北京网站seo优化排名,最便宜的重庆网站建设,婚纱网站怎么做seo,网站建设的实验小结上一篇博客中对Langchain中prompt进行了详细的介绍#xff0c;此篇博客将介绍Langchain中的outparser和memory。当调用大模型生成内容时#xff0c;返回的内容默认是string类型#xff0c;这对于我们获取response中的某些内容信息可能会带来障碍#xff0c;例如返回的内容本… 上一篇博客中对Langchain中prompt进行了详细的介绍此篇博客将介绍Langchain中的outparser和memory。当调用大模型生成内容时返回的内容默认是string类型这对于我们获取response中的某些内容信息可能会带来障碍例如返回的内容本身是json string内容如果能返回json对象的话那么获取response中某个对象的值就更加容易那么如何通过Langchain提供的能力将输出的内容转换成JSON类型呢来看看下面的例子。
import openai
import os
from langchain.prompts import (HumanMessagePromptTemplate, SystemMessagePromptTemplate, ChatPromptTemplate)
from langchain.chat_models import ChatOpenAI
from langchain.output_parsers import ResponseSchema
from langchain.output_parsers import StructuredOutputParseropenai.api_key os.environ.get(OPEN_AI_KEY)customer_review \
This leaf blower is pretty amazing. It has four settings:\
candle blower, gentle breeze, windy city, and tornado. \
It arrived in two days, just in time for my wifes \
anniversary present. \
I think my wife liked it so much she was speechless. \
So far Ive been the only one using it, and Ive been \
using it every other morning to clear the leaves on our lawn. \
Its slightly more expensive than the other leaf blowers \
out there, but I think its worth it for the extra features.review_template \
For the following text, extract the following information:gift: Was the item purchased as a gift for someone else? \
Answer True if yes, False if not or unknown.delivery_days: How many days did it take for the product\
to arrive? If this information is not found, output -1.price_value: Extract any sentences about the value or price,\
and output them as a comma separated Python list.text: {text}human_template_message HumanMessagePromptTemplate.from_template(review_template)
chat_template ChatPromptTemplate.from_messages([human_template_message])
message chat_template.format_messages(textcustomer_review)
chat ChatOpenAI(model_namegpt-3.5-turbo)
response chat(message)
print(response.content) 上面的代码生成的结果如下图所示从一段文本中提取出了giftdelivery_days和price_value.但是因为不是JSON对象所以如果要获取提取出来的某个值是不行的。 如果想输出JSON格式的数据应该如何处理呢首先在prompt增加了{formact_instruction},通过langchain提供的ResponseSchema定义要提取的字段名称描述信息接着通过StructureOutputParser生成parser再调用parser的get_format_instruction方法生成format_instruction.
review_template_2 \
For the following text, extract the following information:gift: Was the item purchased as a gift for someone else? \
Answer True if yes, False if not or unknown.delivery_days: How many days did it take for the product\
to arrive? If this information is not found, output -1.price_value: Extract any sentences about the value or price,\
and output them as a comma separated Python list.text: {text}{format_instructions}
gift_schema ResponseSchema(namegift,descriptionWas the item purchased\as a gift for someone else? \Answer True if yes,\False if not or unknown.)delivery_days_schema ResponseSchema(namedelivery_days,descriptionHow many days\did it take for the product\to arrive? If this \information is not found,\output -1.)price_value_schema ResponseSchema(nameprice_value,descriptionExtract any\sentences about the value or \price, and output them as a \comma separated Python list.)response_schema [gift_schema, delivery_days_schema, price_value_schema]
out_parser StructuredOutputParser.from_response_schemas(response_schema)
format_instruction out_parser.get_format_instructions()
# print(format_instrucation)human_prompt HumanMessagePromptTemplate.from_template(review_template_2)
chat_prompt ChatPromptTemplate.from_messages([human_prompt])
message chat_prompt.format_messages(textcustomer_review, format_instructionsformat_instruction)
chat ChatOpenAI(model_namegpt-3.5-turbo)
response chat(message)
print(type(response.content))
result out_parser.parse(response.content)
print(result)
print(result.get(delivery_days))生成的format_instruction如下所示可以看到实际是一个包含字段名称以及字段类型说明的json对象。 执行完上面的整体代码结果如下图所示可以看到返回的是一个json对象可以单独打印比如delivery_days的值。 以上就是如何让输出的内容是JSON对象的实现说明。 当使用 LangChain 中的储存(Memory)模块时它可以帮助保存和管理历史聊天消息以及构建关于特定实体的知识。这些组件可以跨多轮对话储存信息并允许在对话期间跟踪特定信息和上下文。LangChain 提供了多种储存类型。其中缓冲区储存允许保留最近的聊天消息摘要储存则提供了对整个对话的摘要。实体储存 则允许在多轮对话中保留有关特定实体的信息。这些记忆组件都是模块化的可与其他组件组合使用从而增强机器人的对话管理能力。储存模块可以通过简单的API调用来访问和更新允许开发人员更轻松地实现对话历史记录的管理和维护。接下来主要介绍四种类型的Memory具体如下所示
对话缓存储存 (ConversationBufferMemory对话缓存窗口储存 (ConversationBufferWindowMemory对话令牌缓存储存 (ConversationTokenBufferMemory对话摘要缓存储存 (ConversationSummaryBufferMemory
import openai
import os
from langchain.chains import ConversationChain
from langchain.chat_models import ChatOpenAI
from langchain.memory import ConversationBufferMemory
from langchain.prompts import (SystemMessagePromptTemplate, HumanMessagePromptTemplate, ChatPromptTemplate, ChatMessagePromptTemplate)openai.api_key os.environ.get(OPENAI_API_KEY)model ChatOpenAI(model_namegpt-3.5-turbo)
memory ConversationBufferMemory()
chat ConversationChain(llmmodel, memorymemory, verboseTrue)
chat.predict(inputHI, my name is taoli?)
chat.predict(inputWhat is 11?)
chat.predict(inputwhat is my name?)
print(memory.buffer)
上面的代码使用ConversationBufferMemory来记录整个历史对话打印memory.buffer的值结果如下所示可以看到当第三个问题问AIwhat is my name时AI可以正确回答应为Memory中存入了整个对话History信息。 除了在ConversationChain中增加memory对象对memory赋值外实际也可以对memory对象直接调用save_context()进行赋值input就是human的输入output模拟AI的返回。
memoryTwo ConversationBufferMemory()
memoryTwo.save_context({input: Hi I came from china}, {output: china is beatiful})
memoryTwo.save_context({input: what is your name}, {output: my name is chatbot})
print(memoryTwo.buffer)
print(memoryTwo.load_memory_variables({})) 打印的信息如下图所示buffer中的信息和ConversionChain生成的一样调用load_memory_variables({})方法把整个对话信息连接起来赋值给history变量。 如果把所有的history都记录下来那么每次传入给LLM的文字太多token消耗很大所以langchain还提供了ConversationBufferWindowMemory通过定义窗口大小即K的值来控制记录最新的K轮对话历史信息。memory ConversationBufferWindowMemory(k1)。 如果是有大量的文字描述内容为了节省token以及保证单次对话的token不要超过限制那么还可以使用ConversationSummaryBufferMemory使用方式上和ConversationBufferMemory相同。以上就是对Langchain提供的memory的使用介绍。
