Update app.py

app.py

@@ -8,22 +8,29 @@ llm = Llama.from_pretrained(
 )
 
 basic_prompt = "Below is the context which is your conversation history and the last user question. Write a response according the context and question. ### Context: user: Ответь мне на вопрос о моем здоровье. assistant: Конечно! Какой у Вас вопрос? ### Question: {question} ### Response:"
+input_text = st.text_input('text')
+model_input = basic_prompt.format(question=input_text)
 
-def generate_response(question):
-    model_input = basic_prompt.format(question=input_text)
-    if question:
-        output = llm(
-          model_input, # Prompt
-          max_tokens=32, # Generate up to 32 tokens, set to None to generate up to the end of the context window
-          stop=["<end_of_turn>"],
-          echo=False # Echo the prompt back in the output
-        ) # Generate a completion, can also call create_completion
-        st.write(output["choices"][0]["text"])
-    else:
-        st.write("Please enter a question to get a response.")
+if input_text:
+    # Create an empty placeholder for the output
+    output_placeholder = st.empty()
     
-input_text = st.text_input('Задайте мне медицинский вопрос...')
+    # Initialize an empty string to store the generated text
+    generated_text = ""
+    
+    # Stream the output
+    for token in llm(
+        model_input,
+        max_tokens=32,
+        stop=[""],
+        echo=True,
+        stream=True  # Enable streaming
+    ):
+        # Append the new token to the generated text
+        generated_text += token['choices'][0]['text']
+        
+        # Update the placeholder with the current generated text
+        output_placeholder.write(generated_text)
 
-# Button to trigger response generation
-if st.button('Generate Response'):
-    generate_response(input_text)
+    # After the generation is complete, you can do any final processing if needed
+    st.write("Generation complete!")