Duplicate from Graceliying/pdf_chat

Co-authored-by: Grace Li <Graceliying@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+Toastmasters-CC-Manual.pdf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Pdf Chat
+emoji: 📉
+colorFrom: purple
+colorTo: red
+sdk: streamlit
+sdk_version: 1.21.0
+app_file: app.py
+pinned: false
+duplicated_from: Graceliying/pdf_chat
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

Toastmasters-CC-Manual.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec9fdec57c22ead344bac5319e0097990f20df8660285b75256c81427817ace8
+size 5989158

app.py

@@ -0,0 +1,120 @@
+import streamlit as st
+import openai
+import os
+from dotenv import load_dotenv
+from PyPDF2 import PdfReader
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.embeddings import OpenAIEmbeddings, HuggingFaceInstructEmbeddings
+from langchain.vectorstores import FAISS
+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 PIL import Image
+
+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
+
+# documentation for CharacterTextSplitter:
+# https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/character_text_splitter.html
+def get_text_chunk(text):
+    text_splitter = CharacterTextSplitter(
+        separator="\n",
+        chunk_size = 1000,
+        chunk_overlap = 200,
+        length_function = len
+    )
+    chunks = text_splitter.split_text(text)
+    return chunks
+
+#embedding using openAI embedding. Warn: This will cost you money
+def get_vectorstore_openAI(text_chunks):
+    embeddings = OpenAIEmbeddings()
+    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
+    return vectorstore
+
+#embedding using instructor-xl with your local machine for free
+#you can find more details at: https://huggingface.co/hkunlp/instructor-xl
+def get_vectorstore(text_chunks):
+    embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
+    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
+    return vectorstore
+
+def get_conversation_chain(vectorstore):
+    llm = ChatOpenAI()
+    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 openai api_key from .evn
+    load_dotenv()
+    #openai.api_key = os.getenv("OPENAI_API_KEY")
+    
+    ##############################################################################
+    #set up basic page
+    st.set_page_config(page_title="Chat With multiple PDFs", page_icon=":books:")
+    st.write(css, unsafe_allow_html=True)
+
+    #initial session_state in order to avoid refresh
+    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 based on PDF you provided :books:")
+    user_question = st.text_input("Ask a question about your documents:")
+
+    if user_question:
+        handle_userinput(user_question)
+
+# Define the templates
+
+    with st.sidebar:
+        st.subheader("Your PDF documents")
+        pdf_docs = st.file_uploader("Upload your pdfs here and click on 'Proces'", accept_multiple_files= True)
+        #if the button is pressed
+        if st.button("Process"):
+            with st.spinner("Processing"):
+                #get pdf text
+                raw_text = get_pdf_text(pdf_docs)
+                print('raw_text is created')
+
+                #get the text chunks
+                text_chunks = get_text_chunk(raw_text)
+                print('text_chunks are generated')
+
+                #create vector store
+                vectorstore = get_vectorstore_openAI(text_chunks)
+                print('vectorstore is created')
+
+                #create converstion chain
+                st.session_state.conversation = get_conversation_chain(vectorstore)
+                print('conversation chain created')
+    
+
+
+
+# to run this application, you need to run "streamlit run app.py"
+if __name__ == '__main__':
+    main()

htmlTemplates.py

@@ -0,0 +1,55 @@
+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">
+        <svg xmlns="http://www.w3.org/2000/svg" width="256" height="256" viewBox="0 0 32 32"
+            style="max-height: 50px; max-width: 50px; border-radius: 50%; object-fit: cover;">
+        <g fill="white"><path d="M13.472 26h5.056C19.34 26 20 25.326 20 24.5s-.66-1.5-1.472-1.5h-5.056C12.66 23 12 23.674 12 24.5s.66 1.5 1.472 1.5ZM10.5 10a4.5 4.5 0 1 0 0 9h11a4.5 4.5 0 1 0 0-9h-11Zm.75 2c.69 0 1.25.56 1.25 1.25v2.5a1.25 1.25 0 1 1-2.5 0v-2.5c0-.69.56-1.25 1.25-1.25Zm8.25 1.25a1.25 1.25 0 1 1 2.5 0v2.5a1.25 1.25 0 1 1-2.5 0v-2.5Z"/><path d="M4 4.915a1.5 1.5 0 1 0-1 0v7.355a2 2 0 0 0-1 1.728v7.004c0 .736.403 1.382 1 1.729v1.319A6.945 6.945 0 0 0 9.95 31h12.1A6.943 6.943 0 0 0 29 24.06v-1.39c.597-.347 1-.994 1-1.73v-7.01c0-.736-.403-1.383-1-1.73V5.018a1.55 1.55 0 1 0-1 0v3.396A7.017 7.017 0 0 0 21.98 5h-1.065A1.5 1.5 0 0 0 19.5 3h-7a1.5 1.5 0 0 0-1.415 2H10.03C7.47 5 5.23 6.369 4 8.414v-3.5Zm1 7.115A5.03 5.03 0 0 1 10.03 7h11.95A5.028 5.028 0 0 1 27 12.03v12.03A4.943 4.943 0 0 1 22.05 29H9.95A4.945 4.945 0 0 1 5 24.05V12.03Z"/></g></svg>
+    </div>
+    <div class="message">{{MSG}}</div>
+</div>
+'''
+
+user_template = '''
+<div class="chat-message user">
+    <div class="avatar">
+        <svg 
+            xmlns="http://www.w3.org/2000/svg" 
+            width="256" 
+            height="256" 
+            viewBox="0 0 256 256"
+            style="max-height: 50px; max-width: 50px; border-radius: 50%; object-fit: cover;">
+            <path fill="white" d="M168 96H88a40 40 0 0 0-40 40v8a40 40 0 0 0 40 40h80a40 40 0 0 0 40-40v-8a40 40 0 0 0-40-40Zm24 48a24 24 0 0 1-24 24H88a24 24 0 0 1-24-24v-8a24 24 0 0 1 24-24h80a24 24 0 0 1 24 24Zm16-112a32.06 32.06 0 0 0-31 24H79a32 32 0 0 0-63 8v80a72.08 72.08 0 0 0 72 72h80a72.08 72.08 0 0 0 72-72V64a32 32 0 0 0-32-32Zm16 112a56.06 56.06 0 0 1-56 56H88a56.06 56.06 0 0 1-56-56V64a16 16 0 0 1 32 0a8 8 0 0 0 8 8h112a8 8 0 0 0 8-8a16 16 0 0 1 32 0Zm-120-4a12 12 0 1 1-12-12a12 12 0 0 1 12 12Zm72 0a12 12 0 1 1-12-12a12 12 0 0 1 12 12Z"/>
+            </svg>
+Download SVG
+    </div>    
+    <div class="message">{{MSG}}</div>
+</div>
+'''

requirements.txt

@@ -0,0 +1,10 @@
+streamlit==1.23.1
+PyPDF2==3.0.1
+langchain==0.0.197
+openai==0.27.8
+python-dotenv==1.0.0
+faiss-cpu==1.7.4
+huggingface-hub==0.15.1
+InstructorEmbedding==1.0.1
+sentence-transformers==2.2.2
+tiktoken==0.4.0