Refactor Dockerfile to improve cache directory structure and permissions; update app.py to use a more accurate model identifier and enhance logging for model initialization.

Dockerfile

@@ -13,11 +13,15 @@ RUN apt-get update && apt-get install -y \
 RUN mkdir -p /app/vector_store /app/chat_history /app/.cache && \
     chmod 777 /app/vector_store /app/chat_history /app/.cache
 
-# Set environment variables
-ENV TRANSFORMERS_CACHE=/app/.cache
-ENV HF_HOME=/app/.cache
+# Set environment variables and cache directories
+ENV TRANSFORMERS_CACHE=/app/.cache/huggingface
+ENV HF_HOME=/app/.cache/huggingface
 ENV XDG_CACHE_HOME=/app/.cache
 
+# Create cache directories with proper permissions
+RUN mkdir -p /app/.cache/huggingface && \
+    chmod -R 777 /app/.cache
+
 # Copy requirements first to leverage Docker cache
 COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
@@ -36,4 +40,4 @@ EXPOSE 8000
 USER 1000
 
 # Run the application
-CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8000"]
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8000"]

app.py

@@ -113,12 +113,19 @@ def init_models():
             api_key=os.getenv("GROQ_API_KEY"),
             callback_manager=callback_manager
         )
-        # Используем smaller модель для эмбеддингов
+        
+        # Используем модель с корректным идентификатором
         embeddings = HuggingFaceEmbeddings(
-            model_name="intfloat/multilingual-e5-small-instruct"
+            model_name="sentence-transformers/paraphrase-multilingual-mpnet-base-v2",
+            cache_folder="/app/.cache"
         )
+        
+        logger.info("Models initialized successfully")
         return llm, embeddings
+        
     except Exception as e:
+        logger.error(f"Model initialization error: {str(e)}")
+        logger.error(traceback.format_exc())
         raise Exception(f"Model initialization failed: {str(e)}")
 
 async def fetch_url(session, url):
@@ -394,4 +401,4 @@ def log_interaction(user_input: str, bot_response: str, context: str):
 
 if __name__ == "__main__":
     import uvicorn
-    uvicorn.run(app, host="0.0.0.0", port=8000)
+    uvicorn.run(app, host="0.0.0.0", port=8000)