Create app.py

app.py

@@ -0,0 +1,167 @@
+from langchain_community.document_loaders import DirectoryLoader
+from langchain_community.document_loaders import PyPDFLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.text_splitter import CharacterTextSplitter
+from langchain_community.vectorstores import FAISS
+from langchain_community.embeddings.huggingface import HuggingFaceEmbeddings
+from langchain.chains import ConversationChain
+from langchain.memory import ConversationBufferMemory
+from langchain.chains import (
+    StuffDocumentsChain, LLMChain, ConversationalRetrievalChain
+)
+from langchain_core.prompts import PromptTemplate
+import streamlit as st
+from PyPDF2 import PdfReader
+
+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">
+    </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>
+'''
+
+def get_pdf_text(pdf_files):
+
+    text = ""
+
+    for pdf_file in pdf_files:
+        reader = PdfReader(pdf_file)
+        for page in reader.pages:
+            text += page.extract_text()
+
+    return text
+
+def get_chunk_text(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_vector_store(text_chunks):
+
+    # For Huggingface Embeddings
+
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2", model_kwargs={
+        'device' : 'cpu'
+    })
+    vectorstore = FAISS.from_texts(texts = text_chunks, embedding = embeddings)
+
+    return vectorstore
+
+
+def get_conversation_chain(vector_store):
+
+    # llm = HuggingFaceHub(repo_id="tiiuae/falcon-40b-instruct", model_kwargs={"temperature":0.5, "max_length":512})
+
+    llm = CTransformers(model='llama-2-7b-chat.ggmlv3.q2_K.bin', # model available here: https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML/tree/main
+                model_type='llama',
+                config={'max_new_tokens': 600,
+                        'context_length':700,
+                        'temperature': 0.01})
+
+    memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)
+
+    conversation_chain = ConversationalRetrievalChain.from_llm(
+        llm = llm,
+        retriever = vector_store.as_retriever(),
+        memory = memory
+    )
+
+    return conversation_chain
+
+def handle_user_input(question):
+
+    response = st.session_state.conversation({'question':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():
+    st.set_page_config(page_title='Chat with Your own 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 Your own PDFs :books:')
+    question = st.text_input("Ask anything to your PDF: ")
+
+    if question:
+        handle_user_input(question)
+
+    with st.sidebar:
+        st.subheader("Upload your Documents Here: ")
+        pdf_files = st.file_uploader("Choose your PDF Files and Press OK", type=['pdf'], accept_multiple_files=True)
+
+        if st.button("OK"):
+            with st.spinner("Processing your PDFs..."):
+
+                # Get PDF Text
+                raw_text = get_pdf_text(pdf_files)
+
+                # Get Text Chunks
+                text_chunks = get_chunk_text(raw_text)
+
+                # Create Vector Store
+
+                vector_store = get_vector_store(text_chunks)
+                st.write("DONE")
+
+                # Create conversation chain
+
+                st.session_state.conversation =  get_conversation_chain(vector_store)
+
+main()