#python #agent #agents #ai_search #chatbot #chatgpt #data_pipelines #deep_learning #document_parser #document_understanding #genai #graph #graphrag #llm #nlp #pdf_to_text #preprocessing #rag #retrieval_augmented_generation #table_structure_recognition #text2sql

RAGFlow is an open-source tool that helps businesses answer questions accurately using large language models and deep document understanding. It extracts information from various complex data formats, such as Word documents, Excel files, and web pages, and provides grounded citations to support its answers. You can try a demo online or set it up on your own server using Docker. The setup is relatively straightforward, requiring a few steps like cloning the repository, building the Docker image, and configuring the system settings. RAGFlow offers key features like template-based chunking, reduced hallucinations, and compatibility with multiple data sources, making it a powerful tool for truthful question-answering capabilities. This benefits users by providing reliable and explainable answers, streamlining their workflow, and supporting integration with their business systems.

https://github.com/infiniflow/ragflow

#python #emnlp2024 #knowledge_curation #large_language_models #naacl #nlp #report_generation #retrieval_augmented_generation

STORM is a system that helps you write articles like those on Wikipedia by using internet searches. Here’s how it benefits you STORM conducts internet research, collects references, and generates an outline for your topic.
- **Collaborative Feature** You can install STORM using `pip install knowledge-storm` and customize it according to your needs.
- **User-Friendly**: Over 70,000 people have used STORM, and it helps experienced Wikipedia editors in their pre-writing stage.

This system makes researching and writing articles much easier and more efficient.

https://github.com/stanford-oval/storm

#other #chatbot #hugging_face #llm #llm_local #llm_prompting #llm_security #llmops #machine_learning #open_ai #pathway #rag #real_time #retrieval_augmented_generation #vector_database #vector_index

Pathway's AI Pipelines help you quickly create and deploy AI applications with high accuracy. These pipelines use the latest knowledge from your data sources and offer ready-to-deploy templates for large language models. You can test these apps on your own machine and deploy them on cloud services like GCP, AWS, or Azure, or on-premises. The apps connect to various data sources such as file systems, Google Drive, and databases, and they include built-in data indexing for efficient searches. This makes it easy to extract and organize data from documents in real-time, reducing the need for separate infrastructure setups. This simplifies the process of building and maintaining AI applications, saving you time and effort.

https://github.com/pathwaycom/llm-app

#python #genai #gpt #gpt_4 #graphrag #knowledge_graph #large_language_models #llm #rag #retrieval_augmented_generation

LightRAG is a system that helps computers understand and answer questions better by using a special way of organizing information called a "graph." This graph shows how different pieces of information are connected, making it easier for the system to find related answers. It works fast and can handle complex questions by combining two types of searches: one that looks at specific details and another that looks at broader topics. This makes it very useful for answering questions that need both specific and general information. Users benefit from getting accurate and relevant answers quickly, which is helpful in many applications like customer service and document retrieval.

https://github.com/HKUDS/LightRAG

#python #agent_computer_interface #ai_agents #computer_automation #computer_use #grounding #gui_agents #in_context_reinforcement_learning #memory #mllm #planning #retrieval_augmented_generation

Agent S2 is a smart AI assistant that handles computer tasks by breaking them into smaller steps and using specialized tools for each part, making it highly adaptable and efficient across different systems like Windows and Android. It outperforms other AI tools in completing complex tasks, learns from experience, and adjusts plans as needed, helping users automate digital work more reliably and effectively.

https://github.com/simular-ai/Agent-S

#python #agents #generative_ai_tools #llamacpp #llm #onnx #openvino #parsing #retrieval_augmented_generation #small_specialized_models

llmware is a powerful, easy-to-use platform that helps you build AI applications using small, specialized language models designed for business tasks like question-answering, summarization, and data extraction. It supports private, secure deployment on your own machines without needing expensive GPUs, making it cost-effective and safe for enterprise use. You can organize and search your documents, run smart queries, and combine knowledge with AI to get accurate answers quickly. It also offers many ready-to-use models and examples, plus tools for building chatbots and agents that automate complex workflows. This helps you save time, improve accuracy, and securely leverage AI for your business needs[1][3][5].

https://github.com/llmware-ai/llmware

#python #multi_modal_rag #retrieval_augmented_generation

RAG-Anything is a powerful AI system that helps you search and understand documents containing mixed content like text, images, tables, and math formulas all in one place. It uses smart parsing and analysis to break down complex documents and builds a knowledge graph to connect different types of information. This means you can ask detailed questions about any part of a document—whether text or images—and get clear, accurate answers quickly. It supports many file types like PDFs and Office files, making it ideal for research, technical work, or business reports where you need a unified, easy way to explore rich, multimodal content. This saves you time and effort by avoiding multiple tools and gives you deeper insights from your documents.

https://github.com/HKUDS/RAG-Anything

#python #ai #context #embedded #faiss #knowledge_base #knowledge_graph #llm #machine_learning #memory #nlp #offline_first #opencv #python #rag #retrieval_augmented_generation #semantic_search #vector_database #video_processing

Memvid lets you store millions of text pieces inside a single MP4 video file using QR codes, making your data 50-100 times smaller than usual databases. You can search this video instantly in under 100 milliseconds without needing servers or internet after setup. It works offline, is easy to use with simple Python code, and supports PDFs and chat with your data. The upcoming version 2 will add features like continuous memory updates, shareable capsules, fast local caching, and better video compression, making your AI memory smarter, faster, and more flexible. This means you get a powerful, portable, and efficient way to manage and search huge knowledge bases quickly and easily.

https://github.com/Olow304/memvid

#python #ai #faiss #gpt_oss #langchain #llama_index #llm #localstorage #offline_first #ollama #privacy #python #rag #retrieval_augmented_generation #vector_database #vector_search #vectors

LEANN is a tiny, powerful vector database that lets you turn your laptop into a personal AI assistant capable of searching millions of documents using 97% less storage than traditional systems without losing accuracy. It works by storing a compact graph and computing embeddings only when needed, saving huge space and keeping your data private on your device. You can search your files, emails, browser history, chat logs, live data from platforms like Slack and Twitter, and even codebases—all locally without cloud costs. This means fast, private, and efficient AI-powered search and retrieval on your own laptop.

https://github.com/yichuan-w/LEANN