免费个人网址,seo搜索引擎优化总结报告,做游戏网站思想步骤,可以做视频的一个网站概述
本文是结合 github#xff1a;OpenAI Function Calling 101在 Azure OpenAI 上的实现#xff1a;
Github Function Calling 101
如何将函数调用与 Azure OpenAI 服务配合使用 - Azure OpenAI Service
使用像ChatGPT这样的llm的困难之一是它们不产生结构化的数据输出…概述
本文是结合 githubOpenAI Function Calling 101在 Azure OpenAI 上的实现
Github Function Calling 101
如何将函数调用与 Azure OpenAI 服务配合使用 - Azure OpenAI Service
使用像ChatGPT这样的llm的困难之一是它们不产生结构化的数据输出。这对于在很大程度上依赖结构化数据进行系统交互的程序化系统非常重要。例如如果你想构建一个程序来分析电影评论的情绪你可能必须执行如下提示:
prompt f
Please perform a sentiment analysis on the following movie review:
{MOVIE_REVIEW_TEXT}
Please output your response as a single word: either Positive or Negative. Do not add any extra characters.这样做的问题是它并不总是有效。法学硕士学位通常会加上一个不受欢迎的段落或更长的解释比如:“这部电影的情感是:积极的。”
prompt fPlease perform a sentiment analysis on the following movie review:{The Shawshank Redemption}Please output your response as a single word: either Positive or Negative. Do not add any extra characters.
---
#OpenAI Answer
import nltk
from nltk.sentiment import SentimentIntensityAnalyzer# Define the movie review
movie_review The Shawshank Redemption# Perform sentiment analysis
sid SentimentIntensityAnalyzer()
sentiment_scores sid.polarity_scores(movie_review)# Determine the sentiment based on the compound score
if sentiment_scores[compound] 0:sentiment Positive
else:sentiment Negative# Output the sentiment
sentiment
---
The sentiment analysis of the movie review The Shawshank Redemption is Positive.虽然您可以通过正则表达式得到答案()但这显然不是理想的。理想的情况是LLM将返回类似以下结构化JSON的输出:
{sentiment: positive
}进入OpenAI的新函数调用! 函数调用正是上述问题的答案。 本Jupyter笔记本将演示如何在Python中使用OpenAI的新函数调用的简单示例。如果你想看完整的文档请点击这个链接https://platform.openai.com/docs/guides/gpt/function-calling
实验
初始化配置
安装openai Python客户端已经安装的需要升级它以获得新的函数调用功能
pip3 install openai
pip3 install openai --upgrade# Importing the necessary Python libraries
import os
import json
import yaml
import openai结合Azure Openai 的内容将 API 的设置按照 Azure 给的方式结合文件放 key,同时准备一个about-me.txt
#../keys/openai-keys.yaml
API_KEY: 06332xxxxxxcd4e70bxxxxxx6ee135#../data/about-me.txt
Hello! My name is Enigma Zhao. I am an Azure cloud engineer at Microsoft. I enjoy learning about AI and teaching what I learn back to others. I have two sons and a daughter. I drive a Audi A3, and my favorite video game series is The Legend of Zelda.openai.api_version 2023-07-01-preview
openai.api_type azure
openai.api_base https://aoaifr01.openai.azure.com/# Loading the API key and organization ID from file (NOT pushed to GitHub)
with open(../keys/openai-keys.yaml) as f:keys_yaml yaml.safe_load(f)# Applying our API key
openai.api_key keys_yaml[API_KEY]
os.environ[OPENAI_API_KEY] keys_yaml[API_KEY]# Loading the About Me text from local file
with open(../data/about-me.txt, r) as f:about_me f.read()测试Json 转换
在使用函数调用之前先看一下如何使用提示工程和Regex生成一个结构JSON在以后会使用到。
# Engineering a prompt to extract as much information from About Me as a JSON object
about_me_prompt f
Please extract information as a JSON object. Please look for the following pieces of information.
