted at EMNLP Findings 2025

SearchAugmentedLLM empowers LLMs with information from the web

A Python cli-command tool for creating reports for any Google query.

A comprehensive RAG FastAPI service that handles document uploads and retrievals, built with Python. Uses PyMuPDF for document processing, turbopuffer for vector storage, OpenAI for models, and cohere for reranking.

This is RAG Modules Repo. This includes various modules in the RAG ecosystem.

FastAPI Local RAG Q&A Demo

A small reranker service using mixedbread.ai reranker model

CRoM (Context Rot Mitigation)-EfficientLLM is a Python toolkit designed to optimize the context provided to Large Language Models (LLMs). It provides a suite of tools to intelligently select, re-rank, and manage text chunks to fit within a model's context budget while maximizing relevance and minimizing performance drift.

The method of re-ranking involves a two-stage retrieval system, with re-rankers playing a crucial role in evaluating the relevance of each document to the query. RAG systems can be optimized to mitigate hallucinations and ensure dependable search outcomes by selecting the optimal reranking model.