Update app.py

app.py

@@ -4,6 +4,7 @@ from fastapi import FastAPI, Request
 import subprocess
 from huggingface_hub import InferenceClient, login  #, configure_http_backend, get_session
 import langid
+from litellm import completion
 # import requests
 
 
@@ -78,15 +79,25 @@ def generate_response(text):
 
     messages = [{"role": "user", "content": content}]
 
+    # try:
+    #     completion = client.chat.completions.create(
+    #         model=model,
+    #         messages=messages,
+    #         max_tokens=2048,
+    #         temperature=0.5,
+    #         top_p=0.7
+    #     )
+    #     return completion.choices[0].message.content
     try:
-        completion = client.chat.completions.create(
+        completion_res = completions(
             model=model,
             messages=messages,
-            max_tokens=2048,
+            max_tokens=200,
             temperature=0.5,
             top_p=0.7
         )
-        return completion.choices[0].message.content
+        print(f"completion_res: {completion_res}")
+        return completion_res
     except Exception as e:
         logger.error(f"Error generating response: {e}")
         return "Error: Could not generate response."