Name
Job title
Company
Number of children as a single number
Car make
Car model
Favorite video game seriesThis is the body of text to extract the information from:
{about_me}# Getting the response back from ChatGPT (gpt-4)
openai_response openai.ChatCompletion.create(enginegpt-4,messages [{role: user, content: about_me_prompt}]
)# Loading the response as a JSON object
json_response json.loads(openai_response[choices][0][message][content])
print(json_response)输出如下
rootubuntu0:~/python# python3 [fc1.py](http://fc1.py/)
{Name: Enigma Zhao, Job title: Azure cloud engineer, Company: Microsoft, Number of children: 3, Car make: Audi, Car model: A3, Favorite video game series: The Legend of Zelda}简单的自定义函数
# Defining our initial extract_person_info function
def extract_person_info(name, job_title, num_children):Prints basic About Me informationInputs:name (str): Name of the personjob_title (str): Job title of the personnum_chilren (int): The number of children the parent has.print(fThis person\s name is {name}. Their job title is {job_title}, and they have {num_children} children.)# Defining how we want ChatGPT to call our custom functions
my_custom_functions [{name: extract_person_info,description: Get About Me information from the body of the input text,parameters: {type: object,properties: {name: {type: string,description: Name of the person},job_title: {type: string,description: Job title of the person},num_children: {type: integer,description: Number of children the person is a parent to}}}}
] openai_response openai.ChatCompletion.create(enginegpt-4,messages [{role: user, content: about_me}],functions my_custom_functions,function_call auto
)print(openai_response)输出如下,OpenAI 讲 about_me 的内容根据 function 的格式进行梳理调用 function 输出
rootubuntu0:~/python# python3 fc2.py
{id: chatcmpl-7tYiDoEjPpzNw3tPo3ZDFdaHSbS5u,object: chat.completion,created: 1693475829,model: gpt-4,prompt_annotations: [{prompt_index: 0,content_filter_results: {hate: {filtered: false,severity: safe},self_harm: {filtered: false,severity: safe},sexual: {filtered: false,severity: safe},violence: {filtered: false,severity: safe}}}],choices: [{index: 0,finish_reason: function_call,message: {role: assistant,function_call: {name: extract_person_info,arguments: {\n \name\: \Enigma Zhao\,\n \job_title\: \Azure cloud engineer\,\n \num_children\: 3\n}}},content_filter_results: {}}],usage: {completion_tokens: 36,prompt_tokens: 147,total_tokens: 183}
}在上面的示例中自定义函数提取三个非常具体的信息位通过传递自定义的“About Me”文本作为提示符来证明这可以成功地工作。
如果传入任何其他不包含该信息的提示会发生什么?
