Update app.py

app.py

@@ -131,47 +131,8 @@ def user_input(user_question, api_key):
 
     #chat history
     update_chat_history(user_question, response["output_text"])
-'''
 
 
-def user_input(user_question, api_key):
-    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001", google_api_key=api_key)
-    new_db = FAISS.load_local("faiss_index", embeddings)
-    docs = new_db.similarity_search(user_question)
-    chain = get_conversational_chain()
-    response_gemini = chain({"input_documents": docs, "question": user_question}, return_only_outputs=True)
-    
-    # Initialize the Hugging Face model and tokenizer
-    model_name_or_path = "Writer/palmyra-small"
-    model = AutoModelForCausalLM.from_pretrained(model_name_or_path)
-    tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
-
-    # Define the prompt template
-    prompt_template = f"""
-    Transform the following response into a more conversational tone without adding new information:
-    
-    Response:
-    {response_gemini["output_text"]}
-    
-    Transformed Response:
-    """
-
-    # Tokenize the prompt
-    inputs = tokenizer(prompt_template, return_tensors="pt", truncation=True,max_length=512)
-
-    # Generate the transformed response using the Hugging Face model
-    outputs = model.generate(**inputs)
-
-    # Decode the generated response
-    transformed_response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-
-    # Display the transformed response
-    st.write("Reply: ", transformed_response)
-
-    # Update chat history
-    update_chat_history(user_question, transformed_response)
-'''
-
 
 
 def main():