当前位置：首页 > news >正文

【Basic】【response_synthesizers1】自定义提示词响应合成器案例

news 2026/5/12 17:46:23

本案例演示如何使用LlamaIndex中的自定义提示词和响应合成器，通过TreeSummarize和Refine策略，实现不同风格的文本响应生成。

1. 案例目标

本案例的主要目标是：

演示如何创建自定义提示词模板，用于控制AI响应的风格和格式
展示如何使用TreeSummarize和Refine两种不同的响应合成策略
实现基于Pydantic模型的结构化输出
通过不同风格的提示词参数（如莎士比亚风格、俳句风格等）生成多样化的响应

2. 技术栈与核心依赖

LlamaIndex- 用于文档索引、查询和响应合成
OpenAI API- 提供大语言模型能力
Pydantic- 用于定义结构化数据模型

核心依赖安装

pip install llama-index

3. 环境配置

在开始之前，需要设置OpenAI API密钥：

import os import openai os.environ["OPENAI_API_KEY"] = "sk-..." openai.api_key = os.environ["OPENAI_API_KEY"]

4. 案例实现

4.1 数据准备

首先，下载并加载Paul Graham的文章作为示例数据：

from llama_index.core import SimpleDirectoryReader # 创建目录并下载数据 !mkdir -p 'data/paul_graham/' !wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/examples/data/paul_graham/paul_graham_essay.txt' -O 'data/paul_graham/paul_graham_essay.txt' # 加载数据 reader = SimpleDirectoryReader( input_files=["./data/paul_graham/paul_graham_essay.txt"] ) docs = reader.load_data() text = docs[0].text

4.2 自定义提示词模板

创建自定义的问答提示词和优化提示词模板：

from llama_index.core import PromptTemplate # 问答提示词模板，添加了tone_name变量用于控制风格 qa_prompt_tmpl = ( "Context information is below.\n" "---------------------\n" "{context_str}\n" "---------------------\n" "Given the context information and not prior knowledge, " "answer the query.\n" "Please also write the answer in the style of {tone_name}.\n" "Query: {query_str}\n" "Answer: " ) qa_prompt = PromptTemplate(qa_prompt_tmpl) # 优化提示词模板，用于改进已有答案 refine_prompt_tmpl = ( "The original query is as follows: {query_str}\n" "We have provided an existing answer: {existing_answer}\n" "We have the opportunity to refine the existing answer " "(only if needed) with some more context below.\n" "------------\n" "{context_msg}\n" "------------\n" "Given the new context, refine the original answer to better " "answer the query. " "Please also write the answer in the style of {tone_name}.\n" "If the context isn't useful, return the original answer.\n" "Refined Answer: " ) refine_prompt = PromptTemplate(refine_prompt_tmpl)

4.3 使用TreeSummarize响应合成器

使用TreeSummarize策略生成莎士比亚风格的响应：

from llama_index.core.response_synthesizers import TreeSummarize # 创建TreeSummarize实例，使用自定义提示词 summarizer = TreeSummarize(verbose=True, summary_template=qa_prompt) # 生成响应 response = summarizer.get_response( "who is Paul Graham?", [text], tone_name="a Shakespeare play" ) print(str(response))

4.4 使用Refine响应合成器

使用Refine策略生成俳句风格的响应：

from llama_index.core.response_synthesizers import Refine # 创建Refine实例，使用自定义提示词 summarizer = Refine( verbose=True, text_qa_template=qa_prompt, refine_template=refine_prompt ) # 生成响应 response = summarizer.get_response( "who is Paul Graham?", [text], tone_name="a haiku" ) print(str(response))

4.5 使用Pydantic模型的结构化输出

定义Pydantic模型并生成结构化响应：

from llama_index.core.types import BaseModel from typing import List # 定义Pydantic模型 class Biography(BaseModel): """Data model for a biography.""" name: str best_known_for: List[str] extra_info: str # 创建TreeSummarize实例，指定输出模型 summarizer = TreeSummarize( verbose=True, summary_template=qa_prompt, output_cls=Biography ) # 生成结构化响应 response = summarizer.get_response( "who is Paul Graham?", [text], tone_name="a business memo" ) print(str(response))

5. 案例效果

运行上述代码后，我们可以看到以下效果：

5.1 莎士比亚风格响应

Paul Graham, a noble and esteemed gentleman, is a man of many talents and accomplishments. He hath traversed the realms of art, entrepreneurship, and writing, leaving a lasting impact on each. With his brush, he hath brought life to canvases, capturing the essence of what he saw. In the realm of technology, he hath revolutionized the way we do business, founding Viaweb and bringing the power of the web to entrepreneurs and artists alike. His wisdom and guidance hath shaped the future of technology and entrepreneurship through his co-founding of Y Combinator. But above all, Paul Graham is a visionary, a trailblazer, and a true Renaissance man, whose intellectual curiosity and quest for lasting creation hath inspired generations to come.

5.2 俳句风格响应

Paul Graham, a web pioneer,
Co-founded Y Combinator,
But stepped down to ensure,
Long-term success and more.

5.3 结构化输出

name='Paul Graham' best_known_for=['Co-founder of Y Combinator', 'Writer', 'Investor'] extra_info="Paul Graham is a renowned entrepreneur, writer, and investor. He is best known as the co-founder of Y Combinator, a highly successful startup accelerator. Graham has played a significant role in shaping the startup ecosystem and has been instrumental in the success of numerous startups. He is also a prolific writer, known for his insightful essays on a wide range of topics, including technology, startups, and entrepreneurship. Graham's writings have been widely read and have had a profound impact on the tech community. In addition to his work with Y Combinator and his writing, Graham is also an active investor, providing seed funding and mentorship to early-stage startups. His contributions to the startup world have earned him a reputation as one of the most influential figures in the industry."