cp

deployment/cloud-function/README.md

@@ -1,66 +1,120 @@
-# Cloud Function for Image Processing
+# Cloud Function for Image Embedding Processing
 
-This directory contains the source code for the Cloud Function that processes image embeddings.
+This Cloud Function processes images to generate embeddings using Google's Vertex AI multimodal embedding model and stores them in a Qdrant vector database.
 
-## Deployment
+## Overview
 
-**Note: This Cloud Function is now deployed via Terraform, not the previous bash script.**
+The function is triggered by Pub/Sub messages containing image processing tasks. It:
 
-The Cloud Function is automatically deployed when you run:
+1. Downloads images from Google Cloud Storage
+2. Generates embeddings using Vertex AI's `multimodalembedding@001` model
+3. Stores embeddings in Qdrant vector database
+4. Updates image metadata in Firestore
 
-```bash
-cd deployment/terraform
-terraform apply
-```
+## Key Features
 
-## What the Cloud Function Does
-
-1. **Triggered by Pub/Sub**: Listens to the `image-processing-topic` for new image processing tasks
-2. **Downloads Images**: Retrieves images from Google Cloud Storage
-3. **Generates Embeddings**: Uses Google Cloud Vision API to create image embeddings
-4. **Stores Vectors**: Saves embeddings to the Qdrant vector database
-5. **Updates Status**: Updates Firestore with processing status and embedding metadata
-
-## Environment Variables
-
-The following environment variables are automatically configured by Terraform:
-
-- `QDRANT_HOST`: IP address of the vector database VM
-- `QDRANT_PORT`: Port for Qdrant (default: 6333)
-- `QDRANT_API_KEY`: API key for Qdrant authentication
-- `QDRANT_COLLECTION`: Collection name for storing vectors (default: image_vectors)
-
-## Function Configuration
-
-- **Runtime**: Python 3.11
-- **Memory**: 512MB
-- **Timeout**: 540 seconds (9 minutes)
-- **Max Instances**: 10
-- **Min Instances**: 0 (scales to zero when not in use)
-- **Retry Policy**: Automatic retries on failure
+- **Vertex AI Multimodal Embeddings**: Uses Google's state-of-the-art multimodal embedding model
+- **1408-dimensional vectors**: High-quality embeddings for semantic image search
+- **Automatic retry**: Built-in retry logic for failed processing
+- **Status tracking**: Real-time status updates in Firestore
+- **Scalable**: Auto-scaling Cloud Function with configurable limits
 
 ## Dependencies
 
-See `requirements.txt` for the complete list of Python dependencies.
+- `google-cloud-aiplatform`: Vertex AI SDK for multimodal embeddings
+- `google-cloud-firestore`: Firestore database client
+- `google-cloud-storage`: Cloud Storage client
+- `qdrant-client`: Vector database client
+- `numpy`: Numerical operations
+- `Pillow`: Image processing
+
+## Environment Variables
+
+The function requires these environment variables:
+
+```bash
+# Google Cloud Configuration
+GOOGLE_CLOUD_PROJECT=your-project-id
+VERTEX_AI_LOCATION=us-central1
+
+# Firestore Configuration
+FIRESTORE_PROJECT_ID=your-project-id
+FIRESTORE_DATABASE_NAME=(default)
+
+# Cloud Storage Configuration
+GCS_BUCKET_NAME=your-bucket-name
+
+# Qdrant Configuration
+QDRANT_HOST=your-qdrant-host
+QDRANT_PORT=6333
+QDRANT_API_KEY=your-api-key
+QDRANT_COLLECTION=image_vectors
+QDRANT_HTTPS=false
+
+# Logging
+LOG_LEVEL=INFO
+```
+
+## Testing
+
+### Local Testing
+
+1. Set up your environment:
+```bash
+export GOOGLE_CLOUD_PROJECT=your-project-id
+export VERTEX_AI_LOCATION=us-central1
+```
+
+2. Install dependencies:
+```bash
+pip install -r requirements.txt
+```
+
+3. Run the test script:
+```bash
+python test_vertex_ai_embeddings.py
+```
+
+This will create a test image and verify that embeddings are generated correctly.
+
+### Expected Output
+
+The test should output something like:
+```
+INFO:__main__:Testing Vertex AI multimodal embeddings...
+INFO:__main__:Using project: your-project-id
+INFO:__main__:Creating test image...
+INFO:__main__:Created test image with 1234 bytes
+INFO:__main__:Generating embeddings using Vertex AI...
+INFO:__main__:Generated embeddings with shape: (1408,)
+INFO:__main__:Embeddings dtype: float32
+INFO:__main__:Embeddings range: [-0.1234, 0.5678]
+INFO:__main__:Embeddings norm: 1.0000
+INFO:__main__:✅ All tests passed! Vertex AI embeddings are working correctly.
+INFO:__main__:🎉 Test completed successfully!
+```
+
+## Deployment
+
+The function is deployed using Terraform. See the main deployment documentation for details.
 
 ## Monitoring
 
-The function automatically logs to Google Cloud Logging. You can monitor:
+- Check Cloud Function logs in Google Cloud Console
+- Monitor Firestore for image status updates
+- Check Qdrant for stored embeddings
 
-- Function executions
-- Error rates
-- Processing times
-- Pub/Sub message handling
+## Troubleshooting
 
-## Manual Testing
+### Common Issues
 
-To manually trigger the function, publish a message to the Pub/Sub topic:
+1. **Authentication errors**: Ensure the service account has `roles/aiplatform.user` permission
+2. **API not enabled**: Ensure `aiplatform.googleapis.com` is enabled
+3. **Quota limits**: Check Vertex AI quotas in your project
+4. **Network issues**: Ensure the function can reach Qdrant and other services
 
-```json
-{
-  "image_id": "test-image-123",
-  "storage_path": "your-bucket/path/to/image.jpg",
-  "team_id": "team-456",
-  "retry_count": 0
-}
-``` 
+### Error Messages
+
+- `"Failed to generate embeddings - no image embedding returned"`: Check image format and size
+- `"PROJECT_ID not found in environment variables"`: Set `GOOGLE_CLOUD_PROJECT`
+- `"Error generating embeddings"`: Check Vertex AI API access and quotas