Upload Dockerfile and requirements

Dockerfile

@@ -0,0 +1,45 @@
+# User Modeling Agent — DSN × BCT LLM Agent Challenge, Task A
+# Containerized Streamlit web application.
+#
+# Build:   docker build -t user-modeling-agent .
+# Run:     docker run -p 7860:7860 --env-file .env user-modeling-agent
+# Open:    http://localhost:7860
+#
+# The container needs an LLM key at runtime. Pass it with --env-file .env
+# (a file containing LLM_PROVIDER and GEMINI_API_KEY / OPENAI_API_KEY),
+# or with -e LLM_PROVIDER=gemini -e GEMINI_API_KEY=...
+
+FROM python:3.11-slim
+
+# System deps occasionally needed by pandas / pyarrow wheels
+RUN apt-get update && apt-get install -y --no-install-recommends \
+        build-essential \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+# Install Python dependencies first so this layer caches across code changes
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the application
+COPY . .
+
+# Streamlit serves on 7860
+EXPOSE 7860
+
+# Container healthcheck — Streamlit exposes a health endpoint
+HEALTHCHECK --interval=30s --timeout=5s --start-period=20s --retries=3 \
+    CMD python -c "import urllib.request,sys; urllib.request.urlopen('http://localhost:7860/_stcore/health'); " || exit 1
+
+# Run the Streamlit web app, reachable from outside the container
+ENTRYPOINT ["streamlit", "run", "app.py", \
+            "--server.port=7860", \
+            "--server.address=0.0.0.0", \
+            "--server.headless=true"]
+
+# --- Alternative: run the FastAPI service instead of the Streamlit app ---
+# Comment out the ENTRYPOINT above and uncomment below:
+# EXPOSE 8000
+# ENTRYPOINT ["uvicorn", "task_a_user_modeling.main:app", \
+#             "--host", "0.0.0.0", "--port", "8000"]

requirements.txt

@@ -0,0 +1,35 @@
+# ── Core ─────────────────────────────────────────────
+openai>=1.50.0
+langchain>=0.3.0
+langchain-openai>=0.2.0
+langchain-google-genai>=2.0.0    # Gemini support (optional, only if LLM_PROVIDER=gemini)
+langchain-core>=0.3.0
+python-dotenv>=1.0.0
+tenacity>=8.2.0           # retry decorator for flaky LLM calls
+
+# ── Data ─────────────────────────────────────────────
+pandas>=2.2.0
+numpy>=1.26.0
+pyarrow>=15.0.0           # parquet for Amazon Reviews 2023
+datasets>=2.18.0          # huggingface datasets loader
+
+# ── Embeddings & retrieval ───────────────────────────
+chromadb>=0.5.0
+sentence-transformers>=3.0.0
+
+# ── API + UI ─────────────────────────────────────────
+fastapi>=0.110.0
+uvicorn[standard]>=0.29.0
+pydantic>=2.6.0
+streamlit>=1.32.0
+httpx>=0.27.0
+
+# ── Evaluation ───────────────────────────────────────
+bert-score>=0.3.13
+scikit-learn>=1.4.0
+tqdm>=4.66.0
+
+# ── Dev / paper ──────────────────────────────────────
+jupyter>=1.0.0
+matplotlib>=3.8.0
+seaborn>=0.13.0