Update app.py

app.py

@@ -26,52 +26,6 @@ def respond(message,
     #make a moslem bot
     messages.append({"role": "user", "content": "I want you to answer strictly based on quran and hadith"})
     messages.append({"role": "assistant", "content": "I'd be happy to help! Please go ahead and provide the sentence you'd like me to analyze. Please specify whether you're referencing a particular verse or hadith (Prophetic tradition) from the Quran or Hadith, or if you're asking me to analyze a general statement."})
-
-    #adding fatwa references
-    '''device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
-    selected_references = torch.load('selected_references.sav', map_location=torch.device(device))
-    encoded_questions = torch.load('encoded_questions.sav', map_location=torch.device(device))
-    
-    task = 'Given a web search query, retrieve relevant passages that answer the query'
-    queries = [
-        get_detailed_instruct(task, message)
-    ]
-    print("start\n")
-    print(time.time())
-
-    query_embeddings = model.encode(queries, convert_to_tensor=True, normalize_embeddings=True)
-    scores = (query_embeddings @ encoded_questions.T) * 100
-    selected_references['similarity'] = scores.tolist()[0]
-    sorted_references = selected_references.sort_values(by='similarity', ascending=False)
-    sorted_references = sorted_references.iloc[:1]
-    sorted_references = sorted_references.sort_values(by='similarity', ascending=True)
-    print(sorted_references.shape[0])
-    print(sorted_references['similarity'].tolist())
-    print("sorted references\n")
-    print(time.time())
-
-    from googletrans import Translator
-    translator = Translator()
-    
-    for index, row in sorted_references.iterrows():
-        if(type(row["user"]) is str and type(row['assistant']) is str):
-            try:
-                translator = Translator()
-                print(index)
-                print(f'{row["user"]}')
-                translated = translator.translate(f'{row["user"]}', src='ar', dest='en')
-                print(translated)
-                user = translated.text
-                print(user)
-                assistant = translator.translate(row['assistant']).text
-                messages.append({"role": "user", "content":user })
-                messages.append({"role": "assistant", "content": assistant})
-            except Exception as error:
-                print("An error occurred:", error)
-                print("adding fatwa references exception occurred")
-    
-    print("append references\n")
-    print(time.time())'''
     
     #adding more references
     df = pd.read_csv("moslem-bot-reference.csv", sep='|')
@@ -112,12 +66,24 @@ def respond(message,
         print("An error occurred:", error)
         print("en_message exception occurred")
     
+    
     print(messages)
     print("added last question\n")
     print(time.time())
 
     response = ""
+    for message in client.chat_completion(
+        messages,
+        max_tokens=max_tokens,
+        stream=True,
+        temperature=temperature,
+        top_p=top_p,
+    ):
+        token = message.choices[0].delta.content
 
+        response += token
+        yield response
+    """
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
@@ -151,7 +117,7 @@ def respond(message,
         except Exception as error:
             print("An error occurred:", error)
             yield response
-    
+    """
 demo = gr.Interface(
     fn=respond,
     additional_inputs=[