Initial chatbot app with Gemma

Dockerfile

@@ -0,0 +1,13 @@
+# Dockerfile
+FROM python:3.10-slim
+
+WORKDIR /app
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY app.py .
+
+ENV PORT=8080
+
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8080"]

app.py

@@ -0,0 +1,36 @@
+from fastapi import FastAPI, Request
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel
+from huggingface_hub import InferenceClient
+import os
+
+HF_TOKEN = os.getenv("HF_TOKEN")
+MODEL_ID = "google/gemma-2b-it"
+client = InferenceClient(token=HF_TOKEN)
+
+app = FastAPI()
+
+# Allow CORS for all origins (for development and Netlify)
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  # For production, specify frontend domain
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+class ChatRequest(BaseModel):
+    message: str
+
+@app.post("/chat")
+async def chat(req: ChatRequest):
+    try:
+        messages = [{"role": "user", "content": req.message}]
+        response = client.chat_completion(
+            model=MODEL_ID,
+            messages=messages,
+            temperature=0.7,
+        )
+        return {"response": response.choices[0].message.content}
+    except Exception as e:
+        return {"error": str(e)}

requirements.txt

@@ -0,0 +1,4 @@
+fastapi
+uvicorn
+huggingface_hub
+python-dotenv