Deploy to Hugging Face Spaces with Docker config

Dockerfile

@@ -0,0 +1,36 @@
+# Use an official Python runtime as a parent image
+FROM python:3.10-slim
+
+# Set the working directory in the container
+WORKDIR /app
+
+# Install system dependencies for audio and document processing
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    libasound2-dev \
+    portaudio19-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy the requirements file into the container
+COPY requirements.txt .
+
+# Install any needed packages specified in requirements.txt
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the rest of the application code
+COPY . .
+
+# Create directory for models/cache with full permissions
+RUN mkdir -p /.cache && chmod -R 777 /.cache
+
+# Set environment variables for memory efficiency
+ENV MKL_NUM_THREADS=1
+ENV OMP_NUM_THREADS=1
+ENV TRANSFORMERS_CACHE=/.cache
+ENV HF_HOME=/.cache
+
+# Hugging Face Spaces uses port 7860 by default
+EXPOSE 7860
+
+# Run the application
+CMD ["gunicorn", "--bind", "0.0.0.0:7860", "app:app", "--timeout", "120", "--workers", "1", "--threads", "4"]

README.md

@@ -0,0 +1,27 @@
+---
+title: Insurance Brochure RAG
+emoji: 🛡️
+colorFrom: green
+colorTo: blue
+sdk: docker
+app_port: 7860
+pinned: false
+---
+
+# Insurance Brochure RAG Application
+
+An AI-powered RAG system for analyzing insurance brochures and documents.
+
+## Local Development
+
+1. Install requirements: `pip install -r requirements.txt`
+2. Set `.env` variables (see `.env.example`)
+3. Run `python app.py`
+
+## Hugging Face Deployment
+
+This app is configured to run on Hugging Face Spaces using the **Docker SDK**.
+
+### Configuration
+- **Instance Type**: 16GB RAM (CPU Basic) or higher.
+- **Secrets**: Add `GROQ_API_KEY` in the Space settings.

app.py

@@ -262,5 +262,5 @@ def list_files():
     return jsonify({"files": []})
 
 if __name__ == "__main__":
-    port = int(os.environ.get("PORT", 8000))
+    port = int(os.environ.get("PORT", 7860))
     app.run(host="0.0.0.0", port=port)

render.yaml

@@ -3,9 +3,15 @@ services:
     name: brochure-rag
     env: python
     buildCommand: pip install -r requirements.txt
-    startCommand: gunicorn app:app
+    startCommand: gunicorn app:app --workers 1 --threads 2 --timeout 120
     envVars:
       - key: PYTHON_VERSION
         value: 3.10.0
       - key: PORT
         value: 10000
+      - key: MKL_NUM_THREADS
+        value: "1"
+      - key: OMP_NUM_THREADS
+        value: "1"
+      - key: TRANSFORMERS_OFFLINE
+        value: "1"

requirements.txt

@@ -1,9 +1,6 @@
 flask
 gunicorn
 flask-cors
-fastapi
-uvicorn
-python-multipart
 langchain
 langchain-community
 langchain-core
@@ -19,7 +16,6 @@ tqdm
 langchain-huggingface
 SpeechRecognition
 langchain-groq
-streamlit
 requests
 pdfplumber
 python-docx