app.py

import os
from typing import List, Literal, Optional

from fastapi import FastAPI, HTTPException
from fastapi.responses import JSONResponse
from openai import OpenAI
from pydantic import BaseModel, Field

app = FastAPI(title="GLM-5 Chat API", version="1.0.0")

HF_TOKEN = os.getenv("HUGGINGFACEHUB_API_TOKEN")
MODEL_NAME = os.getenv("MODEL_NAME", "zai-org/GLM-5")

if not HF_TOKEN:
    raise RuntimeError("HF_TOKEN environment variable is missing.")

client = OpenAI(
    base_url="https://router.huggingface.co/v1",
    api_key=HF_TOKEN,
)


class ChatMessage(BaseModel):
    role: Literal["system", "user", "assistant"]
    content: str


class ChatRequest(BaseModel):
    messages: List[ChatMessage] = Field(..., min_length=1)
    temperature: Optional[float] = 0.7
    max_tokens: Optional[int] = 700
    top_p: Optional[float] = 0.95


class SimpleChatRequest(BaseModel):
    message: str
    system_prompt: Optional[str] = "أنت مساعد ذكي ومفيد. جاوب بشكل طبيعي وواضح."
    temperature: Optional[float] = 0.7
    max_tokens: Optional[int] = 700
    top_p: Optional[float] = 0.95


@app.get("/")
def root():
    return {
        "ok": True,
        "service": "glm5-fastapi",
        "model": MODEL_NAME,
        "endpoints": ["/health", "/chat", "/chat/simple"],
    }


@app.get("/health")
def health():
    return {"ok": True, "model": MODEL_NAME}


@app.post("/chat/simple")
def chat_simple(req: SimpleChatRequest):
    try:
        response = client.chat.completions.create(
            model=MODEL_NAME,
            messages=[
                {"role": "system", "content": req.system_prompt},
                {"role": "user", "content": req.message},
            ],
            temperature=req.temperature,
            max_tokens=req.max_tokens,
            top_p=req.top_p,
        )

        choice = response.choices[0]

        reply = ""
        if choice.message and choice.message.content:
            reply = choice.message.content

        finish_reason = getattr(choice, "finish_reason", None)

        usage = None
        if getattr(response, "usage", None):
            usage = {
                "prompt_tokens": response.usage.prompt_tokens,
                "completion_tokens": response.usage.completion_tokens,
                "total_tokens": response.usage.total_tokens,
            }

        return JSONResponse(
            {
                "ok": True,
                "model": MODEL_NAME,
                "reply": reply,
                "finish_reason": finish_reason,
                "usage": usage,
            }
        )

    except Exception as e:
        raise HTTPException(status_code=500, detail=str(e))


@app.post("/chat")
def chat(req: ChatRequest):
    try:
        response = client.chat.completions.create(
            model=MODEL_NAME,
            messages=[m.model_dump() for m in req.messages],
            temperature=req.temperature,
            max_tokens=req.max_tokens,
            top_p=req.top_p,
        )

        choice = response.choices[0]

        reply = ""
        if choice.message and choice.message.content:
            reply = choice.message.content

        finish_reason = getattr(choice, "finish_reason", None)

        usage = None
        if getattr(response, "usage", None):
            usage = {
                "prompt_tokens": response.usage.prompt_tokens,
                "completion_tokens": response.usage.completion_tokens,
                "total_tokens": response.usage.total_tokens,
            }

        return JSONResponse(
            {
                "ok": True,
                "model": MODEL_NAME,
                "reply": reply,
                "finish_reason": finish_reason,
                "usage": usage,
            }
        )

    except Exception as e:
        raise HTTPException(status_code=500, detail=str(e))