Fosowl/agenticSeek
AgenticSeek is a fully local, autonomous AI assistant powered by Deepseek R1 agents that can code, browse the web, and manage files without relying on cloud services, ensuring user data privacy and eliminating ongoing costs.
Awesome AI Agents › Programming Languages
NisaarAgharia/Advanced_RAG
Advanced_RAG is a comprehensive project that explores advanced Retrieval-Augmented Generation (RAG) techniques through practical Python notebooks. It leverages the Langchain framework alongside powerful language models such as OpenAI GPTs and META LLAMA3 to enhance large language models (LLMs) with rich, contextual knowledge. The project is designed to provide a deep understanding of RAG by guiding users through various stages and components of the RAG process, from basic query handling to sophisticated agentic and adaptive mechanisms. The repository includes detailed architecture flows that visually explain the journey of a query through a RAG system, highlighting key components like query construction, multi-query retrieval, self-reflection, and agentic flows. These visual aids help users grasp the complex interactions within advanced RAG systems. The notebooks cover a wide range of topics, including basic RAG app building, query transformations, routing to data sources, indexing methods in vector databases, and retrieval mechanisms such as reranking and fusion. More advanced notebooks delve into self-reflective RAG, which incorporates self-grading on retrieved documents and generated responses, and agentic RAG, which introduces agentic flows to improve retrieval and generation processes. Adaptive and corrective agentic RAG notebooks further enhance these concepts by adding adaptability and correction capabilities to the agentic flows. The project also features a notebook demonstrating the use of LLAMA 3 8B as a local agentic RAG model, showcasing the ability to run sophisticated RAG agents locally. Overall, Advanced_RAG serves as an educational and practical resource for developers and researchers interested in pushing the boundaries of natural language generation by integrating retrieval-augmented techniques with state-of-the-art language models. It offers a hands-on approach to building and understanding complex RAG systems, making it valuable for those aiming to improve the accuracy and informativeness of LLM outputs.
https://github.com/NisaarAgharia/Advanced_RAG
Also in Programming Languages
MODSetter/SurfSense
SurfSense is a highly customizable AI research agent that integrates with personal knowledge bases and external sources to provide advanced, privacy-conscious research and knowledge management capabilities.
HKUDS/AI-Researcher
AI-Researcher is a fully automated scientific discovery platform powered by large language models that autonomously conducts research from idea generation to manuscript creation.
InternLM/xtuner
XTuner is a comprehensive and efficient toolkit for fine-tuning large language and vision-language models, supporting a wide range of models and training algorithms with scalability and flexibility.
developersdigest/llm-answer-engine
A Perplexity-inspired answer engine built with Next.js and multiple AI and search technologies to provide rich, context-aware responses including sources, images, videos, and follow-up questions.
run-llama/LlamaIndexTS
LlamaIndexTS is a lightweight, extensible data framework designed to integrate large language models into server-side JavaScript applications, supporting multiple runtimes and a wide range of LLM providers.
EgoAlpha/prompt-in-context-learning
An open-source comprehensive resource and engineering guide for mastering in-context learning and prompt engineering with large language models like ChatGPT, GPT-3, and FlanT5.
AnotiaWang/deep-research-web-ui
Deep Research Web UI is a secure, AI-powered web interface that enables iterative, deep research by combining search engines, web scraping, and large language models with real-time feedback and exportable research reports.