Update app.py

app.py

@@ -5,7 +5,8 @@ import torch
 import optimum
 from transformers import (AutoModelForCausalLM, AutoTokenizer, LlamaForCausalLM, LlamaTokenizer, GenerationConfig, pipeline,)
 
-app = FastAPI()
+app = FastAPI(title="Deploying FastAPI Apps on Huggingface")
+
     
 # Load the model and tokenizer
 model_name_or_path = "TheBloke/Wizard-Vicuna-7B-Uncensored-GPTQ"
@@ -51,13 +52,17 @@ def load_model_norm():
     return model, tokenizer 
 
 
+@app.get("/", tags=["Home"])
+async def api_home():
+    return {'detail': 'Welcome to Eren Bot!'}
+    
 @app.get("/")
 async def read_root():
     return {"message": "Welcome to Eren Bot!"}
 
 
 # Endpoint to start a new conversation thread
-@app.post('/start_conversation')
+@app.post('/api/start_conversation')
 async def start_conversation(request: Request):
     data = await request.json()
     prompt = data.get('prompt')
@@ -73,7 +78,7 @@ async def start_conversation(request: Request):
 
 
 # Endpoint to get the response of a conversation thread
-@app.get('/get_response/{thread_id}')
+@app.get('/api/get_response/{thread_id}')
 async def get_response(thread_id: int):
     if thread_id not in conversations:
         raise HTTPException(status_code=404, detail="Thread not found")