https://github.com/atithi4dev/vectraq-server

End-to-end intelligent document Q&A system using LangChain, OpenAI, and vector databases. Upload PDFs and get GPT-powered answers instantly.
https://github.com/atithi4dev/vectraq-server

document-ai langc openai pdf-cahtbot vector-search

Last synced: about 1 month ago
JSON representation

End-to-end intelligent document Q&A system using LangChain, OpenAI, and vector databases. Upload PDFs and get GPT-powered answers instantly.

• Host: GitHub
• URL: https://github.com/atithi4dev/vectraq-server
• Owner: atithi4dev
• Created: 2025-06-16T22:35:54.000Z (12 months ago)
• Default Branch: main
• Last Pushed: 2025-06-16T23:46:49.000Z (12 months ago)
• Last Synced: 2025-06-17T00:25:18.433Z (12 months ago)
• Topics: document-ai, langc, openai, pdf-cahtbot, vector-search
• Language: JavaScript
• Homepage:
• Size: 52.7 KB
• Stars: 0
• Watchers: 0
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# ⚡ VectraQ-server

## 📌 Status

> 💤 Currently on hold. Basic PDF parsing was prototyped, but the full “chat with PDF” pipeline is paused for now.

---

**VectraQ** is a document-based Q&A system designed to let users upload PDFs, extract text, and eventually interact with the content using natural language queries powered by LLMs and vector embeddings.

This repo serves as the **monorepo** for both backend and frontend components.

---

## 🎯 Project Goals (Planned)

- Upload and parse PDFs  

- Chunk and embed text using LangChain + OpenAI  

- Store embeddings in a vector database (Pinecone)  

- Enable Q&A over documents with context-aware responses  

- Provide a clean UI for interacting with extracted text  

---

## 🛠️ Tech Stack (Planned)

| Layer      | Tech                       |

|------------|----------------------------|

| Frontend   | React, Vite, Tailwind CSS  |

| Backend    | Node.js, Express.js        |

| NLP        | LangChain, OpenAI API      |

| Vector DB  | Pinecone                   |

| Utilities  | Multer, pdf-parse, Axios   |

---

## 📄 License

MIT License.

---

## 🤝 Contributions

Will open once active development resumes.

---

Turning documents into conversation — **VectraQ** (paused but not forgotten).