-
Notifications
You must be signed in to change notification settings - Fork 0
/
chatapplication.py
125 lines (98 loc) · 4.38 KB
/
chatapplication.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
import streamlit as st
from dotenv import load_dotenv
from PyPDF2 import PdfReader
from langchain.text_splitter import CharacterTextSplitter
from langchain_openai import OpenAIEmbeddings
from langchain_openai import ChatOpenAI
from langchain_community.vectorstores import FAISS
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from langchain_core.messages import AIMessage, HumanMessage
from htmlTemplates import css, bot_template, user_template
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()
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
#============================================================================================================
if "chat_history" not in st.session_state:
st.session_state.chat_history = [
AIMessage(content="Hello, I am a bot. How can I help you?")
]
def main():
load_dotenv()
st.set_page_config(
page_title="Chat with multiple PDFs",
page_icon=":sparkles:"
)
st.write(css, unsafe_allow_html=True)
st.header("Chat with single or multiple PDFs :sparkles:")
for message in st.session_state.chat_history:
if isinstance(message, AIMessage):
with st.chat_message("AI"):
st.write(bot_template.replace("{{MSG}}", message.content), unsafe_allow_html=True)
elif isinstance(message, HumanMessage):
with st.chat_message("Human"):
st.write(user_template.replace("{{MSG}}", message.content), unsafe_allow_html=True)
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)
# Let the user know its successful
st.session_state.isPdfProcessed = "done"
st.success("Done!")
if "isPdfProcessed" in st.session_state:
user_question = st.chat_input("Ask a question about your document(s):")
if user_question is not None and user_question != "":
st.session_state.chat_history.append(HumanMessage(content=user_question))
with st.chat_message("Human"):
st.write(user_template.replace("{{MSG}}", user_question), unsafe_allow_html=True)
with st.chat_message("AI"):
with st.spinner("Fetching data ..."):
response = st.session_state.conversation.invoke({'question': user_question})
answer = response["answer"]
formatted_response = answer.replace("\n", "<br />")
st.write(bot_template.replace("{{MSG}}", formatted_response), unsafe_allow_html=True)
st.session_state.chat_history.append(AIMessage(content=formatted_response))
#============================================================================================================
if __name__ == '__main__':
main()