使用 Pinata、OpenAI 和 Streamlit 與您的 PDF 聊天

mkdir chat-with-pdf
cd chat-with-pdf
python3 -m venv venv
source venv/bin/activate
pip install streamlit openai requests PyPDF2

PINATA_API_KEY=<Your Pinata API Key>
PINATA_SECRET_API_KEY=<Your Pinata Secret Key>
OPENAI_API_KEY=<Your OpenAI API Key>

OPENAI_API_KEY=<Your OpenAI API Key>
PINATA_API_KEY=dfc05775d0c8a1743247
PINATA_SECRET_API_KEY=a54a70cd227a85e68615a5682500d73e9a12cd211dfbf5e25179830dc8278efc

import os  # Import the os module to interact with the operating system
import requests  # Import the requests library to make HTTP requests
from dotenv import load_dotenv  # Import load_dotenv to load environment variables from a .env file

# Load environment variables from the .env file
load_dotenv()

# Define the Pinata API URL for pinning files to IPFS
PINATA_API_URL = "https://api.pinata.cloud/pinning/pinFileToIPFS"

# Retrieve Pinata API keys from environment variables
PINATA_API_KEY = os.getenv("PINATA_API_KEY")
PINATA_SECRET_API_KEY = os.getenv("PINATA_SECRET_API_KEY")

def upload_pdf_to_pinata(file_path):
    """
    Uploads a PDF file to Pinata's IPFS service.

    Args:
        file_path (str): The path to the PDF file to be uploaded.

    Returns:
        str: The IPFS hash of the uploaded file if successful, None otherwise.
    """
    # Prepare headers for the API request with the Pinata API keys
    headers = {
        "pinata_api_key": PINATA_API_KEY,
        "pinata_secret_api_key": PINATA_SECRET_API_KEY
    }

    # Open the file in binary read mode
    with open(file_path, 'rb') as file:
        # Send a POST request to Pinata API to upload the file
        response = requests.post(PINATA_API_URL, files={'file': file}, headers=headers)

        # Check if the request was successful (status code 200)
        if response.status_code == 200:
            print("File uploaded successfully")  # Print success message
            # Return the IPFS hash from the response JSON
            return response.json()['IpfsHash']
        else:
            # Print an error message if the upload failed
            print(f"Error: {response.text}")
            return None  # Return None to indicate failure

import os
from openai import OpenAI
from dotenv import load_dotenv

# Load environment variables from .env file
load_dotenv()

# Initialize OpenAI client with the API key
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
client = OpenAI(api_key=OPENAI_API_KEY)

def get_openai_response(text, pdf_text):
    try:
        # Create the chat completion request
        print("User Input:", text)
        print("PDF Content:", pdf_text)  # Optional: for debugging

        # Combine the user's input and PDF content for context
        messages = [
            {"role": "system", "content": "You are a helpful assistant for answering questions about the PDF."},
            {"role": "user", "content": pdf_text},  # Providing the PDF content
            {"role": "user", "content": text}  # Providing the user question or request
        ]

        response = client.chat.completions.create(
            model="gpt-4",  # Use "gpt-4" or "gpt-4o mini" based on your access
            messages=messages,
            max_tokens=100,  # Adjust as necessary
            temperature=0.7  # Adjust to control response creativity
        )

        # Extract the content of the response
        return response.choices[0].message.content  # Corrected access method
    except Exception as e:
        return f"Error: {str(e)}"

import streamlit as st
import os
import time
from pinata_helper import upload_pdf_to_pinata
from openai_helper import get_openai_response
from PyPDF2 import PdfReader
from dotenv import load_dotenv

# Load environment variables
load_dotenv()

st.set_page_config(page_title="Chat with PDFs", layout="centered")

st.title("Chat with PDFs using OpenAI and Pinata")

uploaded_file = st.file_uploader("Upload your PDF", type="pdf")

# Initialize session state for chat history and loading state
if "chat_history" not in st.session_state:
    st.session_state.chat_history = []
if "loading" not in st.session_state:
    st.session_state.loading = False

if uploaded_file is not None:
    # Save the uploaded file temporarily
    file_path = os.path.join("temp", uploaded_file.name)
    with open(file_path, "wb") as f:
        f.write(uploaded_file.getbuffer())

    # Upload PDF to Pinata
    st.write("Uploading PDF to Pinata...")
    pdf_cid = upload_pdf_to_pinata(file_path)

    if pdf_cid:
        st.write(f"File uploaded to IPFS with CID: {pdf_cid}")

        # Extract PDF content
        reader = PdfReader(file_path)
        pdf_text = ""
        for page in reader.pages:
            pdf_text += page.extract_text()

        if pdf_text:
            st.text_area("PDF Content", pdf_text, height=200)

            # Allow user to ask questions about the PDF
            user_input = st.text_input("Ask something about the PDF:", disabled=st.session_state.loading)

            if st.button("Send", disabled=st.session_state.loading):
                if user_input:
                    # Set loading state to True
                    st.session_state.loading = True

                    # Display loading indicator
                    with st.spinner("AI is thinking..."):
                        # Simulate loading with sleep (remove in production)
                        time.sleep(1)  # Simulate network delay
                        # Get AI response
                        response = get_openai_response(user_input, pdf_text)

                    # Update chat history
                    st.session_state.chat_history.append({"user": user_input, "ai": response})

                    # Clear the input box after sending
                    st.session_state.input_text = ""

                    # Reset loading state
                    st.session_state.loading = False

            # Display chat history
            if st.session_state.chat_history:
                for chat in st.session_state.chat_history:
                    st.write(f"**You:** {chat['user']}")
                    st.write(f"**AI:** {chat['ai']}")

                # Auto-scroll to the bottom of the chat
                st.write("<style>div.stChat {overflow-y: auto;}</style>", unsafe_allow_html=True)

                # Add three dots as a loading indicator if still waiting for response
                if st.session_state.loading:
                    st.write("**AI is typing** ...")

        else:
            st.error("Could not extract text from the PDF.")
    else:
        st.error("Failed to upload PDF to Pinata.")

streamlit run app.py