Update app.py

app.py

@@ -1,36 +1,104 @@
-import openai
-import langchain
-import datetime
-import os
-from langchain.chains import RetrievalQA
+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.vectorstores import FAISS
 from langchain.chat_models import ChatOpenAI
-from langchain.document_loaders import CSVLoader
-from langchain.vectorstores import DocArrayInMemorySearch
-from IPython.display import display, Markdown
-from langchain.llms import OpenAI
-from langchain_community.document_loaders import Docx2txtLoader
-from langchain_community.document_loaders import UnstructuredWordDocumentLoader
-from langchain.indexes import VectorstoreIndexCreator
-from langchain_community.document_loaders import PyPDFLoader
+from langchain.memory import ConversationBufferMemory
+from langchain.chains import ConversationalRetrievalChain
+from htmlTemplates import css, bot_template, user_template
+from langchain.llms import HuggingFaceHub
 
+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
 
-from dotenv import load_dotenv, find_dotenv
-_ = load_dotenv(find_dotenv()) 
 
+def get_text_chunks(text):
+    text_splitter = CharacterTextSplitter(
+        separator="\n",
+        chunk_size=1000,
+        chunk_overlap=200,
+        length_function=len
+    )
+    chunks = text_splitter.split_text(text)
+    return chunks
 
-# Get the current date
-current_date = datetime.datetime.now().date()
 
-# Define the date after which the model should be set to "gpt-3.5-turbo"
-target_date = datetime.date(2024, 6, 12)
+def get_vectorstore(text_chunks):
+    embeddings = OpenAIEmbeddings()
+    # embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
+    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
+    return vectorstore
 
-# Set the model variable based on the current date
-if current_date > target_date:
-    llm_model = "gpt-3.5-turbo"
-else:
-    llm_model = "gpt-3.5-turbo-0301"
 
-loader = PyPDFLoader("Firm_Data.pdf")
-index = VectorstoreIndexCreator(
-    vectorstore_cls=DocArrayInMemorySearch
-).from_loaders([loader])
+def get_conversation_chain(vectorstore):
+    llm = ChatOpenAI()
+    # llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.5, "max_length":512})
+
+    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):
+        if i % 2 == 0:
+            st.write(user_template.replace(
+                "{{MSG}}", message.content), unsafe_allow_html=True)
+        else:
+            st.write(bot_template.replace(
+                "{{MSG}}", message.content), unsafe_allow_html=True)
+
+
+def main():
+    load_dotenv()
+    st.set_page_config(page_title="Chat with multiple PDFs",
+                       page_icon=":books:")
+    st.write(css, unsafe_allow_html=True)
+
+    if "conversation" not in st.session_state:
+        st.session_state.conversation = None
+    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:")
+    if user_question:
+        handle_userinput(user_question)
+
+    with st.sidebar:
+        st.subheader("Your documents")
+        pdf_docs = st.file_uploader(
+            "Upload your PDFs here and click on 'Process'", accept_multiple_files=True)
+        if st.button("Process"):
+            with st.spinner("Processing"):
+                # get pdf text
+                raw_text = get_pdf_text(pdf_docs)
+
+                # get the text chunks
+                text_chunks = get_text_chunks(raw_text)
+
+                # create vector store
+                vectorstore = get_vectorstore(text_chunks)
+
+                # create conversation chain
+                st.session_state.conversation = get_conversation_chain(
+                    vectorstore)
+
+
+if __name__ == '__main__':
+    main()