Update app.py

app.py

@@ -31,8 +31,8 @@ def get_pdf_text(pdf_docs):
 
 def get_text_chunks(text):
     text_splitter = CharacterTextSplitter(separator="\n",
-                                          chunk_size=500,  # 1000
-                                          chunk_overlap=30,  # 200
+                                          chunk_size=1000,  # 1000
+                                          chunk_overlap=200,  # 200
                                           length_function=len
                                           )
     chunks = text_splitter.split_text(text)
@@ -43,13 +43,14 @@ def get_text_chunks(text):
 def get_vectorstore(text_chunks):
     #embeddings = OpenAIEmbeddings()
     embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
-    # embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/paraphrase-multilingual-mpnet-base-v2")
+    #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,
                    temperature=0.1,
                    top_k=30,
@@ -62,10 +63,12 @@ def get_conversation_chain(vectorstore, model_name):
 
     #llm = ChatOpenAI()
     
-    memory = ConversationBufferMemory(memory_key='chat_history', input_key='question', output_key='answer', return_messages=True)
+    memory = ConversationBufferMemory(memory_key='chat_history',
+                                      input_key='question',
+                                      output_key='answer',
+                                      return_messages=True)
     
     conversation_chain = ConversationalRetrievalChain.from_llm(llm=llm,
-                                                               # condense_question_prompt=CONDENSE_QUESTION_PROMPT,
                                                                retriever=vectorstore.as_retriever(),
                                                                memory=memory,
                                                                return_source_documents=True
@@ -75,6 +78,7 @@ def get_conversation_chain(vectorstore, model_name):
 
 
 def handle_userinput(user_question):
+    
     response = st.session_state.conversation({'question': user_question})
 
     st.session_state.chat_history = response['chat_history']
@@ -111,7 +115,7 @@ if "chat_history" not in st.session_state:
     st.session_state.chat_history = None
 
 st.header("Chat with multiple PDFs :books:")
-user_question = st.text_input("Ask a question about your documents:")
+user_question = st.text_input("Ask a question about your documents: ")
 
 if user_question:
     handle_userinput(user_question)