Refactor Dockerfile and update app launch configuration

Dockerfile

@@ -1,21 +1,35 @@
-FROM python:3.13
+# Dockerfile
+FROM python:3.13-slim
 
+# (Recommended) Install curl & certs on -slim base
+RUN apt-get update && apt-get install -y --no-install-recommends curl ca-certificates \
+  && rm -rf /var/lib/apt/lists/*
+
+# Install uv (installs to /root/.local/bin by default)
 RUN curl -LsSf https://astral.sh/uv/install.sh | sh
-# uv was installed to /root/.local/bin – add it to PATH
+# Make sure uv is on PATH for all later steps
 ENV PATH="/root/.local/bin:${PATH}"
 
+# Create the HF-required user (UID 1000) before copying files
 RUN useradd -m -u 1000 user
-WORKDIR /app
-
-COPY pyproject.toml uv.lock ./
-RUN uv sync --locked
 
-COPY . .
+# Work in the user's home to avoid permissions issues
+ENV HOME=/home/user \
+    PATH="/root/.local/bin:/home/user/.local/bin:${PATH}"
+WORKDIR /home/user/app
 
+# Copy only deps first for better caching; make them owned by 'user'
+COPY --chown=user:user pyproject.toml uv.lock ./
 
-ENV HOME=/home/user PATH="/root/.local/bin:/home/user/.local/bin:${PATH}"
-RUN chown -R user:user /app
+# Use the non-root user for env creation so .venv belongs to them
 USER user
+RUN uv sync --locked
+
+# Copy the rest of your app
+COPY --chown=user:user . .
 
+# Spaces expects your app to listen on this port; keep README app_port in sync
 EXPOSE 7860
+
+# Start the app via uv
 CMD ["uv", "run", "scripts/main.py"]

README.md

@@ -28,7 +28,7 @@ The Gradio demo is deployed on Hugging Face Spaces at: [AI Tutor Chatbot on Hugg
 
 1. **Set environment variables:**
 
-- copy .env.example to a new .env file and fill in the values
+   - copy .env.example to a new .env file and fill in the values
 
 2. **Run the application:**
 

scripts/main.py

@@ -7,20 +7,12 @@ from llama_index.agent.openai import OpenAIAgent
 from llama_index.core.llms import MessageRole
 from llama_index.core.memory import ChatSummaryMemoryBuffer
 from llama_index.core.tools import RetrieverTool, ToolMetadata
-from llama_index.core.vector_stores import (
-    FilterCondition,
-    FilterOperator,
-    MetadataFilter,
-    MetadataFilters,
-)
+from llama_index.core.vector_stores import (FilterCondition, FilterOperator,
+                                            MetadataFilter, MetadataFilters)
 from llama_index.llms.openai import OpenAI
 from prompts import system_message_openai_agent
-from setup import (
-    AVAILABLE_SOURCES,
-    AVAILABLE_SOURCES_UI,
-    CONCURRENCY_COUNT,
-    custom_retriever_all_sources,
-)
+from setup import (AVAILABLE_SOURCES, AVAILABLE_SOURCES_UI, CONCURRENCY_COUNT,
+                   custom_retriever_all_sources)
 
 
 def update_query_engine_tools(selected_sources) -> list[RetrieverTool]:
@@ -263,4 +255,4 @@ with gr.Blocks(
 
 if __name__ == "__main__":
     demo.queue(default_concurrency_limit=CONCURRENCY_COUNT)
-    demo.launch(debug=False, share=False)
+    demo.launch(server_name="0.0.0.0", server_port=7860, debug=False, share=False)