Update app.py

app.py

@@ -22,10 +22,7 @@ app = FastAPI()
 async def read_root():
     return {"Hello": "World!"}
 
-
-@app.post("/model")
-async def model(data: dict):
-    prompt = data.get("prompt")
+def modelResp(promt):
     messages = [
         {"role": "system", "content": "You are a helpful assistant, Sia, developed by Sushma. You will response in polity and brief."},
         {"role": "user", "content": "Who are you?"},
@@ -50,9 +47,7 @@ async def model(data: dict):
 
     return response
 
-@app.post("/model1")
-async def model1(data: dict):
-    prompt = data.get("prompt")
+def modelResp1(promt):
     messages = [
         {"role": "system", "content": "You are a helpful assistant, Sia, developed by Sushma. You will response in polity and brief."},
         {"role": "user", "content": "Who are you?"},
@@ -65,7 +60,7 @@ async def model1(data: dict):
         add_generation_prompt=True
     )
     model_inputs = tokenizer([text], return_tensors="pt").to(device)    
-    generated_ids = model.generate(
+    generated_ids = model1.generate(
         model_inputs.input_ids,
         max_new_tokens=64,
         do_sample=True
@@ -75,4 +70,16 @@ async def model1(data: dict):
     ] 
     response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
 
-    return response 
+    return response
+    
+@app.post("/modelapi")
+async def modelApi(data: dict):
+    prompt = data.get("prompt")
+    response = modelResp(prompt)
+    return response
+
+@app.post("/modelapi1")
+async def modelApi1(data: dict):
+    prompt = data.get("prompt")
+    response = modelResp1(prompt)
+    return response