PDF文档智能问答-文字版PDF

时间:2024-04-17 07:36:52

文字版PDF可使用fitz轻松获取PDF文档中的纯文字内容,再使用大模型进行问答(简化版RAG)。
示例Python代码如下:

# -*- coding: utf-8 -*-

import os
import openai
import fitz

###设置代理,本地vpn
os.environ["http_proxy"] = "http://127.0.0.1:7890"
os.environ["https_proxy"] = "http://127.0.0.1:7890"

openai.api_key = "api key" 


def get_pdf_content(pdf_path: str) -> str:
    doc = fitz.open(pdf_path)
    num_pages = doc.page_count
    text_content_list = []
    # 读取PDF的全部文本内容
    for page_index in range(num_pages):
        page = doc.load_page(page_index)
        text = page.get_text()
        text_content_list.append(text)

    # 合并全部页面的文本
    return ''.join(text_content_list)

def get_answer(pdf_content: str, query: str) -> str:
    response = openai.ChatCompletion.create(
        model="gpt-3.5-turbo",
        messages=[
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": f"The full text of PDF file is: {pdf_content}"},
            {"role": "user", "content": query}
        ],
        max_tokens=1000
    )
    answer = response['choices'][0]['message']['content']
    return answer

if __name__ == '__main__':
    # Example usage — make sure to update the PDF path
    pdf_content = get_pdf_content("../data/oppo_n3_flip.pdf")
    queries = [
        "OPPO Find N3 Flip的价格?",
        "蚂蚁集团发布的大模型叫什么?",
        "混元大模型是什么时候发布的?"
    ]

    # 打印所有问题的答案
    for query in queries:
        answer=get_answer(pdf_content=pdf_content, query=query)
        print(f"query:{query},\n RAG answer:{answer}")

结果如下:
在这里插入图片描述