97 高级提示技巧：变量映射与函数映射_given the context information and not prior knowle-优快云博客

本文链接：https://blog.youkuaiyun.com/xycxycooo/article/details/141423035

高级提示技巧：变量映射与函数映射

在处理大型语言模型（LLM）时，优化提示（prompt）是提升输出质量的关键。本文将介绍一些高级提示技巧，包括部分格式化、提示模板变量映射和提示函数映射，帮助你定义更自定义和表达性的提示，重用现有提示，并以更少的代码行数表达某些操作。

前置知识

在深入学习这些高级提示技巧之前，你需要了解以下基础知识：

Python编程：熟悉Python语言及其常用库。
自然语言处理（NLP）：了解基本的NLP概念和技术。
大型语言模型（LLM）：了解LLM的基本工作原理和常见应用。

安装与配置

首先，我们需要安装必要的库，并配置OpenAI API密钥。

%pip install llama-index-llms-openai

from llama_index.core import PromptTemplate
from llama_index.llms.openai import OpenAI

1. 部分格式化（Partial Formatting）

部分格式化（partial_format）允许你部分格式化提示，填充一些变量，同时保留其他变量稍后填充。这是一个方便的功能，这样你就不必在整个格式化过程中维护所有必需的提示变量，可以在它们进来时部分格式化。

这将创建提示模板的副本。

qa_prompt_tmpl_str = """\
Context information is below.
---------------------
{context_str}
---------------------
Given the context information and not prior knowledge, answer the query.
Please write the answer in the style of {tone_name}
Query: {query_str}
Answer: \
"""

prompt_tmpl = PromptTemplate(qa_prompt_tmpl_str)
partial_prompt_tmpl = prompt_tmpl.partial_format(tone_name="Shakespeare")
partial_prompt_tmpl.kwargs

输出：

{'tone_name': 'Shakespeare'}

格式化后的提示：

fmt_prompt = partial_prompt_tmpl.format(
    context_str="In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters",
    query_str="How many params does llama 2 have",
)
print(fmt_prompt)

输出：

Context information is below.
---------------------
In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters
---------------------
Given the context information and not prior knowledge, answer the query.
Please write the answer in the style of Shakespeare
Query: How many params does llama 2 have
Answer:

2. 提示模板变量映射（Prompt Template Variable Mappings）

模板变量映射允许你指定从“预期”提示键（例如，用于响应合成的context_str和query_str）到模板中实际键的映射。这允许你重用现有的字符串模板，而不必烦人地更改模板变量。

# 注意：这里我们使用 `my_context` 和 `my_query` 作为模板变量

qa_prompt_tmpl_str = """\
Context information is below.
---------------------
{my_context}
---------------------
Given the context information and not prior knowledge, answer the query.
Query: {my_query}
Answer: \
"""

template_var_mappings = {"context_str": "my_context", "query_str": "my_query"}

prompt_tmpl = PromptTemplate(
    qa_prompt_tmpl_str, template_var_mappings=template_var_mappings
)
fmt_prompt = prompt_tmpl.format(
    context_str="In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters",
    query_str="How many params does llama 2 have",
)
print(fmt_prompt)

输出：

Context information is below.
---------------------
In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters
---------------------
Given the context information and not prior knowledge, answer the query.
Query: How many params does llama 2 have
Answer:

3. 提示函数映射（Prompt Function Mappings）

你还可以将函数作为模板变量传递，而不是固定值。这允许你根据其他值动态注入某些值，在查询时依赖。

以下是一些基本示例。我们在提示工程指南中展示了更多高级示例（例如，少量示例）。

qa_prompt_tmpl_str = """\
Context information is below.
---------------------
{context_str}
---------------------
Given the context information and not prior knowledge, answer the query.
Query: {query_str}
Answer: \
"""

def format_context_fn(**kwargs):
    # 用项目符号格式化上下文
    context_list = kwargs["context_str"].split("\n\n")
    fmtted_context = "\n\n".join([f"- {c}" for c in context_list])
    return fmtted_context

prompt_tmpl = PromptTemplate(
    qa_prompt_tmpl_str, function_mappings={"context_str": format_context_fn}
)
context_str = """\
In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters.

Our fine-tuned LLMs, called Llama 2-Chat, are optimized for dialogue use cases.

Our models outperform open-source chat models on most benchmarks we tested, and based on our human evaluations for helpfulness and safety, may be a suitable substitute for closed-source models.
"""

fmt_prompt = prompt_tmpl.format(
    context_str=context_str, query_str="How many params does llama 2 have"
)
print(fmt_prompt)

输出：

Context information is below.
---------------------
- In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters.

- Our fine-tuned LLMs, called Llama 2-Chat, are optimized for dialogue use cases.

- Our models outperform open-source chat models on most benchmarks we tested, and based on our human evaluations for helpfulness and safety, may be a suitable substitute for closed-source models.

---------------------
Given the context information and not prior knowledge, answer the query.
Query: How many params does llama 2 have
Answer: