Update app.py

app.py

@@ -2,7 +2,7 @@ import streamlit as st
 from dotenv import load_dotenv
 from PyPDF2 import PdfReader
 from langchain.text_splitter import CharacterTextSplitter
-from langchain.embeddings import OpenAIEmbeddings, HuggingFaceInstructEmbeddings
+from langchain.embeddings import OpenAIEmbeddings, HuggingFaceInstructEmbeddings, HuggingFaceEmbeddings
 from langchain.vectorstores import FAISS
 from langchain.chat_models import ChatOpenAI
 from langchain.memory import ConversationBufferMemory
@@ -11,56 +11,63 @@ from htmlTemplates import css, bot_template, user_template
 from langchain.llms import HuggingFaceHub, LlamaCpp
 from huggingface_hub import snapshot_download, hf_hub_download
 
-
 repo_name = "IlyaGusev/saiga2_7b_gguf"
 model_name = "model-q2_K.gguf"
     
 snapshot_download(repo_id=repo_name, local_dir=".", allow_patterns=model_name)
 
 def get_pdf_text(pdf_docs):
+    
     text = ""
     for pdf in pdf_docs:
         pdf_reader = PdfReader(pdf)
         for page in pdf_reader.pages:
             text += page.extract_text()
+            
     return text
 
 
 def get_text_chunks(text):
-    text_splitter = CharacterTextSplitter(
-        separator="\n",
-        chunk_size=1000,
-        chunk_overlap=200,
-        length_function=len
-    )
+    
+    text_splitter = CharacterTextSplitter(separator="\n",
+                                          chunk_size=1000,
+                                          chunk_overlap=200,
+                                          length_function=len
+                                         )
     chunks = text_splitter.split_text(text)
+    
     return chunks
 
 
 def get_vectorstore(text_chunks):
-    embeddings = OpenAIEmbeddings()
-    # embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
+    
+    #embeddings = OpenAIEmbeddings()
+    #embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/paraphrase-multilingual-mpnet-base-v2")
     vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
+    
     return vectorstore
 
 
 def get_conversation_chain(vectorstore, model_name):
 
-    llm = LlamaCpp(model_path=model_name, n_ctx=2048)
+    llm = LlamaCpp(model_path=model_name, n_ctx=2048, n_parts=1)
     #llm = ChatOpenAI()
 
-    memory = ConversationBufferMemory(
-        memory_key='chat_history', return_messages=True)
-    conversation_chain = ConversationalRetrievalChain.from_llm(
-        llm=llm,
-        retriever=vectorstore.as_retriever(),
-        memory=memory
-    )
+    memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)
+    
+    conversation_chain = ConversationalRetrievalChain.from_llm(llm=llm,
+                                                               retriever=vectorstore.as_retriever(),
+                                                               memory=memory
+                                                              )
+    
     return conversation_chain
 
 
 def handle_userinput(user_question):
+    
     response = st.session_state.conversation({'question': user_question})
+    
     st.session_state.chat_history = response['chat_history']
 
     for i, message in enumerate(st.session_state.chat_history):
@@ -71,8 +78,9 @@ def handle_userinput(user_question):
             st.write(bot_template.replace(
                 "{{MSG}}", message.content), unsafe_allow_html=True)
 
-
+# main code
 load_dotenv()
+
 st.set_page_config(page_title="Chat with multiple PDFs",
                    page_icon=":books:")
 st.write(css, unsafe_allow_html=True)
@@ -84,6 +92,7 @@ if "chat_history" not in st.session_state:
 
 st.header("Chat with multiple PDFs :books:")
 user_question = st.text_input("Ask a question about your documents:")
+
 if user_question:
     handle_userinput(user_question)
 
@@ -103,8 +112,4 @@ with st.sidebar:
             vectorstore = get_vectorstore(text_chunks)
 
             # create conversation chain
-            st.session_state.conversation = get_conversation_chain(
-                vectorstore, model_name)
-
-
-
+            st.session_state.conversation = get_conversation_chain(vectorstore, model_name)