RAG for Local LLM, chat with PDF/doc/txt files, ChatPDF. 纯原生实现RAG功能,基于本地LLM、embedding模型、reranker模型实现,支持GraphRAG,无须安装任何第三方agent库。
Repository Index
142,273 visible repositories in the index
1,201–1,224 of 1,943 · Most stars
GLM-ASR-Nano: A robust, open-source speech recognition model with 1.5B parameters
- asr
- edge
- llm
- voice
The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".
- agents
- continual-learning
- llm-agents
- self-evolving
Master Reinforcement and Deep Reinforcement Learning using OpenAI Gym and TensorFlow
- reinforcement-learning
- deep-reinforcement-learning
- sarsa
- q-learning
Code and implementations for the ACL 2025 paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhiheng Xi et al.
- agent
- llm
- llm-based-agent
- large-language-models
Confucius4-TTS: a Multilingual and Cross-Lingual Zero-Shot TTS Engine
- audio
- cross-lingual
- deep-learning
- fine-tuning
[CVPR'23] OpenScene: 3D Scene Understanding with Open Vocabularies
- 3d-scene-understanding
- clip
- semantic-segmentation
- llm
[Pytorch] Generative retrieval model using semantic IDs from "Recommender Systems with Generative Retrieval"
- generative-ai
- recommendation-system
- recommender-system
- retrieval-systems
Model Context Protocol (MCP) to enable AI LLMs to trade using MetaTrader platform
Council is an open-source platform for the rapid development and robust deployment of customized generative AI applications
An LLM-powered advanced RAG pipeline built from scratch
Tool for data extraction and interacting with Lean programmatically.
- lean
- machine-learning
- theorem-proving
- lean4
LLMs can generate feedback on their work, use it to improve the output, and repeat this process iteratively.
- few-shot-learning
- language-generation
- large-language-models
- llms
Use late-interaction multi-modal models such as ColPali in just a few lines of code.
Unified Reinforcement Learning Framework
- distributed-reinforcement-learning
- embodied
- google-research-football
- gym
MCP server for JADX-AI Plugin
- ai
- application-security
- mcp-server
- python
Trace-native CI/CD for AI agents: grade production traces, cluster failures, freeze them into replayable regression tests, and block PRs that regress. Self-hostable.
This repository contains the implementation of AutoSchemaKG, a novel framework for automatic knowledge graph construction that combines schema generation via conceptualization.
- graph-construction
- knowledge-graph
- rag
[EMNLP'25] s3 - ⚡ Efficient & Effective Search Agent Training via RL for RAG (RLVR for Search with Minimal Data)
- efficiency
- large-language-models
- rag
- search-agent
A simple web application for a OpenAI-enabled document search. This repo uses Azure OpenAI Service for creating embeddings vectors from documents. For answering the question of a user, it retrieves the most relevant document and then uses GPT-3, GPT-3.5 or GPT-4 to extract the matching answer for the question.
- azureopenai
End-to-end AI short-video production pipeline. FastAPI orchestration + Spring Boot gateway with multi-model failover, circuit breaker, metering, and full-stack observability. AI quality gating: prompt anchoring, CLIP consistency, AV sync auto-rescue.
- ai
- short-video
- video-generation
- ai-pipeline
AI-powered data analysis workbench built for transparency, reproducibility and user control. Inspect the code and evidence behind results, verify calculations through replay, and choose from a wide range of models, including local open-weight models.
A comprehensive library for implementing LLMs, including a unified training pipeline and comprehensive model evaluation.
Hypernetworks that update LLMs to remember factual information