[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-81006":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":14,"subscribersCount":14,"size":14,"stars1d":15,"stars7d":13,"stars30d":16,"stars90d":14,"forks30d":14,"starsTrendScore":16,"compositeScore":16,"rankGlobal":9,"rankLanguage":9,"license":9,"archived":17,"fork":17,"defaultBranch":18,"hasWiki":17,"hasPages":17,"topics":19,"createdAt":9,"pushedAt":9,"updatedAt":20,"readmeContent":21,"aiSummary":22,"trendingCount":14,"starSnapshotCount":14,"syncStatus":13,"lastSyncTime":23,"discoverSource":24},81006,"docs-reader-rag-agent","adityasharmadotai-hash\u002Fdocs-reader-rag-agent","adityasharmadotai-hash","This agent answers questions by reading multiple docs provided by the user",null,"Python",33,9,2,0,1,3,false,"main",[],"2026-06-12 02:04:09","# 📄 Document AI Agent\n\nAn AI-powered chatbot that reads your Word documents and answers questions from them — built with Python, OpenAI, and Streamlit.\n\n**👉 FIND THE STEP-BY-STEP TUTORIAL [HERE](https:\u002F\u002Fgithub.com\u002Fadityasharmadotai-hash\u002Fdocs-reader-rag-agent\u002Fblob\u002Fmain\u002FTUTORIAL.md)**\n\n---\n\n## Overview\n\nDocument AI Agent lets you upload any Word (`.docx`) files and instantly ask questions about their content. Instead of manually searching through documents, you simply type a question and the AI finds the answer for you.\n\nBuilt as a beginner-friendly open source project to demonstrate how Retrieval Augmented Generation (RAG) works at its core — no complex frameworks, just clean Python.\n\n---\n\n## Features\n\n- 💬 Chat interface — ask multiple questions in one session\n- 📂 Multi-document support — reads all `.docx` files in the `docs\u002F` folder\n- 📊 Reads both paragraphs and tables from Word documents\n- 🔍 Answers only from your documents — won't make things up\n- 🤖 Asks clarifying questions when multiple documents are loaded\n- 🧹 Clear chat button to reset the conversation\n\n\u003Cimg width=\"3024\" height=\"1964\" alt=\"image\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F4eceb25e-122c-4681-9191-213956f4e6c9\" \u002F>\n\n---\n\n## How It Works\n\n```\nUser asks a question\n        ↓\nloader.py reads all .docx files from the docs\u002F folder\n        ↓\nagent.py sends the documents + question to OpenAI GPT\n        ↓\nGPT searches through the documents and returns an answer\n        ↓\napp.py displays the answer in the chat interface\n```\n\n---\n\n## Tech Stack\n\n| Tool | Purpose |\n|------|---------|\n| Python | Core programming language |\n| OpenAI GPT-3.5 | AI model that reads and answers |\n| Streamlit | Web interface |\n| python-docx | Reads Word documents |\n\n---\n\n## File Structure\n\n```\n├── app.py            # Streamlit UI and chat interface\n├── agent.py          # Sends questions + docs to OpenAI\n├── loader.py         # Reads and parses .docx files\n├── requirements.txt  # Python dependencies\n└── docs\u002F             # Put your Word documents here\n    ├── document1.docx\n    └── document2.docx\n```\n\u003Cimg width=\"3024\" height=\"1964\" alt=\"image\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Facc5f184-3d34-4d08-bd71-d5172f17fe58\" \u002F>\n\n---\n\n## Getting Started\n\n### 1. Clone the repository\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fadityasharmadotai-hash\u002Fdocs-reader-rag-agent.git\ncd docs-reader-rag-agent\n```\n\n### 2. Install dependencies\n```bash\npip install -r requirements.txt\n```\n\n### 3. Add your documents\nPlace your `.docx` files inside the `docs\u002F` folder.\n\n### 4. Set your OpenAI API key\nCreate a `.env` file in the root folder:\n```\nOPENAI_API_KEY=your-api-key-here\n```\nGet your API key at [platform.openai.com](https:\u002F\u002Fplatform.openai.com)\n\n### 5. Run the app\n```bash\nstreamlit run app.py\n```\n\n---\n\n## Deploy on Streamlit Cloud (Free)\n\n1. Push this repo to GitHub (do **not** commit your `.env` file)\n2. Go to [share.streamlit.io](https:\u002F\u002Fshare.streamlit.io) and sign in with GitHub\n3. Click **New app** → select your repo → set main file to `app.py`\n4. Under **Advanced settings → Secrets**, add:\n```toml\nOPENAI_API_KEY = \"your-api-key-here\"\n```\n5. Click **Deploy** — you'll get a public URL in ~2 minutes\n\n---\n\n## Contributing\n\nPull requests are welcome! If you find a bug or want to suggest a feature, open an issue on GitHub.\n\n---\n\n## License\n\nMIT License — free to use, modify, and share.\n\n---\n\n## ⭐ If you find this useful...\n\nIf you learned something from this project, it would mean a lot if you could:\n\n- ⭐ **[Star this repository](https:\u002F\u002Fgithub.com\u002Fadityasharmadotai-hash)** — it helps others discover this project\n- 💼 **[Follow on LinkedIn](https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Faditya-hicounselor\u002F)** — for daily AI news, tools, and updates\n- 📺 **[Subscribe on YouTube](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCPjQtVNUrf7EKrm8ZoqrCAQ)** — AI agents, tutorials, and the latest in the world of AI\n\n> 🚀 **Looking for a job at a top AI company in the USA?**\n> Fill out your information here → **[Apply Now](https:\u002F\u002Fdocs.google.com\u002Fforms\u002Fd\u002Fe\u002F1FAIpQLSc3gJssBV3B25EZ3sYA7Qcen9NbtOB_wgQaturfB7lTXuAdLQ\u002Fviewform)**\n\n---\n","这个项目是一个基于AI的聊天机器人，能够阅读用户提供的Word文档并回答相关问题。其核心功能包括支持多文档上传、解析Word文档中的段落和表格内容，并通过OpenAI GPT模型生成准确答案，确保所有回答都来源于上传的文档而不进行虚构。此外，该应用还提供了友好的聊天界面，允许在一次会话中提出多个问题，并能在加载多个文档时询问澄清问题以提高准确性。该项目使用Python编写，结合了Streamlit作为前端展示工具，非常适合需要快速从大量Word文档中提取信息的场景，如企业知识库查询、学术研究资料整理等。","2026-06-11 04:03:10","CREATED_QUERY"]