Create main.py

main.py

@@ -0,0 +1,103 @@
+from fastapi import FastAPI, Request
+from fastapi.responses import StreamingResponse, JSONResponse
+from pydantic import BaseModel
+import requests
+import time
+import json
+from typing import List, Optional
+from models import AVAILABLE_MODELS
+
+app = FastAPI()
+
+def unix_id():
+    return str(int(time.time() * 1000))
+
+class Message(BaseModel):
+    role: str
+    content: str
+
+class ChatRequest(BaseModel):
+    messages: List[Message]
+    model: str
+    stream: Optional[bool] = False
+
+@app.get("/v1/models")
+async def list_models():
+    return {"object": "list", "data": AVAILABLE_MODELS}
+
+@app.post("/v1/chat/completions")
+async def chat_completion(request: ChatRequest):
+    headers = {
+        'accept': 'text/event-stream',
+        'content-type': 'application/json',
+        'origin': 'https://www.chatwithmono.xyz',
+        'referer': 'https://www.chatwithmono.xyz/',
+        'user-agent': 'Mozilla/5.0',
+    }
+
+    payload = {
+        "messages": [{"role": msg.role, "content": msg.content} for msg in request.messages],
+        "model": request.model
+    }
+
+    if request.stream:
+        def event_stream():
+            with requests.post(
+                "https://www.chatwithmono.xyz/api/chat",
+                headers=headers,
+                json=payload,
+                stream=True,
+                timeout=120
+            ) as response:
+                for line in response.iter_lines(decode_unicode=True):
+                    if line.startswith("0:"):
+                        piece = line[2:]
+                        yield f"data: {json.dumps({'choices': [{'delta': {'content': piece}, 'finish_reason': None}]})}\n\n"
+                    elif line.startswith(("e:", "d:")):
+                        yield "data: [DONE]\n\n"
+        return StreamingResponse(event_stream(), media_type="text/event-stream")
+
+    else:
+        assistant_response = ""
+        usage_info = {}
+
+        with requests.post(
+            "https://www.chatwithmono.xyz/api/chat",
+            headers=headers,
+            json=payload,
+            stream=True,
+            timeout=120
+        ) as response:
+            for chunk in response.iter_lines(decode_unicode=True):
+                if chunk.startswith("0:"):
+                    try:
+                        piece = json.loads(chunk[2:])
+                        assistant_response += piece
+                    except:
+                        continue
+                elif chunk.startswith(("e:", "d:")):
+                    try:
+                        data = json.loads(chunk[2:])
+                        usage_info = data.get("usage", {})
+                    except:
+                        continue
+
+        return JSONResponse(content={
+            "id": f"chatcmpl-{unix_id()}",
+            "object": "chat.completion",
+            "created": int(time.time()),
+            "model": request.model,
+            "choices": [{
+                "index": 0,
+                "message": {
+                    "role": "assistant",
+                    "content": assistant_response
+                },
+                "finish_reason": "stop"
+            }],
+            "usage": {
+                "prompt_tokens": usage_info.get("promptTokens", 0),
+                "completion_tokens": usage_info.get("completionTokens", 0),
+                "total_tokens": usage_info.get("promptTokens", 0) + usage_info.get("completionTokens", 0),
+            }
+        })