retriever 开源项目推荐（82 个）

SylphAI-Inc /AdalFlow

AdalFlow：用于构建并自动优化 LLM 应用的库。

wangle201210 /go-rag

基于 eino+gf+vue 实现知识库的 RAG

shibing624 /TreeSearch

TreeSearch: Search your codebase like a human — not like a vector database. No embeddings. No chunking. Just millisecond search over structured documents and large codebases. 无需 embedding，无需切分文档，在结构化文档和大型代码库中实现毫秒级检索。

yuanbit /FinBERT-QA

Financial Domain Question Answering with pre-trained BERT Language Model

bitscoper /bitscoper_cyberkit

A Flutter Application: Bluetooth Low Energy Scanner, IPv4 Subnet Scanner, mDNS Scanner, UPnP Scanner, Route Tracer, TCP Port Scanner, Pinger, DNS Record Retriever, File Hash Calculator, String Hash Calculator, Base Encoder, Series URI Crawler, OGP Data Extractor, WHOIS Retriever, CVSS Calculator, Morse Code Translator, and Wi-Fi Details Viewer.

rbiswasfc /eedi-mining-misconceptions

Eedi - Mining Misconceptions in Mathematics Kaggle 竞赛第一名方案

ozynautetu-create /FlowForge-Optima

AdalFlow Alternative 2026: Auto-Optimize LLM Apps Without Code

genoskietv /AdalFlow-Optimizer

Build & Auto-Optimize LLM Apps in 2026: The Ultimate AdalFlow Guide

ssisOneTeam /Korean-Embedding-Model-Performance-Benchmark-for-Retriever

Korean Sentence Embedding Model Performance Benchmark for RAG

travaux-com /VariantRetriever

VariantRetriever is a minimalist package for feature flagging

SnowNation101 /Nyx

Code for the paper [SIGIR'26]“Towards Mixed-Modal Retrieval for Universal Retrieval-Augmented Generation”

raphaelsty /gokapi

Okapi BM25 with Go

aliahmad552 /fake_news_detection_and_summarization_genai_project

The News Summarization & Fake News Detection App is an AI-powered solution I developed to make information consumption smarter and more trustworthy. Built with FastAPI, LangChain, HuggingFace, and FAISS, this application retrieves the latest news articles based on any user query

RonCodes88 /okf-agents

LangGraph and LangChain retriever, tools, and navigator subgraph for OKF (Open Knowledge Format) bundles.

Ave-Sergeev /Disorder

Save many text fragments as WAV files with blazing-fast semantic search. No database required. (Rust, Tonic) (Q3:2025)

Aeiric /thumb

a lightweight video cover capture library

DARK-art108 /mistral-7b-ensemble

Adding InMemoryCaching, Ensemble Retrievers,langchain, faiss for a open domain chatbot

ItsNotRohit02 /InfoSage-Retriever-Reader-Generative-Model

InfoSage is a Question and Answering (Q&A) model using the Retriever-Reader approach. The application is built using the Streamlit framework and utilizes several modules and functionalities along with a database to store user information and feedback.

bonifazi /labradoR

An R Package To Read, Process, and Visualize Retriever's Output.

choucisan /Dog100K

The high-quality large-scale dog image-text dataset (the largest on the web) Dog100K, containing over 100,000 pairs of images and text.