langchain LLMRequestsChain

原文：LLMRequestsChain – LangChain中文网

LLMRequestsChain

使用请求库从URL获取HTML结果，然后使用LLM解析结果

from langchain.llms import OpenAIfrom langchain.chains import LLMRequestsChain, LLMChain

定义使用的提示：

from langchain.prompts import PromptTemplate template = """Between >>> and <<< are the raw search result text from google.Extract the answer to the question '{query}' or say "not found" if the information is not contained.Use the formatExtracted:<answer or "not found">>>> {requests_result} <<<Extracted:""" PROMPT = PromptTemplate(    input_variables=["query", "requests_result"],    template=template,)

实例化LLMRequestsChain：

chain = LLMRequestsChain(llm_chain = LLMChain(llm=OpenAI(temperature=0), prompt=PROMPT))

定义输入：

question = "What are the Three (3) biggest countries, and their respective sizes?"inputs = {    "query": question,    "url": "https://www.google.com/search?q=" + question.replace(" ", "+")}

运行LLMRequestsChain：

chain(inputs)

输出如下：

{'query': 'What are the Three (3) biggest countries, and their respective sizes?', 'url': 'https://www.google.com/search?q=What+are+the+Three+(3)+biggest+countries,+and+their+respective+sizes?', 'output': '俄罗斯(17,098,242平方公里)，加拿大(9,984,670平方公里)，美国(9,826,675平方公里)'}