Automate Deployment: FastAPI Model Loader → Auto Deploy on Render → Send API URL to n8n
Budget: ₹1,500 – ₹12,500 INR
I have an automation set up in n8n that fine-tunes models on Google Colab and saves the model files to Google Drive.
I need a freelancer to continue from there and:
✅ What you need to do:
Create a universal app.py (FastAPI) that:
Dynamically loads models from Google Drive based on book_name in the request.
Caches models to avoid reloading every time.
Automate pushing app.py to GitHub (from Colab or Drive using script).
Set up Render to auto-deploy from that GitHub repo.
Deployment command:
nginx
Copy
Edit
uvicorn app:app --host 0.0.0.0 --port 8000
Add requirements.txt (fastapi, torch, transformers, pydantic, uvicorn).
After deployment, automatically send the API URL and book_name to n8n webhook.
✅ Note:
The n8n setup up to saving files in Drive is already done — you only need to continue from there.
✅ Deliverables:
Universal dynamic app.py
Python script to auto-push app.py to GitHub
Render deployment setup (can be documented)
Automatic webhook trigger to n8n after deployment
I need a freelancer to continue from there and:
✅ What you need to do:
Create a universal app.py (FastAPI) that:
Dynamically loads models from Google Drive based on book_name in the request.
Caches models to avoid reloading every time.
Automate pushing app.py to GitHub (from Colab or Drive using script).
Set up Render to auto-deploy from that GitHub repo.
Deployment command:
nginx
Copy
Edit
uvicorn app:app --host 0.0.0.0 --port 8000
Add requirements.txt (fastapi, torch, transformers, pydantic, uvicorn).
After deployment, automatically send the API URL and book_name to n8n webhook.
✅ Note:
The n8n setup up to saving files in Drive is already done — you only need to continue from there.
✅ Deliverables:
Universal dynamic app.py
Python script to auto-push app.py to GitHub
Render deployment setup (can be documented)
Automatic webhook trigger to n8n after deployment