Spaces:
Runtime error
Runtime error
Upload 3 files
Browse files- app.py +64 -0
- htmlTemplates.py +44 -0
- requirements.txt +14 -0
app.py
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
import streamlit as st
|
3 |
+
from dotenv import load_dotenv
|
4 |
+
from PyPDF2 import PdfReader
|
5 |
+
from langchain.text_splitter import CharacterTextSplitter
|
6 |
+
from langchain.embeddings import OpenAIEmbeddings
|
7 |
+
from langchain.vectorstores import FAISS
|
8 |
+
from langchain.chat_models import ChatOpenAI
|
9 |
+
from langchain.memory import ConversationBufferMemory
|
10 |
+
from langchain.chains import ConversationalRetrievalChain
|
11 |
+
from htmlTemplates import css, bot_template, user_template
|
12 |
+
|
13 |
+
def extract_text_from_pdfs(pdf_docs):
|
14 |
+
text = ""
|
15 |
+
for pdf in pdf_docs:
|
16 |
+
pdf_reader = PdfReader(pdf)
|
17 |
+
for page in pdf_reader.pages:
|
18 |
+
text += page.extract_text()
|
19 |
+
return text
|
20 |
+
|
21 |
+
def split_text_into_chunks(text):
|
22 |
+
text_splitter = CharacterTextSplitter(separator="\n", chunk_size=1000, chunk_overlap=200, length_function=len)
|
23 |
+
return text_splitter.split_text(text)
|
24 |
+
|
25 |
+
def create_vector_store_from_text_chunks(text_chunks):
|
26 |
+
key = os.getenv('OPENAI_KEY')
|
27 |
+
embeddings = OpenAIEmbeddings(openai_api_key=key)
|
28 |
+
return FAISS.from_texts(texts=text_chunks, embedding=embeddings)
|
29 |
+
|
30 |
+
def create_conversation_chain(vectorstore):
|
31 |
+
llm = ChatOpenAI()
|
32 |
+
memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)
|
33 |
+
return ConversationalRetrievalChain.from_llm(llm=llm, retriever=vectorstore.as_retriever(), memory=memory)
|
34 |
+
|
35 |
+
def process_user_input(user_question):
|
36 |
+
response = st.session_state.conversation({'question': user_question})
|
37 |
+
st.session_state.chat_history = response['chat_history']
|
38 |
+
|
39 |
+
for i, message in enumerate(st.session_state.chat_history):
|
40 |
+
template = user_template if i % 2 == 0 else bot_template
|
41 |
+
st.write(template.replace("{{MSG}}", message.content), unsafe_allow_html=True)
|
42 |
+
|
43 |
+
def main():
|
44 |
+
load_dotenv()
|
45 |
+
st.set_page_config(page_title="Chat with multiple PDFs", page_icon=":books:")
|
46 |
+
st.write(css, unsafe_allow_html=True)
|
47 |
+
|
48 |
+
st.header("Chat with multiple PDFs :books:")
|
49 |
+
user_question = st.text_input("Ask a question about your documents:")
|
50 |
+
if user_question:
|
51 |
+
process_user_input(user_question)
|
52 |
+
|
53 |
+
with st.sidebar:
|
54 |
+
st.subheader("Your documents")
|
55 |
+
pdf_docs = st.file_uploader("Upload your PDFs here and click on 'Process'", accept_multiple_files=True)
|
56 |
+
if st.button("Process"):
|
57 |
+
with st.spinner("Processing"):
|
58 |
+
raw_text = extract_text_from_pdfs(pdf_docs)
|
59 |
+
text_chunks = split_text_into_chunks(raw_text)
|
60 |
+
vectorstore = create_vector_store_from_text_chunks(text_chunks)
|
61 |
+
st.session_state.conversation = create_conversation_chain(vectorstore)
|
62 |
+
|
63 |
+
if __name__ == '__main__':
|
64 |
+
main()
|
htmlTemplates.py
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
css = '''
|
2 |
+
<style>
|
3 |
+
.chat-message {
|
4 |
+
padding: 1.5rem; border-radius: 0.5rem; margin-bottom: 1rem; display: flex
|
5 |
+
}
|
6 |
+
.chat-message.user {
|
7 |
+
background-color: #2b313e
|
8 |
+
}
|
9 |
+
.chat-message.bot {
|
10 |
+
background-color: #475063
|
11 |
+
}
|
12 |
+
.chat-message .avatar {
|
13 |
+
width: 20%;
|
14 |
+
}
|
15 |
+
.chat-message .avatar img {
|
16 |
+
max-width: 78px;
|
17 |
+
max-height: 78px;
|
18 |
+
border-radius: 50%;
|
19 |
+
object-fit: cover;
|
20 |
+
}
|
21 |
+
.chat-message .message {
|
22 |
+
width: 80%;
|
23 |
+
padding: 0 1.5rem;
|
24 |
+
color: #fff;
|
25 |
+
}
|
26 |
+
'''
|
27 |
+
|
28 |
+
bot_template = '''
|
29 |
+
<div class="chat-message bot">
|
30 |
+
<div class="avatar">
|
31 |
+
<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;">
|
32 |
+
</div>
|
33 |
+
<div class="message">{{MSG}}</div>
|
34 |
+
</div>
|
35 |
+
'''
|
36 |
+
|
37 |
+
user_template = '''
|
38 |
+
<div class="chat-message user">
|
39 |
+
<div class="avatar">
|
40 |
+
<img src="https://i.ibb.co/rdZC7LZ/Photo-logo-1.png">
|
41 |
+
</div>
|
42 |
+
<div class="message">{{MSG}}</div>
|
43 |
+
</div>
|
44 |
+
'''
|
requirements.txt
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
langchain==0.0.184
|
2 |
+
PyPDF2==3.0.1
|
3 |
+
python-dotenv==1.0.0
|
4 |
+
streamlit==1.18.1
|
5 |
+
openai==0.27.6
|
6 |
+
faiss-cpu==1.7.4
|
7 |
+
tiktoken
|
8 |
+
|
9 |
+
# uncomment to use huggingface llms
|
10 |
+
# huggingface-hub==0.14.1
|
11 |
+
|
12 |
+
# uncomment to use instructor embeddings
|
13 |
+
# InstructorEmbedding==1.0.1
|
14 |
+
# sentence-transformers==2.2.2
|