Upload 4 files

app.py

@@ -0,0 +1,96 @@
+from dotenv import load_dotenv
+import streamlit as st
+from PyPDF2 import PdfReader
+from langchain.text_splitter import CharacterTextSplitter
+from langchain_community.embeddings import HuggingFaceInstructEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain_community.chat_models import ChatOpenAI
+from langchain_community.callbacks.manager import get_openai_callback
+from langchain.memory import ConversationBufferMemory
+from langchain.chains import ConversationalRetrievalChain
+from htmlTemplates import css, user_template, bot_template
+
+
+def get_pdf_text(pdf_docs):
+    """Extract text from multiple uploaded PDF files."""
+    text = ""
+    for pdf in pdf_docs:
+        pdf_reader = PdfReader(pdf)
+        for page in pdf_reader.pages:
+            extracted_text = page.extract_text()
+            if extracted_text:
+                text += extracted_text + "\n"
+    return text
+
+
+def get_text_chunks(text):
+    """Split the extracted text into smaller chunks for vector storage."""
+    text_splitter = CharacterTextSplitter(
+        separator="\n", chunk_size=1000, chunk_overlap=200, length_function=len
+    )
+    return text_splitter.split_text(text)
+
+
+def get_vectorstore(text_chunks):
+    """Convert text chunks into vector embeddings and store them in FAISS."""
+    embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
+    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
+    return vectorstore
+
+
+def get_conversation_chain(vectorstore):
+    """Set up the conversational AI chain using a language model and vector storage."""
+    llm = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0.8)
+
+    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_user_input(user_question):
+    """Process user input and generate a response."""
+    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="📚")
+
+    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 = []
+
+    st.header("📚 Chat with Multiple PDFs")
+
+    user_question = st.text_input("Ask a question about your documents:")
+    if user_question:
+        handle_user_input(user_question)
+
+    with st.sidebar:
+        st.subheader("Upload Your PDFs")
+        pdf_docs = st.file_uploader("Upload PDFs and click Process", accept_multiple_files=True)
+
+        if st.button("Process"):
+            with st.spinner("Processing..."):
+                raw_text = get_pdf_text(pdf_docs)
+                text_chunks = get_text_chunks(raw_text)
+                vectorstore = get_vectorstore(text_chunks)
+                st.session_state.conversation = get_conversation_chain(vectorstore)
+
+
+if __name__ == '__main__':
+    main()

htmlTemplates.py

@@ -0,0 +1,44 @@
+css = '''
+<style>
+.chat-message {
+    padding: 1.5rem; border-radius: 0.5rem; margin-bottom: 1rem; display: flex
+}
+.chat-message.user {
+    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://i.ibb.co/cN0nmSj/Screenshot-2023-05-28-at-02-37-21.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="avatar">
+        <img src="https://i.ibb.co/rdZC7LZ/Photo-logo-1.png">
+    </div>    
+    <div class="message">{{MSG}}</div>
+</div>
+'''

requirements.txt

@@ -0,0 +1,8 @@
+streamlit==1.29.0
+langchain==0.0.353
+PyPDF2==3.0.1
+python-dotenv==1.0.1
+faiss-cpu==1.7.4
+openai==0.28.1
+huggingface_hub==0.20.2
+numpy

test.py

@@ -0,0 +1,110 @@
+from dotenv import load_dotenv
+import streamlit as st
+from PyPDF2 import PdfReader
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.embeddings.huggingface import HuggingFaceInstructEmbeddings
+from langchain.memory import ConversationBufferMemory
+from langchain.chains.conversational_retrieval.base import ConversationalRetrievalChain
+from langchain.vectorstores import faiss
+from langchain.chains.question_answering import load_qa_chain
+from langchain.chat_models.openai import ChatOpenAI
+from langchain.callbacks import get_openai_callback
+from htmlTemplates import css, user_template, bot_template
+from langchain.llms import huggingface_hub
+
+
+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
+    )
+    chunks = text_splitter.split_text(text)
+    return chunks
+
+
+def get_vectorstore(text_chunks):
+    # embeddings = OpenAIEmbeddings()
+    embeddings = HuggingFaceInstructEmbeddings(
+        model_name="hkunlp/instructor-xl")
+    vectorstore = faiss.FAISS.from_texts(
+        texts=text_chunks, embedding=embeddings)
+    return vectorstore
+
+
+def get_conversation_chain(vectorstore):
+    llm = ChatOpenAI()
+    # llm = huggingface_hub.HuggingFaceHub(
+    #     repo_id="google/flan-t5-xxl", model_kwargs={"temperature": 0.8, "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 = []
+    if "chat_history" not in st.session_state:
+        st.session_state.chat_history = []
+    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()