update

api.py

@@ -74,6 +74,26 @@ class ChatRequest(BaseModel):
     messages: List[ChatMessage]
     temperature: float = Field(0.2, ge=0.1, le=1.0)
     max_tokens: int = Field(256, ge=1, le=1024)
+# ========== OPENAI / OPENROUTER SCHEMAS ==========
+
+class OpenAIMessage(BaseModel):
+    role: str
+    content: str
+
+class ChatCompletionRequest(BaseModel):
+    model: str
+    messages: List[OpenAIMessage]
+    temperature: Optional[float] = 0.2
+    max_tokens: Optional[int] = 256
+    top_p: Optional[float] = 0.95
+    stream: Optional[bool] = False
+
+class CompletionRequest(BaseModel):
+    model: str
+    prompt: str
+    temperature: Optional[float] = 0.2
+    max_tokens: Optional[int] = 256
+    top_p: Optional[float] = 0.95
 
 # ========== GESTION DU MODÈLE ==========
 class ModelManager:
@@ -449,6 +469,68 @@ async def download_status():
         }
     return {"downloaded": False, "message": "No model downloaded yet"}
 
+@app.post("/v1/chat/completions")
+async def openai_chat(request: ChatCompletionRequest):
+    try:
+        messages = [m.dict() for m in request.messages]
+
+        response_text = model_manager.chat(
+            messages=messages,
+            temperature=request.temperature,
+            max_tokens=request.max_tokens
+        )
+
+        return {
+            "id": f"chatcmpl-{int(time.time())}",
+            "object": "chat.completion",
+            "created": int(time.time()),
+            "model": request.model,
+            "choices": [
+                {
+                    "index": 0,
+                    "message": {
+                        "role": "assistant",
+                        "content": response_text
+                    },
+                    "finish_reason": "stop"
+                }
+            ],
+            "usage": {
+                "prompt_tokens": 0,
+                "completion_tokens": 0,
+                "total_tokens": 0
+            }
+        }
+
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+@app.post("/v1/completions")
+async def openai_completion(request: CompletionRequest):
+    try:
+        response_text = model_manager.generate(
+            prompt=request.prompt,
+            temperature=request.temperature,
+            max_tokens=request.max_tokens,
+            top_p=request.top_p
+        )
+
+        return {
+            "id": f"cmpl-{int(time.time())}",
+            "object": "text_completion",
+            "created": int(time.time()),
+            "model": request.model,
+            "choices": [
+                {
+                    "text": response_text,
+                    "index": 0,
+                    "finish_reason": "stop"
+                }
+            ]
+        }
+
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))   
+
 if __name__ == "__main__":
     import uvicorn
     port = int(os.getenv("PORT", 7860))