How to deploy FastAPI LLM app on GCP

pip install fastapi uvicorn openai

# Install Google Cloud SDK from https://cloud.google.com/sdk/docs/install

# Authenticate with GCP
 gcloud auth login
 gcloud config set project YOUR_GCP_PROJECT_ID

# Set environment variable for OpenAI API key
 export OPENAI_API_KEY=os.environ["OPENAI_API_KEY"]

import os
from fastapi import FastAPI
from pydantic import BaseModel
from openai import OpenAI

app = FastAPI()
client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

class PromptRequest(BaseModel):
    prompt: str

@app.post("/generate")
async def generate_text(request: PromptRequest):
    response = client.chat.completions.create(
        model="gpt-4o-mini",
        messages=[{"role": "user", "content": request.prompt}]
    )
    return {"response": response.choices[0].message.content}

# Dockerfile
# FROM python:3.10-slim
# WORKDIR /app
# COPY requirements.txt .
# RUN pip install -r requirements.txt
# COPY . .
# CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8080"]

# Build and deploy commands
# docker build -t gcr.io/YOUR_GCP_PROJECT_ID/fastapi-llm-app .
# docker push gcr.io/YOUR_GCP_PROJECT_ID/fastapi-llm-app
# gcloud run deploy fastapi-llm-app --image gcr.io/YOUR_GCP_PROJECT_ID/fastapi-llm-app --platform managed --region us-central1 --allow-unauthenticated