Spaces:
Sleeping
Sleeping
File size: 2,363 Bytes
b50cb28 |
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 |
import os
import streamlit as st
from PyPDF2 import PdfReader
from langchain.chat_models import ChatOpenAI
from langchain.chains.question_answering import load_qa_chain
from langchain.docstore.document import Document
# Streamlit UI for OpenAI API Key
st.title("📄 Chat with PDFs")
st.sidebar.title("Configuration")
# OpenAI API Key input
openai_api_key = st.sidebar.text_input(
"Enter your OpenAI API Key:", type="password"
)
if not openai_api_key:
st.warning("Please enter your OpenAI API Key in the sidebar.")
else:
os.environ["OPENAI_API_KEY"] = openai_api_key
llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
# File upload
uploaded_files = st.file_uploader(
"Upload one or more PDF files",
type="pdf",
accept_multiple_files=True
)
if uploaded_files:
def extract_text_from_pdfs(uploaded_files):
"""Extract text content from uploaded PDF files."""
all_text = ""
for uploaded_file in uploaded_files:
pdf_reader = PdfReader(uploaded_file)
for page in pdf_reader.pages:
all_text += page.extract_text()
return all_text
def split_text_into_documents(text, chunk_size=1000, overlap=200):
"""Split long text into manageable chunks."""
chunks = []
for i in range(0, len(text), chunk_size - overlap):
chunk = text[i:i + chunk_size]
chunks.append(Document(page_content=chunk))
return chunks
st.info("Extracting text from PDFs...")
raw_text = extract_text_from_pdfs(uploaded_files)
st.success("Text extracted successfully!")
# Split text into chunks
st.info("Splitting text into smaller chunks...")
documents = split_text_into_documents(raw_text)
st.success(f"Text split into {len(documents)} chunks.")
# Ask questions
st.subheader("Ask questions about your PDFs:")
question = st.text_input("Enter your question:")
if question:
# Load QA chain
chain = load_qa_chain(llm, chain_type="stuff")
st.info("Fetching the answer...")
# Get the answer
answer = chain.run(input_documents=documents, question=question)
st.success(f"Answer: {answer}")
|