Upload README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
title: Pathshala AI
|
| 3 |
+
colorFrom: green
|
| 4 |
+
colorTo: blue
|
| 5 |
+
sdk: gradio
|
| 6 |
+
sdk_version: 4.44.0
|
| 7 |
+
app_file: app.py
|
| 8 |
+
pinned: false
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Pathshala AI
|
| 12 |
+
|
| 13 |
+
Pathshala AI is a bilingual AI tutor demo for rural primary students in Nepal.
|
| 14 |
+
|
| 15 |
+
The Gradio Space accepts a student question in English, Nepali, or romanized Nepali plus optional textbook context, then returns:
|
| 16 |
+
|
| 17 |
+
- English explanation
|
| 18 |
+
- Nepali explanation
|
| 19 |
+
- 3 simple quiz questions
|
| 20 |
+
|
| 21 |
+
## Deploy To Hugging Face Spaces
|
| 22 |
+
|
| 23 |
+
1. Create a new Hugging Face Space.
|
| 24 |
+
2. Choose `Gradio` as the SDK.
|
| 25 |
+
3. Upload the files from this `hf_space/` folder into the root of the Space:
|
| 26 |
+
- `app.py`
|
| 27 |
+
- `requirements.txt`
|
| 28 |
+
- `README.md`
|
| 29 |
+
4. Commit the files. Hugging Face will build and run the Space automatically.
|
| 30 |
+
|
| 31 |
+
You can also deploy with Git:
|
| 32 |
+
|
| 33 |
+
```bash
|
| 34 |
+
git clone https://huggingface.co/spaces/YOUR_USERNAME/pathshala-ai
|
| 35 |
+
cp hf_space/app.py pathshala-ai/app.py
|
| 36 |
+
cp hf_space/requirements.txt pathshala-ai/requirements.txt
|
| 37 |
+
cp hf_space/README.md pathshala-ai/README.md
|
| 38 |
+
cd pathshala-ai
|
| 39 |
+
git add .
|
| 40 |
+
git commit -m "Deploy Pathshala AI Gradio demo"
|
| 41 |
+
git push
|
| 42 |
+
```
|
| 43 |
+
|
| 44 |
+
## Recommended Submission Mode
|
| 45 |
+
|
| 46 |
+
For the easiest hackathon submission, deploy the Space without `BACKEND_URL`.
|
| 47 |
+
It will use the built-in mock fallback, so judges can try it immediately.
|
| 48 |
+
|
| 49 |
+
For the full RAG workflow, first deploy the FastAPI backend somewhere public, then set `BACKEND_URL` in the Space settings.
|
| 50 |
+
|
| 51 |
+
## Backend Mode
|
| 52 |
+
|
| 53 |
+
Set `BACKEND_URL` to use the FastAPI backend:
|
| 54 |
+
|
| 55 |
+
```bash
|
| 56 |
+
BACKEND_URL=https://your-backend.example.com
|
| 57 |
+
```
|
| 58 |
+
|
| 59 |
+
In Hugging Face Spaces, add it under:
|
| 60 |
+
|
| 61 |
+
```text
|
| 62 |
+
Space settings -> Variables and secrets -> New variable
|
| 63 |
+
```
|
| 64 |
+
|
| 65 |
+
The app calls `POST /ask` and displays the backend response.
|
| 66 |
+
If the backend returns `normalized_question`, the Space shows the interpreted question above the English explanation.
|
| 67 |
+
|
| 68 |
+
## Mock Mode
|
| 69 |
+
|
| 70 |
+
If `BACKEND_URL` is missing or the backend is unavailable, the Space uses a simple mock fallback so the demo remains easy to try.
|
| 71 |
+
|
| 72 |
+
Example question:
|
| 73 |
+
|
| 74 |
+
```text
|
| 75 |
+
soil erosion vaneko ke ho
|
| 76 |
+
```
|
| 77 |
+
|
| 78 |
+
You can also try mixed romanized Nepali questions such as:
|
| 79 |
+
|
| 80 |
+
```text
|
| 81 |
+
photosynthesis vaneko ke ho vana
|
| 82 |
+
```
|