Upload 3 files

app.py

@@ -0,0 +1,108 @@
+# 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
+
+
+# creating custom template to guide llm model
+custom_template = """Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question, in its original language.
+Chat History:
+{chat_history}
+Follow Up Input: {question}
+Standalone question:"""
+
+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=0.2,model_name='gpt-4-turbo')
+    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()

htmlTemplates.py

@@ -0,0 +1,45 @@
+css = '''
+<style>
+.chat-message {
+    padding: 1.5rem; border-radius: 0.5rem; margin-bottom: 1rem; display: flex
+}
+.chat-message.user {
+    align: right,
+    background-color: #2b313e
+}
+.chat-message.bot {
+    background-color: #475063
+}
+.chat-message .avatar {
+  width: 20%;
+}
+.chat-message .avatar img {
+  max-width: 78px;
+  max-height: 78px;
+  border-radius: 50%;
+  object-fit: cover;
+}
+.chat-message .message {
+  width: 80%;
+  padding: 0 1.5rem;
+  color: #fff;
+}
+'''
+bot_template = '''
+<div class="chat-message bot">
+    <div class="avatar">
+        <img src="https://cdn-icons-png.flaticon.com/512/6134/6134346.png" style="max-height: 78px; max-width: 78px; border-radius: 50%; object-fit: cover;">
+    </div>
+    <div class="message">{{MSG}}</div>
+</div>
+'''
+
+user_template = '''
+<div class="chat-message user">
+    <div class="message" style="text-align:right">{{MSG}}</div>
+    <div class="avatar">
+        <img src="https://png.pngtree.com/png-vector/20190321/ourmid/pngtree-vector-users-icon-png-image_856952.jpg">
+    </div>    
+    
+</div>
+'''

requirements.txt

@@ -0,0 +1,13 @@
+langchain
+pypdf4
+chromadb
+streamlit
+einops
+langchain-together
+faiss-gpu
+sentence-transformers
+htmltemplate
+PyPDF2==3.0.1
+openai
+tiktoken
+einops