Step 6A — Deploy to Streamlit Cloud (Recommended for Rapid Demos)

1. Ensure your chatbot folder contains:
   • app.py
   • requirements.txt (all dependencies: streamlit, vertexai, python-dotenv, etc.)
   • .streamlit/config.toml (optional: set server.port, theme, etc.)
2. Create a GitHub repository for your project and push the folder:

git init
git add .
git commit -m "Initial commit"
git branch -M main
git remote add origin https://github.com/yourusername/your-chatbot.git
git push -u origin main

3. Go to Streamlit Cloud and sign in (use your GitHub account).
4. Click New App → Select Repository → Branch → Directory and click Deploy.
5. Wait a few minutes — your app URL will look like: https://your-chatbot.streamlit.app
6. Open the URL to test. Everyone with the URL can now access your chatbot.

Step 6B — Deploy to GCP Cloud Run (Optional: More Control / Custom Domain)

1. Install Google Cloud SDK if not already:

   https://cloud.google.com/sdk/docs/install

2. Authenticate and set project:

   gcloud auth login
   gcloud config set project YOUR_PROJECT_ID

3. Create Dockerfile in your project root:

   # Use official Python base image
   FROM python:3.12-slim
   
   # Set working directory
   WORKDIR /app
   
   # Copy files
   COPY . /app
   
   # Install dependencies
   RUN pip install --upgrade pip
   RUN pip install -r requirements.txt
   
   # Expose Streamlit port
   EXPOSE 8501
   
   # Command to run
   CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0"]
           

4. Build Docker image:

   gcloud builds submit --tag gcr.io/YOUR_PROJECT_ID/chatbot

5. Deploy to Cloud Run:

   gcloud run deploy chatbot \
     --image gcr.io/YOUR_PROJECT_ID/chatbot \
     --platform managed \
     --region us-central1 \
     --allow-unauthenticated

6. GCP will provide a URL like https://chatbot-xxxxxx-uc.a.run.app
7. Open the URL and test. Your chatbot is now running fully on cloud infrastructure.

Step 6C — Important Tips

• Ensure your .env with GCP credentials is either in Cloud Secrets or replaced by ADC (Application Default Credentials) when deploying.
• Check logs if your app fails:

  streamlit logs
  gcloud logs read --project YOUR_PROJECT_ID

• For Streamlit Cloud, keep requirements.txt updated with all packages.
• Test locally first:

  streamlit run app.py

• Use avatars as emojis or public URLs so they load correctly in the cloud deployment.

Step 6D — Quick Checklist