Spaces:
Runtime error
Runtime error
File size: 3,920 Bytes
d64a8e1 |
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 |
import streamlit as st
from dotenv import load_dotenv
import pickle
from PyPDF2 import PdfReader
from streamlit_extras.add_vertical_space import add_vertical_space
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import FAISS
from langchain.llms import OpenAI
from langchain.chains.question_answering import load_qa_chain
from langchain.callbacks import get_openai_callback
import os
with st.sidebar:
st.title('PDF Chat App')
st.markdown('''
## About
This app is an LLM-powered PDF chatbot built using:
- [Streamlit](https://streamlit.io/)
- [LangChain](https://python.langchain.com/)
- [OpenAI](https://platform.openai.com/docs/models) LLM model
## How it works
- Load up a PDF file
- Extract the text from the PDF file
- Split the text into chunks
- Create embeddings using OpenAI, which are vectors of floating-point numbers that measure the relatedness of text strings
- Save these embeddings as vectors in a vector store, such as FAISS
- Use a similarity search to ask a question
- Get the answer and tokens used from OpenAI
''')
st.write('Made with 🤖 by [Cazimir Roman](https://cazimir.dev)')
def load_app():
# upload a PDF file
pdf = st.file_uploader("Upload your PDF", type='pdf')
if pdf is not None:
pdf_reader = PdfReader(pdf)
text = ""
for page in pdf_reader.pages:
text += page.extract_text()
text_splitter = RecursiveCharacterTextSplitter(
chunk_size = 1000,
chunk_overlap=200,
length_function=len
)
chunks = text_splitter.split_text(text=text)
store_name = pdf.name[:-4]
# check if vector store exists. if not, create one
if os.path.exists(f"{store_name}.pkl"):
with open(f"{store_name}.pkl", "rb") as f:
vectorStore = pickle.load(f)
st.success('Text embeddings loaded from disk')
else:
with st.spinner("Creating vector store embeddings..."):
embeddings = OpenAIEmbeddings()
vectorStore = FAISS.from_texts(chunks, embeddings)
with open(f"{store_name}.pkl", "wb") as f:
pickle.dump(vectorStore, f)
st.success('Embeddings computation completed')
# Accept user question/query
st.divider()
query = st.text_input("Ask a question about your PDF file")
if query:
st.write(f"You asked: {query}")
with st.spinner("Thinking..."):
# top 3 that are most similar to our query
docs = vectorStore.similarity_search(query)
llm = OpenAI(temperature=0)
chain = load_qa_chain(llm=llm, chain_type="stuff")
with get_openai_callback() as cb:
response = chain.run(input_documents=docs, question=query)
st.write(response)
def main():
print("Main called")
st.header("Chat with your PDF")
container = st.container()
with container:
open_ai_key = os.getenv("OPENAI_API_KEY")
api_key = container.text_input("Enter your OpenAI API key", type="password", value="" if open_ai_key == None else open_ai_key)
# You can find it here: https://platform.openai.com/account/api-keys
submit = container.button("Submit")
if open_ai_key:
load_app()
# submit button is pressed
if submit:
# check if api key length correct
if len(api_key) == 51:
os.environ["OPENAI_API_KEY"] = api_key
load_app()
else:
st.error("Api key is not correct")
if __name__ == '__main__':
main() |