Update main.py

main.py

@@ -6,7 +6,7 @@ import uvicorn
 
 app = FastAPI()
 
-client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
+client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.3")
 
 class Item(BaseModel):
     prompt: str
@@ -48,7 +48,7 @@ def generate(item: Item):
         output += response.token.text
     return output
 
-@app.post("/generate/")
+@app.post("/chat/completions/")
 async def generate_text(item: Item):
     return {"response": generate(item)}