Update app.py

app.py

@@ -0,0 +1,122 @@
+# importing dependencies
+from dotenv import load_dotenv
+import streamlit as st
+from PyPDF2 import PdfReader
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import faiss
+from langchain.prompts import PromptTemplate
+from langchain.memory import ConversationBufferMemory
+from langchain.chains import ConversationalRetrievalChain
+from langchain.chat_models import ChatOpenAI
+from htmlTemplates import css, bot_template, user_template
+from langchain.embeddings import openai
+from langchain.embeddings.openai import OpenAIEmbeddings
+import os
+
+ 
+from openai import OpenAI
+api_key = os.getenv("OPENAI_API_KEY")
+client = OpenAI(api_key=api_key)
+
+
+# creating custom template to guide llm model
+custom_template ="""<s>[INST]You will start the conversation by greeting the user and introducing yourself as qanoon-bot,\
+stating your availability for legal assistance. Your next step will depend on the user's response.\
+If the user expresses a need for legal assistance in Pakistan, you will ask them to describe their case or problem.\
+After receiving the case or problem details from the user, you will provide the solutions and procedures according to the knowledge base and also give related penal codes and procedures. \
+However, if the user does not require legal assistance in Pakistan, you will immediately thank them and\
+say goodbye, ending the conversation. Remember to base your responses on the user's needs, providing accurate and\
+concise information regarding the Pakistan legal law and rights where applicable. Your interactions should be professional and\
+focused, ensuring the user's queries are addressed efficiently without deviating from the set flows.\
+CHAT HISTORY: {chat_history}
+QUESTION: {question}
+ANSWER:
+</s>[INST]
+"""
+
+CUSTOM_QUESTION_PROMPT = PromptTemplate.from_template(custom_template)
+
+# extracting text from pdf
+def get_pdf_text(docs):
+    text=""
+    for pdf in docs:
+        pdf_reader=PdfReader(pdf)
+        for page in pdf_reader.pages:
+            text+=page.extract_text()
+    return text
+
+# converting text to chunks
+def get_chunks(raw_text):
+    text_splitter=CharacterTextSplitter(separator="\n",
+                                        chunk_size=1000,
+                                        chunk_overlap=200,
+                                        length_function=len)   
+    chunks=text_splitter.split_text(raw_text)
+    return chunks
+
+# using all-MiniLm embeddings model and faiss to get vectorstore
+def get_vectorstore(chunks):
+    embeddings=OpenAIEmbeddings()
+    vectorstore=faiss.FAISS.from_texts(texts=chunks,embedding=embeddings)
+    return vectorstore
+
+# generating conversation chain  
+def get_conversationchain(vectorstore):
+    llm=ChatOpenAI(temperature=0.4,model_name='gpt-4o-mini')
+    memory = ConversationBufferMemory(memory_key='chat_history', 
+                                      return_messages=True,
+                                      output_key='answer') # using conversation buffer memory to hold past information
+    conversation_chain = ConversationalRetrievalChain.from_llm(
+                                llm=llm,
+                                retriever=vectorstore.as_retriever(),
+                                condense_question_prompt=CUSTOM_QUESTION_PROMPT,
+                                memory=memory)
+    return conversation_chain
+
+# generating response from user queries and displaying them accordingly
+def handle_question(question):
+    response=st.session_state.conversation({'question': question})
+    st.session_state.chat_history=response["chat_history"]
+    for i,msg in enumerate(st.session_state.chat_history):
+        if i%2==0:
+            st.write(user_template.replace("{{MSG}}",msg.content,),unsafe_allow_html=True)
+        else:
+            st.write(bot_template.replace("{{MSG}}",msg.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:")
+    question=st.text_input("Ask question from your document:")
+    if question:
+        handle_question(question)
+    with st.sidebar:
+        st.subheader("Your documents")
+        docs=st.file_uploader("Upload your PDF here and click on 'Process'",accept_multiple_files=True)
+        if st.button("Process"):
+            with st.spinner("Processing"):
+                
+                #get the pdf
+                raw_text=get_pdf_text(docs)
+                
+                #get the text chunks
+                text_chunks=get_chunks(raw_text)
+                
+                #create vectorstore
+                vectorstore=get_vectorstore(text_chunks)
+                
+                #create conversation chain
+                st.session_state.conversation=get_conversationchain(vectorstore)
+
+
+if __name__ == '__main__':
+    main()