{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "with open(\".inner/军事新闻.txt\") as f:\n", " state_of_the_union = f.read()" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "data": { "text/plain": [ ", model_name='text-davinci-003', temperature=0.0, max_tokens=256, top_p=1, frequency_penalty=0, presence_penalty=0, n=1, best_of=1, model_kwargs={}, openai_api_key=None, openai_api_base=None, openai_organization=None, batch_size=20, request_timeout=None, logit_bias={}, max_retries=6, streaming=False, allowed_special=set(), disallowed_special='all'), output_key='text'), combine_document_chain=StuffDocumentsChain(memory=None, callbacks=None, callback_manager=None, verbose=False, input_key='input_documents', output_key='output_text', llm_chain=LLMChain(memory=None, callbacks=None, callback_manager=None, verbose=False, prompt=PromptTemplate(input_variables=['text'], output_parser=None, partial_variables={}, template='对以下内容进行简要总结：\\n\\n\"{text}\"\\n\\n\\n简明摘要:', template_format='f-string', validate_template=True), llm=OpenAI(cache=None, verbose=False, callbacks=None, callback_manager=None, client=, model_name='text-davinci-003', temperature=0.0, max_tokens=256, top_p=1, frequency_penalty=0, presence_penalty=0, n=1, best_of=1, model_kwargs={}, openai_api_key=None, openai_api_base=None, openai_organization=None, batch_size=20, request_timeout=None, logit_bias={}, max_retries=6, streaming=False, allowed_special=set(), disallowed_special='all'), output_key='text'), document_prompt=PromptTemplate(input_variables=['page_content'], output_parser=None, partial_variables={}, template='{page_content}', template_format='f-string', validate_template=True), document_variable_name='text', document_separator='\\n\\n'), collapse_document_chain=None, document_variable_name='text', return_intermediate_steps=False)>" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from langchain import OpenAI\n", "from langchain.chains.summarize import load_summarize_chain\n", "\n", "llm = OpenAI(temperature=0)\n", "summary_chain = load_summarize_chain(llm, chain_type=\"map_reduce\")\n", "summary_chain.dict" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "from langchain.chains import AnalyzeDocumentChain" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "data": { "text/plain": [ ", combine_docs_chain=MapReduceDocumentsChain(memory=None, callbacks=None, callback_manager=None, verbose=False, input_key='input_documents', output_key='output_text', llm_chain=LLMChain(memory=None, callbacks=None, callback_manager=None, verbose=False, prompt=PromptTemplate(input_variables=['text'], output_parser=None, partial_variables={}, template='对以下内容进行简要总结：\\n\\n\"{text}\"\\n\\n\\n简明摘要:', template_format='f-string', validate_template=True), llm=OpenAI(cache=None, verbose=False, callbacks=None, callback_manager=None, client=, model_name='text-davinci-003', temperature=0.0, max_tokens=256, top_p=1, frequency_penalty=0, presence_penalty=0, n=1, best_of=1, model_kwargs={}, openai_api_key=None, openai_api_base=None, openai_organization=None, batch_size=20, request_timeout=None, logit_bias={}, max_retries=6, streaming=False, allowed_special=set(), disallowed_special='all'), output_key='text'), combine_document_chain=StuffDocumentsChain(memory=None, callbacks=None, callback_manager=None, verbose=False, input_key='input_documents', output_key='output_text', llm_chain=LLMChain(memory=None, callbacks=None, callback_manager=None, verbose=False, prompt=PromptTemplate(input_variables=['text'], output_parser=None, partial_variables={}, template='对以下内容进行简要总结：\\n\\n\"{text}\"\\n\\n\\n简明摘要:', template_format='f-string', validate_template=True), llm=OpenAI(cache=None, verbose=False, callbacks=None, callback_manager=None, client=, model_name='text-davinci-003', temperature=0.0, max_tokens=256, top_p=1, frequency_penalty=0, presence_penalty=0, n=1, best_of=1, model_kwargs={}, openai_api_key=None, openai_api_base=None, openai_organization=None, batch_size=20, request_timeout=None, logit_bias={}, max_retries=6, streaming=False, allowed_special=set(), disallowed_special='all'), output_key='text'), document_prompt=PromptTemplate(input_variables=['page_content'], output_parser=None, partial_variables={}, template='{page_content}', template_format='f-string', validate_template=True), document_variable_name='text', document_separator='\\n\\n'), collapse_document_chain=None, document_variable_name='text', return_intermediate_steps=False))>" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "summarize_document_chain = AnalyzeDocumentChain(combine_docs_chain=summary_chain)\n", "summarize_document_chain.dict" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "' 美国陆军日前下令大部分飞行员暂停飞行，以确保飞行员安全，并审查风险批准和风险管理过程。自3月以来，已有12名士兵死于直升机坠毁事故，最近一起事故发生在4月27日，导致3名士兵死亡，另有1人受伤，原因正在调查中。'" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "summarize_document_chain.run(state_of_the_union)" ] } ], "metadata": { "kernelspec": { "display_name": "base", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.10.10" }, "orig_nbformat": 4 }, "nbformat": 4, "nbformat_minor": 2 }