Spaces:
Running
Running
# π AI Study Assistant (Powered by Microsoft Phi-3) | |
Welcome to the **AI Study Assistant** β your personalized academic learning tool, built to help students understand complex course material with clarity, precision, and speed. | |
### π What it does | |
- β **Upload Study Material**: PDF, DOCX, TXT, or PPTX | |
- π€ **Ask Questions**: About any concept in the uploaded files | |
- π§ **AI-Powered Reasoning**: Uses Microsoftβs Phi-3 (128k) to provide deep, structured, academic responses | |
- π **Retrieval-Augmented Generation**: Combines vector-based document search with LLMs | |
- π **Context-Based Answers**: Doesnβt hallucinate β only uses whatβs in your file | |
- β¨ **Auto-Summary**: Large answers are summarized into a short academic recap | |
--- | |
### π Who it's for | |
- Students revising for exams | |
- Professionals needing quick insights from documents | |
- Educators building tutoring tools | |
- Anyone learning from dense academic material | |
--- | |
### π How it works | |
1. **Upload** one or more lecture files (PDF, Word, PPT, TXT) | |
2. Ask a question like: | |
- *"Define supervised learning"* | |
- *"Explain the difference between classification and regression"* | |
3. The AI will: | |
- Extract your document | |
- Find the most relevant parts | |
- Think deeply using a powerful LLM | |
- Give a clean, well-structured, academic answer | |
--- | |
### π§ Under the hood | |
| Component | Description | | |
|------------------|----------------------------------------------------------| | |
| **LLM** | `microsoft/phi-3-mini-128k-instruct` (4-bit CPU mode) | | |
| **Vector Search** | FAISS + HuggingFace MiniLM Embeddings | | |
| **Framework** | Gradio Interface via Hugging Face Spaces | | |
| **Auto Summary** | DistilBART summarization for long answers | | |
--- | |
### π Privacy | |
This app does **not** store or log any of your uploaded files or questions. All processing happens in memory and is discarded after your session. | |
--- | |
### π¬ Example Prompts | |
> - "List all types of memory in operating systems" | |
> - "What does this document say about reinforcement learning?" | |
> - "Explain deadlock prevention based on the slides" | |
--- | |
### π‘ Inspiration | |
Built to replicate how a personal AI tutor should behave: focused, accurate, context-aware, and reliable β not a chatbot, but a **study partner**. | |
--- | |
### π§βπ» Built by | |
> Designed & developed by a student β for students β using only open-source models. | |
--- | |
### π Tags | |
`#Education` `#AI` `#Phi3` `#StudentTools` `#NLP` `#Gradio` `#DocumentQA` `#OpenSource` | |