RAG高级优化 检索后处理模块成竹在胸

通过上文的方法​ ​RAG高级优化：一文看尽query的转换之路​ ​，我们召回了一些相关片段，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

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。

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 themiddle of the list and more relevant elements at beginning / end.See:"""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 ContextualCompressionRetrieverfrom langchain.retrievers.document_compressors import LLMChainExtractorfrom langchain_openai import OpenAIllm = 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)

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

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, ep03emotion_stimuli_dict["ep06"] = (emotion_stimuli_dict["ep01"]+ emotion_stimuli_dict["ep02"]+ emotion_stimuli_dict["ep03"])from llama_index.prompts import PromptTemplateqa_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)

原文链接：​ ​​ ​​