在API客户端调用function_call中设置了一个参数并将其设置为auto。这个参数实际上是在告诉ChatGPT在确定何时为自定义函数构建输出时使用它的最佳判断。
所以当提交的提示符与任何自定义函数都不匹配时会发生什么呢? 简单地说它默认为典型的行为就好像函数调用不存在一样。 我们用一个任意的提示来测试一下:“埃菲尔铁塔有多高?”修改如下
openai_response openai.ChatCompletion.create(enginegpt-4,messages [{role: user, content: How tall is the Eiffel Tower?}],functions my_custom_functions,function_call auto
)print(openai_response)输出结果
{id: chatcmpl-7tYvdaiKaoiWW7NXz8QDeZZYEKnko,object: chat.completion,created: 1693476661,model: gpt-4,prompt_annotations: [{prompt_index: 0,content_filter_results: {hate: {filtered: false,severity: safe},self_harm: {filtered: false,severity: safe},sexual: {filtered: false,severity: safe},violence: {filtered: false,severity: safe}}}],choices: [{index: 0,finish_reason: stop,message: {role: assistant,content: The Eiffel Tower is approximately 330 meters (1083 feet) tall.},content_filter_results: {hate: {filtered: false,severity: safe},self_harm: {filtered: false,severity: safe},sexual: {filtered: false,severity: safe},violence: {filtered: false,severity: safe}}}],usage: {completion_tokens: 18,prompt_tokens: 97,total_tokens: 115}
}多样本情况
现在让我们演示一下当我们将3个不同的样本应用于所有自定义函数时会发生什么。
# Defining a function to extract only vehicle information
def extract_vehicle_info(vehicle_make, vehicle_model):Prints basic vehicle informationInputs:- vehicle_make (str): Make of the vehicle- vehicle_model (str): Model of the vehicleprint(fVehicle make: {vehicle_make}\nVehicle model: {vehicle_model})# Defining a function to extract all information provided in the original About Me prompt
def extract_all_info(name, job_title, num_children, vehicle_make, vehicle_model, company_name, favorite_vg_series):Prints the full About Me informationInputs:- name (str): Name of the person- job_title (str): Job title of the person- num_chilren (int): The number of children the parent has- vehicle_make (str): Make of the vehicle- vehicle_model (str): Model of the vehicle- company_name (str): Name of the company the person works for- favorite_vg_series (str): Persons favorite video game series.print(fThis person\s name is {name}. Their job title is {job_title}, and they have {num_children} children.They drive a {vehicle_make} {vehicle_model}.They work for {company_name}.Their favorite video game series is {favorite_vg_series}.)# Defining how we want ChatGPT to call our custom functions
my_custom_functions [{name: extract_person_info,description: Get About Me information from the body of the input text,parameters: {type: object,properties: {name: {type: string,description: Name of the person},job_title: {type: string,description: Job title of the person},num_children: {type: integer,description: Number of children the person is a parent to}}}},{name: extract_vehicle_info,description: Extract the make and model of the person\s car,parameters: {type: object,properties: {vehicle_make: {type: string,description: Make of the person\s vehicle},vehicle_model: {type: string,description: Model of the person\s vehicle}}}},{name: extract_all_info,description: Extract all information about a person including their vehicle make and model,parameters: {type: object,properties: {name: {type: string,description: Name of the person},job_title: {type: string,description: Job title of the person},num_children: {type: integer,description: Number of children the person is a parent to},vehicle_make: {type: string,description: Make of the person\s vehicle},vehicle_model: {type: string,description: Model of the person\s vehicle},company_name: {type: string,description: Name of the company the person works for},favorite_vg_series: {type: string,description: Name of the person\s favorite video game series}}}}
]# Defining a list of samples
samples [str(about_me),My name is David Hundley. I am a principal machine learning engineer, and I have two daughters.,She drives a Kia Sportage.
]# Iterating over the three samples
for i, sample in enumerate(samples):print(fSample #{i 1}\s results:)# Getting the response back from ChatGPT (gpt-4)openai_response openai.ChatCompletion.create(engine gpt-4,messages [{role: user, content: sample}],functions my_custom_functions,function_call auto)# Printing the samples responseprint(openai_response)输出如下
