test_00019.py

from dotenv import load_dotenv  # 用于加载环境变量
from langchain.globals import set_debug, set_verbose
import bs4
from dotenv import load_dotenv  # 用于加载环境变量
from langchain import hub
from langchain.globals import set_debug, set_verbose
from langchain_chroma import Chroma
from langchain_community.document_loaders import WebBaseLoader
from langchain_community.tools.tavily_search import TavilySearchResults
from langchain_core.messages import HumanMessage
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough
from langchain_openai import ChatOpenAI, OpenAI, OpenAIEmbeddings
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langgraph.checkpoint.memory import MemorySaver
from langgraph.prebuilt import create_react_agent

set_debug(True)
set_verbose(True)
load_dotenv()  # 加载 .env 文件中的环境变量
import os

from langchain.prompts import FewShotPromptTemplate, PromptTemplate
from langchain_experimental.tabular_synthetic_data.openai import (
    OPENAI_TEMPLATE,
    create_openai_data_generator,
)
from langchain_experimental.tabular_synthetic_data.prompts import (
    SYNTHETIC_FEW_SHOT_PREFIX,
    SYNTHETIC_FEW_SHOT_SUFFIX,
)
from langchain_openai import ChatOpenAI
from pydantic import BaseModel

os.environ["USER_AGENT"] = "myagent"
model = ChatOpenAI(model="gpt-4o-mini")

import bs4
from langchain.chains import create_retrieval_chain
from langchain.chains.combine_documents import create_stuff_documents_chain
from langchain_community.document_loaders import WebBaseLoader
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.vectorstores import InMemoryVectorStore
from langchain_openai import OpenAIEmbeddings
from langchain_text_splitters import RecursiveCharacterTextSplitter

# 1. Load, chunk and index the contents of the blog to create a retriever.

llm = OpenAI(temperature=0.5, model="gpt-4")

# Load, chunk and index the contents of the blog.
loader = WebBaseLoader(
    web_paths=("https://lilianweng.github.io/posts/2023-06-23-agent/",),
    bs_kwargs=dict(
        parse_only=bs4.SoupStrainer(
            class_=("post-content", "post-title", "post-header")
        )
    ),
)
docs = loader.load()

text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
splits = text_splitter.split_documents(docs)
vectorstore = InMemoryVectorStore.from_documents(
    documents=splits, embedding=OpenAIEmbeddings()
)
retriever = vectorstore.as_retriever()


# 2. Incorporate the retriever into a question-answering chain.
system_prompt = (
    "You are an assistant for question-answering tasks. "
    "Use the following pieces of retrieved context to answer "
    "the question. If you don't know the answer, say that you "
    "don't know. Use three sentences maximum and keep the "
    "answer concise."
    "\n\n"
    "{context}"
)

prompt = ChatPromptTemplate.from_messages(
    [
        ("system", system_prompt),
        ("human", "{input}"),
    ]
)

question_answer_chain = create_stuff_documents_chain(model, prompt)
rag_chain = create_retrieval_chain(retriever, question_answer_chain)
response = rag_chain.invoke({"input": "What is Task Decomposition?"})
response["answer"]
vectorstore = Chroma.from_documents(documents=splits, embedding=OpenAIEmbeddings())

# Retrieve and generate using the relevant snippets of the blog.
retriever = vectorstore.as_retriever()
prompt = hub.pull("rlm/rag-prompt")


def format_docs(docs):
    return "\n\n".join(doc.page_content for doc in docs)


rag_chain = (
    {"context": retriever | format_docs, "question": RunnablePassthrough()}
    | prompt
    | llm
    | StrOutputParser()
)

rag_chain.invoke("What is Task Decomposition?")