update

docs/CHANGING_AI_MODEL.md

@@ -15,6 +15,21 @@ OLLAMA_MODEL=phi3:latest
 
 ## ✅ How to Change the Model
 
+### Important Note
+
+✅ **The model IS automatically checked and downloaded on startup**
+
+The `ollama-setup` service runs on every `docker-compose up` and:
+- Checks if the model specified in `.env` exists
+- Downloads it if missing
+- Skips download if already present
+
+This means you can simply:
+1. Change `OLLAMA_MODEL` in `.env`
+2. Run `docker-compose up -d`
+3. Wait for download (if needed)
+4. Done!
+
 ### Step 1: Update .env File
 
 Edit `backend/.env` and change the `OLLAMA_MODEL` value:
@@ -30,22 +45,38 @@ OLLAMA_MODEL=mistral:7b
 OLLAMA_MODEL=your-custom-model:latest
 ```
 
-### Step 2: Restart Services
-
-The model will be automatically downloaded on startup:
+### Step 2: Restart Services (Model Auto-Downloads)
 
+**Option A: Simple restart (Recommended)**
 ```bash
-# Stop services
-docker-compose down
-
-# Start services (model will be pulled automatically)
+# Restart all services
 docker-compose up -d
 
-# Watch the download progress
+# Watch the model check/download
 docker-compose logs -f ollama-setup
 ```
 
-**Note:** First startup with a new model takes 2-10 minutes depending on model size.
+The `ollama-setup` service will:
+- Check if the new model exists
+- Download it if missing (2-10 minutes)
+- Skip download if already present
+
+**Option B: Manual pull (if you want control)**
+```bash
+# Pull the model manually first
+./pull-ollama-model.sh
+
+# Then restart
+docker-compose restart crawler backend
+```
+
+**Option C: Full restart**
+```bash
+docker-compose down
+docker-compose up -d
+```
+
+**Note:** Model download takes 2-10 minutes depending on model size.
 
 ## Supported Models
 
@@ -264,3 +295,68 @@ A: 5-10GB for small models, 50GB+ for large models. Plan accordingly.
 - [OLLAMA_SETUP.md](OLLAMA_SETUP.md) - Ollama installation & configuration
 - [GPU_SETUP.md](GPU_SETUP.md) - GPU acceleration setup
 - [AI_NEWS_AGGREGATION.md](AI_NEWS_AGGREGATION.md) - AI features overview
+
+
+## Complete Example: Changing from phi3 to llama3
+
+```bash
+# 1. Check current model
+curl -s http://localhost:5001/api/ollama/models | python3 -m json.tool
+# Shows: "current_model": "phi3:latest"
+
+# 2. Update .env file
+# Edit backend/.env and change:
+# OLLAMA_MODEL=llama3:8b
+
+# 3. Pull the new model
+./pull-ollama-model.sh
+# Or manually: docker-compose exec ollama ollama pull llama3:8b
+
+# 4. Restart services
+docker-compose restart crawler backend
+
+# 5. Verify the change
+curl -s http://localhost:5001/api/ollama/models | python3 -m json.tool
+# Shows: "current_model": "llama3:8b"
+
+# 6. Test performance
+curl -s http://localhost:5001/api/ollama/test | python3 -m json.tool
+# Should show improved quality with llama3
+```
+
+## Quick Reference
+
+### Change Model Workflow
+
+```bash
+# 1. Edit .env
+vim backend/.env  # Change OLLAMA_MODEL
+
+# 2. Pull model
+./pull-ollama-model.sh
+
+# 3. Restart
+docker-compose restart crawler backend
+
+# 4. Verify
+curl http://localhost:5001/api/ollama/test
+```
+
+### Common Commands
+
+```bash
+# List downloaded models
+docker-compose exec ollama ollama list
+
+# Pull a specific model
+docker-compose exec ollama ollama pull mistral:7b
+
+# Remove a model
+docker-compose exec ollama ollama rm phi3:latest
+
+# Check current config
+curl http://localhost:5001/api/ollama/config
+
+# Test performance
+curl http://localhost:5001/api/ollama/test
+```