Update app.py

app.py

@@ -1,3 +1,4 @@
+from transformers import AutoModel
 import streamlit as st
 import tempfile
 from langchain.text_splitter import RecursiveCharacterTextSplitter
@@ -11,7 +12,6 @@ from langchain.llms import LlamaCpp
 from langchain.prompts import PromptTemplate
 import os
 import pandas as pd
-from transformers import AutoModel
 
 
 prompt_template_questions = """
@@ -96,21 +96,20 @@ if file_path:
     verbose=True,
     n_ctx=4096
     )
-    model = AutoModel.from_pretrained("TheBloke/zephyr-7B-beta-GGUF")
       # Initialize question generation chain
     question_gen_chain = load_summarize_chain(llm=llm_question_gen, chain_type="refine", verbose=True,
                                               question_prompt=PROMPT_QUESTIONS, refine_prompt=REFINE_PROMPT_QUESTIONS)
     # Run question generation chain
     questions = question_gen_chain.run(docs_question_gen)
 
-    # Initialize Large Language Model for answer generation
-    llm_answer_gen = LlamaCpp(
+    llm_question_gen = LlamaCpp(
     streaming = True,
     model_path = AutoModel.from_pretrained("TheBloke/zephyr-7B-beta-GGUF"),
     temperature=0.75,
     top_p=1, 
     verbose=True,
-    n_ctx=4096)
+    n_ctx=4096
+    )
 
      # Create vector database for answer generation
     embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2", model_kwargs={"device": "cpu"})
@@ -154,3 +153,25 @@ if file_path:
 if file_path:
     os.remove(file_path)
 
+
+
+    
+    # Initialize Large Language Model for question generation
+    llm_question_gen = LlamaCpp(
+    streaming = True,
+    model_path = AutoModel.from_pretrained("TheBloke/zephyr-7B-beta-GGUF"),
+    temperature=0.75,
+    top_p=1, 
+    verbose=True,
+    n_ctx=4096
+    )
+   
+    # Initialize Large Language Model for answer generation
+    llm_answer_gen = LlamaCpp(
+    streaming = True,
+    model_path = AutoModel.from_pretrained("TheBloke/zephyr-7B-beta-GGUF"),
+    temperature=0.75,
+    top_p=1, 
+    verbose=True,
+    n_ctx=4096)
+