hotfix

app.py

@@ -32,7 +32,7 @@ def respond(
 
     response = ""
 
-    if not use_cohere_api:
+    if use_cohere_api:
         cohere_response = client_cohere.chat(
             message=message,
             model=COHERE_MODEL,
@@ -42,16 +42,16 @@ def respond(
         response = cohere_response.text
         yield response
     else:
-        for message in client.chat_completion(
+        for message in client_hf.chat_completion(
             messages,
             max_tokens=max_tokens,
+            stream=True,
             temperature=temperature,
             top_p=top_p,
         ):
-            token = message.choices[0].delta.content
-
+            token = message.choices[0].delta.content  # Extract generated token
             response += token
-            yield response
+            yield response  # Yield response incrementally
 
 
 """