Update app.py

app.py

@@ -151,7 +151,7 @@ def readitaloud(result):
     components.html(documentHTML5, width=800, height=300)
     #return result
 
-def chat_with_model_llama(prompt, document_section, model_choice='Llama-2-7b-chat-hf'):
+def chat_with_model(prompt, document_section, model_choice='Llama-2-7b-chat-hf'):
     # API_URL = 'https://qe55p8afio98s0u3.us-east-1.aws.endpoints.huggingface.cloud'  # Dr Llama
     API_URL = "https://api-inference.huggingface.co/models/meta-llama/Llama-2-7b-chat-hf"  # HF model for Llama 7B
     #API_KEY = os.getenv('API_KEY')
@@ -169,15 +169,18 @@ def chat_with_model_llama(prompt, document_section, model_choice='Llama-2-7b-cha
     conversation.append({'role': 'user', 'content': prompt})
     if len(document_section)>0:
         conversation.append({'role': 'assistant', 'content': document_section})
+        
     start_time = time.time()
     st.write('starting at ', start_time)
     report = []
     res_box = st.empty()
+    
     collected_chunks = []
     collected_messages = []
 
     endpoint_url = API_URL
     hf_token = API_KEY
+    
     client = InferenceClient(endpoint_url, token=hf_token)
     gen_kwargs = dict(
         max_new_tokens=512,
@@ -185,8 +188,8 @@ def chat_with_model_llama(prompt, document_section, model_choice='Llama-2-7b-cha
         top_p=0.9,
         temperature=0.2,
         repetition_penalty=1.02,
-        stop_sequences=["\nUser:", "<|endoftext|>", "</s>"],
-    )
+        stop_sequences=["\nUser:", "<|endoftext|>", "</s>"]    )
+    
     stream = client.text_generation(prompt, stream=True, details=True, **gen_kwargs)
     report=[]
     res_box = st.empty()
@@ -218,7 +221,7 @@ def chat_with_model_llama(prompt, document_section, model_choice='Llama-2-7b-cha
   
     
 # Chat and Chat with files
-def chat_with_model(prompt, document_section, model_choice='gpt-3.5-turbo'):
+def chat_with_model2(prompt, document_section, model_choice='gpt-3.5-turbo'):
     model = model_choice
     conversation = [{'role': 'system', 'content': 'You are a python script writer.'}]
     conversation.append({'role': 'user', 'content': prompt})