app.py

import gradio
import os

from langchain.chains.question_answering import load_qa_chain
from langchain.document_loaders import UnstructuredURLLoader
# from langchain import HuggingFaceHub
from langchain import OpenAI

# os.environ["HUGGINGFACEHUB_API_TOKEN"] = "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"

# llm = HuggingFaceHub(repo_id="declare-lab/flan-alpaca-large", model_kwargs={"temperature":0.1, "max_length":512})

# os.environ["LANGCHAIN_TRACING_V2"] = "true"
# os.environ["LANGCHAIN_ENDPOINT"] = "https://api.smith.langchain.com"
# os.environ["LANGCHAIN_API_KEY"] = "ls__ae9b316f4ee9475b84f66c616344d713"
# os.environ["LANGCHAIN_PROJECT"] = "Sequential-Chain"

os.environ["OPENAI_API_KEY"] = 'sk-siyoMOttFuCrzfdETrRFS7bz140Dk5DUklCIW3UyVTzooiKj'
os.environ['OPENAI_API_BASE'] = 'https://api.chatanywhere.com.cn'

llm=OpenAI(temperature=0.7, model_name="gpt-3.5-turbo", max_tokens=1024)

def main():

    gradio_interface = gradio.Interface(
    fn = my_inference_function,
    inputs = "text",
    outputs = "text")

    gradio_interface.launch()


def my_inference_function(url):
  loader = UnstructuredURLLoader(urls=[url])
  data = loader.load()
  chain = load_qa_chain(llm=llm, chain_type="stuff")
  # response = chain.run(input_documents=data, question="Summarize this article in a paragraph and provide a name and link")
  response = chain.run(input_documents=data, question="Extract or summarize the tool names, introductions, and links in the article. 提取或总结文章中的工具名称、介绍、链接")
  return response

if __name__ == '__main__':
    main()