crazyyanchao / llmcompiler
LLMCompiler is an Agent Architecture designed to speed up the execution of agent tasks by executing them quickly in the DAG. It also saves the cost of redundant token use by reducing the number of calls to the LLM.
☆18Updated last week
Related projects ⓘ
Alternatives and complementary repositories for llmcompiler
- Repo for for paper "AgentRE: An Agent-Based Framework for Navigating Complex Information Landscapes in Relation Extraction".☆50Updated 3 months ago
- Luann allows you to create a LLM agent,which has complete memory module (long-term memory, short-term memory) and knowledge module（Variou…☆16Updated this week
- HybridRAG is a hybrid model of Vector and Graph☆15Updated 3 months ago
- Deployment a light and full OpenAI API for production with vLLM to support /v1/embeddings with all embeddings models.☆37Updated 4 months ago
- ☆25Updated 7 months ago
- An open-source chat text to control actions agentic workflow framework/showcase powered by Agently AI application development framework.☆24Updated 2 months ago
- [EMNLP 2024] LongRAG: A Dual-perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering☆79Updated 2 weeks ago
- ☆42Updated 2 months ago
- This project is a collection of fine-tuning scripts to help researchers fine-tune Qwen 2 VL on HuggingFace datasets.☆47Updated 2 months ago
- This repository presents the original implementation of LumberChunker: Long-Form Narrative Document Segmentation by André V. Duarte, João…☆43Updated last month
- ☆49Updated 2 months ago
- Tutorials from AutoGen Basics to Use Cases☆27Updated last year
- ☆20Updated 5 months ago
- Elevating RAG with Multi-Agent Systems☆42Updated last week
- ☆41Updated last month
- AgileGen: Empowering Agile-Based Generative Software Development through Human-AI Teamwork (accepted by ACM TOSEM)☆15Updated 2 weeks ago
- Measuring RAG solutions throughput and latency☆13Updated 3 months ago
- LLM RAG 应用，支持 API 调用，语音交互。☆10Updated 4 months ago
- 🔎 A deep-dive into HyDE for Advanced LLM RAG + 💡 Introducing AutoHyDE, a semi-supervised framework to improve the effectiveness, covera…☆29Updated 7 months ago
- A Next.js version of Claude Aritfacts , inspired by llamacoder☆16Updated last month
- ☆59Updated last month
- 通过该项目将Dify通过Pipeline接入OpenwebUI，可以兼并OpenwebUI的前端优势和相应生态以及Dify强大的模型可拓展性和Workflow的效益。☆9Updated 2 months ago
- StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization☆72Updated last week
- A simple AI Agent Framework using table software like Excel/Google Sheets as GUI☆14Updated 5 months ago
- Official Code for Oᴘᴇɴ-RAG: Enhanced Retrieval Augmented Reasoning with Open-Source Large Language Models (EMNLP Findings 2024)☆78Updated this week
- The Library for LLM-based multi-agent applications☆65Updated this week
- Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model☆16Updated last month
- Data preparation code for CrystalCoder 7B LLM☆42Updated 6 months ago
- I have explained how to create superior RAG pipeline for complex pdfs using LlamaParse. We can extract text and tables from pdf and QA on…☆39Updated 8 months ago
- 与 https://github.com/tonori/mem0ai-api 配合使用的非官方的 mem0ai provider.☆38Updated 3 months ago