OmniMind AI is an Enterprise-level AI Assistant platform designed using modern Generative AI technologies.
It combines Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and intelligent memory-based conversations to create a powerful AI workspace.
The system allows users to interact with an AI assistant, upload documents, retrieve contextual information, and receive intelligent responses powered by local LLM models.
🚧 This project is currently under active development.
New AI capabilities, agent workflows, UI improvements, and optimizations are continuously being added.
- Interactive chatbot experience
- Natural language understanding
- Context-aware responses
- Upload PDF documents
- Extract and process document knowledge
- Semantic search using embeddings
- AI answers based on document context
- Maintains previous interactions
- Provides more personalized responses
- Improves contextual understanding
- Ollama powered local AI models
- Privacy-focused AI execution
- No dependency on external APIs
- FastAPI-based REST architecture
- Modular API routing
- Scalable service structure
- Streamlit-based AI workspace
- Interactive user interface
- Document upload support
- Python
- Large Language Models (LLMs)
- Retrieval-Augmented Generation
- NLP
- Embeddings
- LangChain
- FastAPI
- Streamlit
- HuggingFace Embeddings
- ChromaDB
- Vector Database
- Ollama
- VS Code
- Git
- GitHub
OmniMind-AI │ ├── backend │ ├── services │ │ ├── chat_service.py │ │ ├── ollama_service.py │ │ └── rag_service.py │ │ │ ├── main.py │ ├── database.py │ └── config.py │ ├── frontend │ └── app.py │ ├── vector_db ├── requirements.txt └── README.md
Clone the repository
git clone https://github.com/riyagupta1106/OmniMind-AI.git