updated docker file

Dockerfile

@@ -13,13 +13,15 @@ RUN pip install --no-cache-dir --upgrade pip \
 COPY . /app
 
 # Create logs directory with proper permissions
-RUN mkdir -p /app/logs && chmod -R 777 /app/logs
+RUN mkdir -p /app/logs /app/.cache/huggingface && chmod -R 777 /app/logs /app/.cache/huggingface
+
 
 # Install additional dependencies
 RUN apt-get update && apt-get install -y tmux curl
 
 # Ensure the Hugging Face cache is set correctly
 ENV TRANSFORMERS_CACHE="/app/.cache/huggingface"
+ENV HF_HOME="/app/.cache/huggingface"
 
 # Set Python path
 ENV PYTHONPATH="/app/src"

requirements.txt

@@ -7,5 +7,6 @@ pinecone
 torch
 torchvision
 torchaudio
+transformers
 sentence_transformers
 groq

src/backend/data/pinecone_db.py

@@ -136,7 +136,7 @@ def upsert_data_in_db(df: pd.DataFrame):
     
         vectors = []
         for idx, (embedding, (_, row_data)) in enumerate(zip(batch["embedding"], batch.iterrows())):
-            vector_id = f"q_{i + idx}"  # Ensures IDs remain unique across batches
+            vector_id = f"question_{i + idx}"  # Ensures IDs remain unique across batches
             metadata = {
                 "question": row_data.get("input"),
                 "answer": row_data.get("output")