initiate the space

.gitignore

@@ -0,0 +1,42 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+dist/
+build/
+*.egg-info/
+*.egg
+
+# Virtual environments
+venv/
+env/
+.env
+
+# IDE specific files
+.idea/
+.vscode/
+
+# Jupyter Notebook specific files
+.ipynb_checkpoints/
+
+# Compiled Python files
+*.pyc
+
+# Logs and temporary files
+*.log
+*.bak
+*.swp
+*.tmp
+
+# Coverage reports
+htmlcov/
+.coverage
+
+# Dependency directories
+lib/
+lib64/

README.md

@@ -1,12 +1,13 @@
----
-title: Pdf Buddy
-emoji: 📉
-colorFrom: blue
-colorTo: purple
-sdk: streamlit
-sdk_version: 1.21.0
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Langchain Demo - PDF Text Chatbot
+
+This repository contains a pet demo showcasing the use of Langchain, Hugging Face's Embedding & LLM, to build a chatbot for PDF documents. It is customized from [original repository](https://github.com/alejandro-ao/ask-multiple-pdfs). The chatbot is deployed as a Streamlit web application on Hugging Face Spaces using GitHub Actions.
+
+## Overview
+
+The Langchain Demo allows you to extract text content from PDF documents and interact with them using a chatbot interface. The main steps involved in the process are as follows:
+
+1. **Extract PDF Text Content**: The demo extracts the text content from PDF documents.
+
+2. **Text Chunking and Embedding**: The extracted text is broken down into smaller chunks and processed using a powerful Hugging Face instruction-finetuned text embedding model and saved in a vector database.
+
+3. **Response Generation**: The selected chunks are then passed to a language model provided by Hugging Face. Conversational retrieval by leveraging the LLM for generating responses, the vector store for efficient similarity-based retrieval, and the conversation buffer memory to maintain the context of the conversation history.

app.py

@@ -0,0 +1,120 @@
+import streamlit as st
+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.memory import ConversationBufferMemory
+from langchain.chains import ConversationalRetrievalChain
+from htmlTemplates import css, bot_template, user_template
+from langchain.llms import HuggingFaceHub
+import os
+from dotenv import load_dotenv
+
+
+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()
+    print("HAHA")
+    model_name = "hkunlp/instructor-xl"
+    model_kwargs = {'device': 'cpu'}
+    embeddings  = HuggingFaceInstructEmbeddings(
+                model_name=model_name, model_kwargs=model_kwargs)
+    print("HAHA")
+    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
+    return vectorstore
+
+
+def get_conversation_chain(vectorstore):
+    # llm = ChatOpenAI()
+    llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.5, "max_length":218})
+
+    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="PDF Buddy", page_icon=":coffee:")
+    st.markdown(
+        """
+        <style>
+        body {
+            background-color: #fce6ef;
+        }
+        </style>
+        """,
+        unsafe_allow_html=True
+    )
+    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("PDF Buddy :coffee:")
+    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()

htmlTemplates.py

@@ -0,0 +1,57 @@
+css = '''
+<style>
+body {
+    background-color: #fce6ef;
+}
+
+.chat-message {
+    padding: 1.5rem;
+    border-radius: 0.5rem;
+    margin-bottom: 1rem;
+    display: flex;
+}
+
+.chat-message.user {
+    background-color: #fdeff2;
+}
+
+.chat-message.bot {
+    background-color: #fba5c0;
+}
+
+.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;
+}
+</style>
+'''
+
+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 +1,15 @@
+langchain
+PyPDF2
+python-dotenv
+streamlit
+openai
+faiss-cpu
+altair
+tiktoken
+
+# use huggingface llms
+huggingface-hub
+
+# Use instructor embeddings
+InstructorEmbedding
+sentence-transformers