Fix: Add protobuf dependency and remove problematic model pre-download

Dockerfile

@@ -13,9 +13,8 @@ COPY requirements.txt .
 # Install Python dependencies
 RUN pip install --no-cache-dir -r requirements.txt
 
-# Download models at build time
+# Pre-download embedding model (optional, saves first-request time)
 RUN python -c "from sentence_transformers import SentenceTransformer; SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')"
-RUN python -c "from transformers import pipeline; pipeline('text-classification', model='microsoft/deberta-v3-xsmall')"
 
 # Copy application code
 COPY . .

requirements.txt

@@ -11,3 +11,4 @@ python-dotenv>=1.0.0
 huggingface-hub>=0.16.0
 requests>=2.31.0
 scikit-learn>=1.3.0
+protobuf>=3.20.0