输入：接收输入提示(x)和之前生成的文本（y<t)，其中(y-t)是模型基于本次问题生成的文本？
检索预测：模型 (M) 预测是否需要检索（Retrieve），基于((x,y<t))。
检索判断：如果 (Retrieve)==是：1.检索相关文本段落：使用(R) 基于((x,y<t))检索相关文本段落(D)。2.相关性预测：模型(M)预测相关性(ISREL)，基于(x)，段落(d)和(y<t) 对每个(d)进行评估。3.支持性和有用性预测：模型(M)预测支持性(ISSUP)和有用性(ISUSE)，基于(x,y<t,d)对每个(d)进行评估。4.排序：基于(ISREL),(ISSUP),和(ISUSE)对(y<t)进行排序。
如果 (Retrieve)==否：1.生成下一个段落：模型(M)基于(x)生成(y_t)。2.有用性预测：模型(M)预测有用性(ISUSE)，基于(x,y_t)进行评估。

from langchain_core.prompts import ChatPromptTemplatefrom langchain_core.pydantic_v1 import BaseModel, Fieldfrom langchain_openai import ChatOpenAI
# Data modelclass GradeDocuments(BaseModel):"""Binary score for relevance check on retrieved documents."""
binary_score: str = Field(description="Documents are relevant to the question, 'yes' or 'no'")
# LLM with function callllm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)structured_llm_grader = llm.with_structured_output(GradeDocuments)
# Promptsystem = """You are a grader assessing relevance of a retrieved document to a user question. \n It does not need to be a stringent test. The goal is to filter out erroneous retrievals. \nIf the document contains keyword(s) or semantic meaning related to the user question, grade it as relevant. \nGive a binary score 'yes' or 'no' score to indicate whether the document is relevant to the question."""
grade_prompt = ChatPromptTemplate.from_messages([("system", system),("human", "Retrieved document: \n\n {document} \n\n User question: {question}"),])
retrieval_grader = grade_prompt | structured_llm_graderquestion = "agent memory"docs = retriever.get_relevant_documents(question)doc_txt = docs[1].page_contentprint(retrieval_grader.invoke({"question": question, "document": doc_txt}))

### Hallucination Grader
# Data modelclass GradeHallucinations(BaseModel):"""Binary score for hallucination present in generation answer."""
binary_score: str = Field(description="Answer is grounded in the facts, 'yes' or 'no'")
# LLM with function callllm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)structured_llm_grader = llm.with_structured_output(GradeHallucinations)
# Promptsystem = """You are a grader assessing whether an LLM generation is grounded in / supported by a set of retrieved facts. \n  Give a binary score 'yes' or 'no'. 'Yes' means that the answer is grounded in / supported by the set of facts."""hallucination_prompt = ChatPromptTemplate.from_messages([("system", system),("human", "Set of facts: \n\n {documents} \n\n LLM generation: {generation}"),])
hallucination_grader = hallucination_prompt | structured_llm_graderhallucination_grader.invoke({"documents": docs, "generation": generation})

### Answer Grader
# Data modelclass GradeAnswer(BaseModel):"""Binary score to assess answer addresses question."""
binary_score: str = Field(description="Answer addresses the question, 'yes' or 'no'")
# LLM with function callllm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)structured_llm_grader = llm.with_structured_output(GradeAnswer)
# Promptsystem = """You are a grader assessing whether an answer addresses / resolves a question \n  Give a binary score 'yes' or 'no'. Yes' means that the answer resolves the question."""answer_prompt = ChatPromptTemplate.from_messages([("system", system),("human", "User question: \n\n {question} \n\n LLM generation: {generation}"),])
answer_grader = answer_prompt | structured_llm_graderanswer_grader.invoke({"question": question, "generation": generation})