NVIDIA / nv-ingest
NVIDIA Ingest is an early access set of microservices for parsing hundreds of thousands of complex, messy unstructured PDFs and other enterprise documents into metadata and text to embed into retrieval systems.
β2,022Updated this week
Alternatives and similar repositories for nv-ingest:
Users that are interested in nv-ingest are comparing it to the libraries listed below
- π¦ CHONK your texts with Chonkie β¨ - The no-nonsense RAG chunking libraryβ2,249Updated this week
- Task-Aware Agent-driven Prompt Optimization Frameworkβ2,188Updated last week
- Parse files for optimal RAGβ3,526Updated last week
- A system for agentic LLM-powered data processing and ETLβ1,514Updated this week
- A toolkit to create optimal Production-readyRetrieval Augmented Generation(RAG) setup for your dataβ1,356Updated last week
- RAG that intelligently adapts to your use case, data, and queriesβ2,747Updated this week
- Agent Framework / shim to use Pydantic with LLMsβ5,346Updated this week
- Everything you need to know to build your own RAG applicationβ1,313Updated last week
- RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundryβ3,518Updated 2 weeks ago
- No-code LLM Platform to launch APIs and ETL Pipelines to structure unstructured documentsβ3,346Updated this week
- open-source framework for creating and managing simulations populated with AI-powered agents. It provides an intuitive platform for desigβ¦β837Updated last week
- From RAG chatbots to code assistants to complex agentic pipelines and beyond, build LLM systems that run better, faster, and cheaper withβ¦β4,430Updated this week
- π€ smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.β5,197Updated this week
- File Parser optimised for LLM Ingestion with no loss π§ Parse PDFs, Docx, PPTx in a format that is ideal for LLMs.β4,966Updated this week
- pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https://tidβ¦β2,159Updated this week
- Building AI agents, atomicallyβ1,976Updated this week
- Document (PDF, Word, PPTX ...) extraction and parse API using state of the art modern OCRs + Ollama supported models. Anonymize documentsβ¦β2,046Updated this week
- π A better UX for chat, writing content, and coding with LLMs.β3,443Updated 2 weeks ago
- The official Python SDK for Model Context Protocol servers and clientsβ1,423Updated this week
- Lightning-fast serving engine for any AI model of any size. Flexible. Easy. Enterprise-scale.β2,705Updated this week
- AI-Driven Research Assistant: An advanced multi-agent system for automating complex research processes. Leveraging LangChain, OpenAI GPT,β¦β1,104Updated last month
- π₯ Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser instance that lets you automate the web wiβ¦β2,898Updated last week
- The Open Source Memory Layer For Autonomous Agentsβ1,955Updated 2 months ago
- Flexible and powerful framework for managing multiple AI agents and handling complex conversationsβ3,835Updated this week
- Implementing the 4 agentic patterns from scratchβ973Updated 2 months ago
- Intelligent gateway for AI agents. Built with fast LLMs for the smart routing, rich observability, and the seamless integration of promptβ¦β1,277Updated this week
- KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning aβ¦β4,258Updated this week
- A lightweight task engine for building stateful AI agents that prioritizes simplicity and flexibility.β837Updated last week
- The code used to train and run inference with the ColPali architecture.β1,386Updated this week
- Chat with any codebase in under two minutes | Fully local or via third-party APIsβ1,155Updated 2 months ago