【AI大模型应用开发】【LangChain系列】实战案例6：利用大模型进行文本总结的方法探索，文本Token超限怎么办？

from langchain.chains.summarize import load_summarize_chain
from langchain_community.document_loaders import WebBaseLoader
from langchain_openai import ChatOpenAI
loader = WebBaseLoader("https://lilianweng.github.io/posts/2023-06-23-agent/")
docs = loader.load()
llm = ChatOpenAI(temperature=0, model_name="gpt-3.5-turbo-1106")
chain = load_summarize_chain(llm, chain_type="stuff")
result = chain.run(docs)
print(result)

from langchain.chains.combine_documents.stuff import StuffDocumentsChain
from langchain.chains.llm import LLMChain
from langchain.prompts import PromptTemplate
# Define prompt
prompt_template = """Write a concise summary of the following:
"{text}"
CONCISE SUMMARY:"""
prompt = PromptTemplate.from_template(prompt_template)
# Define LLM chain
llm = ChatOpenAI(temperature=0, model_name="gpt-3.5-turbo-16k")
llm_chain = LLMChain(llm=llm, prompt=prompt)
# Define StuffDocumentsChain
stuff_chain = StuffDocumentsChain(llm_chain=llm_chain, document_variable_name="text")
docs = loader.load()
print(stuff_chain.run(docs))

prompt_template = """Write a concise summary of the following:
"{text}"
CONCISE SUMMARY:"""

text_splitter = CharacterTextSplitter.from_tiktoken_encoder(
    chunk_size=1000, chunk_overlap=0
)
split_docs = text_splitter.split_documents(docs)

# Map
map_template = """The following is a set of documents
{docs}
Based on this list of docs, please identify the main themes 
Helpful Answer:"""
map_prompt = PromptTemplate.from_template(map_template)
map_chain = LLMChain(llm=llm, prompt=map_prompt)

# Reduce
reduce_template = """The following is set of summaries:
{docs}
Take these and distill it into a final, consolidated summary of the main themes. 
Helpful Answer:"""
reduce_prompt = PromptTemplate.from_template(reduce_template)
# Run chain
reduce_chain = LLMChain(llm=llm, prompt=reduce_prompt, verbose=True)
# Takes a list of documents, combines them into a single string, and passes this to an LLMChain
combine_documents_chain = StuffDocumentsChain(
    llm_chain=reduce_chain, document_variable_name="docs", verbose=True
)
# Combines and iteratively reduces the mapped documents
reduce_documents_chain = ReduceDocumentsChain(
    # This is final chain that is called.
    combine_documents_chain=combine_documents_chain,
    # If documents exceed context for `StuffDocumentsChain`
    collapse_documents_chain=combine_documents_chain,
    # The maximum number of tokens to group documents into.
    token_max=4000,
    verbose=True
)

# Combining documents by mapping a chain over them, then combining results
map_reduce_chain = MapReduceDocumentsChain(
    # Map chain
    llm_chain=map_chain,
    # Reduce chain
    reduce_documents_chain=reduce_documents_chain,
    # The variable name in the llm_chain to put the documents in
    document_variable_name="docs",
    # Return the results of the map steps in the output
    return_intermediate_steps=False,
    verbose=True
)

print(map_reduce_chain.run(split_docs))

def _load_map_reduce_chain(
    llm: BaseLanguageModel,
    map_prompt: BasePromptTemplate = map_reduce_prompt.PROMPT,
    combine_prompt: BasePromptTemplate = map_reduce_prompt.PROMPT,
    combine_document_variable_name: str = "text",
    map_reduce_document_variable_name: str = "text",
    collapse_prompt: Optional[BasePromptTemplate] = None,
    reduce_llm: Optional[BaseLanguageModel] = None,
    collapse_llm: Optional[BaseLanguageModel] = None,
    verbose: Optional[bool] = None,
    token_max: int = 3000,
    callbacks: Callbacks = None,
    *,
    collapse_max_retries: Optional[int] = None,
    **kwargs: Any,
) -> MapReduceDocumentsChain:
    map_chain = LLMChain(
        llm=llm, prompt=map_prompt, verbose=verbose, callbacks=callbacks
    )
    _reduce_llm = reduce_llm or llm
    reduce_chain = LLMChain(
        llm=_reduce_llm, prompt=combine_prompt, verbose=verbose, callbacks=callbacks
    )
    # TODO: document prompt
    combine_documents_chain = StuffDocumentsChain(
        llm_chain=reduce_chain,
        document_variable_name=combine_document_variable_name,
        verbose=verbose,
        callbacks=callbacks,
    )
    if collapse_prompt is None:
        collapse_chain = None
        if collapse_llm is not None:
            raise ValueError(
                "collapse_llm provided, but collapse_prompt was not: please "
                "provide one or stop providing collapse_llm."
            )
    else:
        _collapse_llm = collapse_llm or llm
        collapse_chain = StuffDocumentsChain(
            llm_chain=LLMChain(
                llm=_collapse_llm,
                prompt=collapse_prompt,
                verbose=verbose,
                callbacks=callbacks,
            ),
            document_variable_name=combine_document_variable_name,
        )
    reduce_documents_chain = ReduceDocumentsChain(
        combine_documents_chain=combine_documents_chain,
        collapse_documents_chain=collapse_chain,
        token_max=token_max,
        verbose=verbose,
        callbacks=callbacks,
        collapse_max_retries=collapse_max_retries,
    )
    return MapReduceDocumentsChain(
        llm_chain=map_chain,
        reduce_documents_chain=reduce_documents_chain,
        document_variable_name=map_reduce_document_variable_name,
        verbose=verbose,
        callbacks=callbacks,
        **kwargs,
    )