RAG高级优化：检索后处理模块成竹在胸-51CTO.COM

本文我们将介绍在将召回片段送入大模型之前的一些优化手段，它们能帮助大模型更好的理解上下文知识，给出最佳的回答：

Long-text Reorder
Contextual compression
Refine
Emotion Prompt

Long-text Reorder

根据论文 Lost in the Middle: How Language Models Use Long Contexts，的实验表明，大模型更容易记忆开头和结尾的文档，而对中间部分的文档记忆能力不强，因此可以根据召回的文档和query的相关性进行重排序。

图片

核心的代码可以参考langchain的实现：

def _litm_reordering(documents: List[Document]) -> List[Document]:
    """Lost in the middle reorder: the less relevant documents will be at the
    middle of the list and more relevant elements at beginning / end.
    See: https://arxiv.org/abs//2307.03172"""

    documents.reverse()
    reordered_result = []
    for i, value in enumerate(documents):
        if i % 2 == 1:
            reordered_result.append(value)
        else:
            reordered_result.insert(0, value)
    return reordered_result

Contextual compression

本质上利用LLM去判断检索之后的文档和用户query的相关性，只返回相关度最高的k个。

from langchain.retrievers import ContextualCompressionRetriever
from langchain.retrievers.document_compressors import LLMChainExtractor
from langchain_openai import OpenAI
 
llm = OpenAI(temperature=0)
compressor = LLMChainExtractor.from_llm(llm)
compression_retriever = ContextualCompressionRetriever(
    base_compressor=compressor, base_retriever=retriever
)
 
compressed_docs = compression_retriever.get_relevant_documents(
    "What did the president say about Ketanji Jackson Brown"
)
print(compressed_docs)

Refine

对最后大模型生成的回答进行进一步的改写，保证回答的准确性。主要涉及提示词工程，参考的提示词如下：

The original query is as follows: {query_str}
We have provided an existing answer: {existing_answer}
We have the opportunity to refine the existing answer (only if needed) with some more context below.
------------
{context_msg}
------------
Given the new context, refine the original answer to better answer the query. If the context isn't useful, return the original answer.
Refined Answer:

Emotion Prompt

同样是提示词工程的一部分，思路来源于微软的论文：

Large Language Models Understand and Can Be Enhanced by Emotional Stimuli

在论文中，微软研究员提出，在提示词中增加一些情绪情感相关的提示，有助于大模型输出高质量的回答。

参考提示词如下：

emotion_stimuli_dict = {
    "ep01": "Write your answer and give me a confidence score between 0-1 for your answer. ",
    "ep02": "This is very important to my career. ",
    "ep03": "You'd better be sure.",
    # add more from the paper here!!
}
 
# NOTE: ep06 is the combination of ep01, ep02, ep03
emotion_stimuli_dict["ep06"] = (
    emotion_stimuli_dict["ep01"]
    + emotion_stimuli_dict["ep02"]
    + emotion_stimuli_dict["ep03"]
)
 
 
from llama_index.prompts import PromptTemplate
 
 
qa_tmpl_str = """\
Context information is below.
---------------------
{context_str}
---------------------
Given the context information and not prior knowledge, \
answer the query.
{emotion_str}
Query: {query_str}
Answer: \
"""
qa_tmpl = PromptTemplate(qa_tmpl_str)