Spaces:
Sleeping
Sleeping
File size: 2,146 Bytes
69afeb9 f52dcd5 36ae953 69afeb9 878a75a 69afeb9 878a75a 69afeb9 f52dcd5 69afeb9 f52dcd5 69afeb9 f52dcd5 69afeb9 f52dcd5 69afeb9 878a75a 69afeb9 f52dcd5 69afeb9 f52dcd5 69afeb9 0171304 |
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 |
import os
import streamlit as st
import fitz # PyMuPDF
import openai
from dotenv import load_dotenv
from pinecone import Pinecone, ServerlessSpec
# Load the environment variables from the .env file
load_dotenv()
openai_api_key = os.getenv('OPENAI_API_KEY')
pinecone_api_key = os.getenv('PINECONE_API_KEY')
pinecone_environment = os.getenv('PINECONE_ENVIRONMENT')
# Initialize Pinecone
pc = Pinecone(api_key=pinecone_api_key)
# Streamlit app
st.title("Chat with Your Document")
st.write("Upload a PDF file to chat with its content using Pinecone and OpenAI.")
# File upload
uploaded_file = st.file_uploader("Choose a PDF file", type="pdf")
if uploaded_file is not None:
# Load the PDF file
pdf_document = fitz.open(stream=uploaded_file.read(), filetype="pdf")
pdf_text = ""
for page_num in range(pdf_document.page_count):
page = pdf_document.load_page(page_num)
pdf_text += page.get_text()
# Initialize OpenAI embeddings
openai.api_key = openai_api_key
# Create a Pinecone vector store
index_name = "pdf-analysis"
if index_name not in pc.list_indexes().names():
pc.create_index(
name=index_name,
dimension=512,
metric='euclidean',
spec=ServerlessSpec(cloud='aws', region=pinecone_environment)
)
vector_store = pc.Index(index_name)
# Add the PDF text to the vector store
vector_store.upsert([(str(i), openai.Embedding.create(input=pdf_text)["data"][0]["embedding"]) for i in range(len(pdf_text))])
# Chat with the document
user_input = st.text_input("Ask a question about the document:")
if st.button("Ask"):
if user_input:
response = openai.Completion.create(
engine="davinci",
prompt=f"Analyze the following text and answer the question: {pdf_text}\n\nQuestion: {user_input}",
max_tokens=150
)
st.write(response.choices[0].text.strip())
else:
st.write("Please enter a question to ask.")
# Display the PDF text
st.write("Extracted Text from PDF:")
st.write(pdf_text)
# |