https://github.com/decoded-cipher/inovus-ama
An AI-powered AMA system for Inovus Labs, powered by RAG and LLMs. Ask anything about Inovus.
https://github.com/decoded-cipher/inovus-ama
cloudflare gemini-api nuxt pinecone rag-chatbot
Last synced: 5 months ago
JSON representation
An AI-powered AMA system for Inovus Labs, powered by RAG and LLMs. Ask anything about Inovus.
- Host: GitHub
- URL: https://github.com/decoded-cipher/inovus-ama
- Owner: decoded-cipher
- License: mit
- Created: 2025-06-21T20:28:22.000Z (12 months ago)
- Default Branch: master
- Last Pushed: 2025-11-16T16:19:01.000Z (7 months ago)
- Last Synced: 2025-11-16T18:14:18.110Z (7 months ago)
- Topics: cloudflare, gemini-api, nuxt, pinecone, rag-chatbot
- Language: TypeScript
- Homepage: https://ama.inovuslabs.org
- Size: 505 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# 🧠 Inovus Labs AMA (Ask Me Anything)
### ⚠️ ⚠️ **WARNING: UNDER ACTIVE DEVELOPMENT !** ⚠️ ⚠️
🚧 **This project is work in progress.** Parts — or even the entire platform — **may not function correctly** at this stage. Expect bugs, unfinished features, and potential breaking changes. 🛠️🚀
---
An AI-powered, self-hosted Ask-Me-Anything system for Inovus Labs. Ask questions about Inovus Labs and get accurate, grounded answers based on official Inovus documents and knowledge.
This project implements a custom **Retrieval Augmented Generation (RAG)** pipeline using:
✅ **Gemini API** for both embeddings and answer generation
✅ **Pinecone** for efficient, scalable vector search
✅ **Cloudflare R2** for secure document storage
✅ A modern **Nuxt 3** frontend for seamless user interaction
✅ Node.js + Hono API backend for orchestrating the RAG flow
❎ **Planned MCP Server** integration for real-time, live knowledge
All answers are generated based on your private document collection, with strict topic control. No unrelated or hallucinated information is allowed.
## 🎨 Live Demo
Check out the live demo at [Inovus Labs AMA](https://ama.inovuslabs.com) (currently in development, may be unstable).
## 🗂️ Tech Stack
| Layer | Technology |
|-----------------|----------------------------------------|
| Frontend | Nuxt 3 (Vue 3) + Tailwind CSS |
| RAG Backend | Node.js + Hono |
| Vector Storage | Pinecone |
| Document Storage| Cloudflare R2 |
| Embeddings | Gemini API (embedding-001) |
| Completion | Gemini API (models/gemini-2.5-flash) |
| Deployment | Cloudflare Workers / Pages |
| **Planned** | MCP Server for live data |
## 💡 Features
✅ Conversation History & Context Awareness
✅ Intelligent Follow-up Question Detection
✅ Smart Conversation Summarization (token optimization)
✅ Dynamic Follow-up Suggestions
✅ Clear Conversation functionality
## 🛠️ How It Works
1. User asks a question via the Nuxt frontend
2. API server generates a question embedding (Gemini)
3. Pinecone returns relevant knowledge chunks
4. System composes a grounded prompt
5. Gemini API generates a final answer
6. Response with source references is displayed in the chat UI
In the future, the system will also pull real-time knowledge from the **Inovus MCP Server**.
## 🏷️ License
This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.
## 📦 Roadmap
* [ ] Streaming answers to frontend
* [ ] Advanced rate limiting with Cloudflare Workers
* [ ] **MCP Server integration for real-time knowledge**
* [x] Source citations and traceability