Create app.py

app.py

@@ -0,0 +1,117 @@
+import os
+from typing import Optional
+
+import google.generativeai as genai
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+
+# =========================
+# Config
+# =========================
+
+GEMINI_API_KEY = os.getenv("GEMINI_API_KEY")
+DEFAULT_MODEL = "gemma-3-4b-it"
+
+if not GEMINI_API_KEY:
+    raise RuntimeError("GEMINI_API_KEY is not set in environment variables.")
+
+genai.configure(api_key=GEMINI_API_KEY)
+
+app = FastAPI(title="Gemma FastAPI", version="1.0.0")
+
+
+# =========================
+# Request / Response Models
+# =========================
+
+class ChatRequest(BaseModel):
+    message: str
+    system_prompt: Optional[str] = "أنت مساعد عربي مفيد. أجب بشكل واضح ومباشر."
+    model: Optional[str] = DEFAULT_MODEL
+    temperature: Optional[float] = 0.3
+    max_output_tokens: Optional[int] = 300
+
+
+class ChatResponse(BaseModel):
+    success: bool
+    model: str
+    input_message: str
+    reply: str
+
+
+# =========================
+# Helper
+# =========================
+
+def generate_reply(
+    user_message: str,
+    system_prompt: str,
+    model_name: str,
+    temperature: float,
+    max_output_tokens: int
+) -> str:
+    prompt = f"{system_prompt}\n\nUser: {user_message}\nAssistant:"
+
+    generation_config = genai.types.GenerationConfig(
+        temperature=temperature,
+        max_output_tokens=max_output_tokens,
+        top_p=0.95,
+    )
+
+    model = genai.GenerativeModel(model_name)
+
+    response = model.generate_content(
+        prompt,
+        generation_config=generation_config
+    )
+
+    try:
+        return response.text.strip()
+    except Exception:
+        return "Model returned an empty response."
+
+
+# =========================
+# Routes
+# =========================
+
+@app.get("/")
+def home():
+    return {"status": "ok", "message": "Gemma API is running"}
+
+
+@app.post("/chat", response_model=ChatResponse)
+def chat(req: ChatRequest):
+    if not req.message or not req.message.strip():
+        raise HTTPException(status_code=400, detail="message is required")
+
+    print("\n========== NEW REQUEST ==========")
+    print("Incoming message:")
+    print(req.message)
+    print("Model:", req.model)
+
+    try:
+        reply = generate_reply(
+            user_message=req.message,
+            system_prompt=req.system_prompt or "أنت مساعد مفيد.",
+            model_name=req.model or DEFAULT_MODEL,
+            temperature=req.temperature if req.temperature is not None else 0.3,
+            max_output_tokens=req.max_output_tokens if req.max_output_tokens is not None else 300
+        )
+
+        print("\nModel reply:")
+        print(reply)
+        print("=================================\n")
+
+        return ChatResponse(
+            success=True,
+            model=req.model or DEFAULT_MODEL,
+            input_message=req.message,
+            reply=reply
+        )
+
+    except Exception as e:
+        print("\nERROR:")
+        print(str(e))
+        print("=================================\n")
+        raise HTTPException(status_code=500, detail=str(e))