rootubuntu0:~/python# python3 [fc3.py](http://fc3.py/)
Sample #1s results:
{
id: chatcmpl-7tq3Nh7BSccfFAmT2psZcRR3hHpZ7,
object: chat.completion,
created: 1693542489,
model: gpt-4,
prompt_annotations: [
{
prompt_index: 0,
content_filter_results: {
hate: {
filtered: false,
severity: safe
},
self_harm: {
filtered: false,
severity: safe
},
sexual: {
filtered: false,
severity: safe
},
violence: {
filtered: false,
severity: safe
}
}
}
],
choices: [
{
index: 0,
finish_reason: function_call,
message: {
role: assistant,
function_call: {
name: extract_all_info,
arguments: {\n\name\: \Enigma Zhao\,\n\job_title\: \Azure cloud engineer\,\n\num_children\: 3,\n\vehicle_make\: \Audi\,\n\vehicle_model\: \A3\,\n\company_name\: \Microsoft\,\n\favorite_vg_series\: \The Legend of Zelda\\n}
}
},
content_filter_results: {}
}
],
usage: {
completion_tokens: 67,
prompt_tokens: 320,
total_tokens: 387
}
}
Sample #2s results:
{
id: chatcmpl-7tq3QUA3o1yixTLZoPtuWOfKA38ub,
object: chat.completion,
created: 1693542492,
model: gpt-4,
prompt_annotations: [
{
prompt_index: 0,
content_filter_results: {
hate: {
filtered: false,
severity: safe
},
self_harm: {
filtered: false,
severity: safe
},
sexual: {
filtered: false,
severity: safe
},
violence: {
filtered: false,
severity: safe
}
}
}
],
choices: [
{
index: 0,
finish_reason: function_call,
message: {
role: assistant,
function_call: {
name: extract_person_info,
arguments: {\n\name\: \David Hundley\,\n\job_title\: \principal machine learning engineer\,\n\num_children\: 2\n}
}
},
content_filter_results: {}
}
],
usage: {
completion_tokens: 33,
prompt_tokens: 282,
total_tokens: 315
}
}
Sample #3s results:
{
id: chatcmpl-7tq3RxN3tCLKbPadWkGQguploKFw2,
object: chat.completion,
created: 1693542493,
model: gpt-4,
prompt_annotations: [
{
prompt_index: 0,
content_filter_results: {
hate: {
filtered: false,
severity: safe
},
self_harm: {
filtered: false,
severity: safe
},
sexual: {
filtered: false,
severity: safe
},
violence: {
filtered: false,
severity: safe
}
}
}
],
choices: [
{
index: 0,
finish_reason: function_call,
message: {
role: assistant,
function_call: {
name: extract_vehicle_info,
arguments: {\n \vehicle_make\: \Kia\,\n \vehicle_model\: \Sportage\\n}
}
},
content_filter_results: {}
}
],
usage: {
completion_tokens: 27,
prompt_tokens: 268,
total_tokens: 295
}
}对于每个相应的提示ChatGPT选择了正确的自定义函数可以特别注意到API的响应对象中function_call下的name值。
除了这是一种方便的方法来确定使用哪个函数的参数之外我们还可以通过编程将实际的自定义Python函数映射到此值以适当地选择运行正确的代码。
# Iterating over the three samples
for i, sample in enumerate(samples):print(fSample #{i 1}\s results:)# Getting the response back from ChatGPT (gpt-4)openai_response openai.ChatCompletion.create(engine gpt-4,messages [{role: user, content: sample}],functions my_custom_functions,function_call auto)[choices][0][message]# Checking to see that a function call was invokedif openai_response.get(function_call):# Checking to see which specific function call was invokedfunction_called openai_response[function_call][name]# Extracting the arguments of the function callfunction_args json.loads(openai_response[function_call][arguments])# Invoking the proper functionsif function_called extract_person_info:extract_person_info(*list(function_args.values()))elif function_called extract_vehicle_info:extract_vehicle_info(*list(function_args.values()))elif function_called extract_all_info:extract_all_info(*list(function_args.values()))输出如下
rootubuntu0:~/python# python3 fc4.py
Sample #1s results:This persons name is Enigma Zhao. Their job title is Azure cloud engineer, and they have 3 children.They drive a Audi A3.They work for Microsoft.Their favorite video game series is The Legend of Zelda.Sample #2s results:
This persons name is David Hundley. Their job title is principal machine learning engineer, and they have 2 children.
Sample #3s results:
Vehicle make: Kia
Vehicle model: SportageOpenAI Function Calling with LangChain
考虑到LangChain在生成式AI社区中的受欢迎程度添加一些代码来展示如何在LangChain中使用这个功能。
注意在使用前要安装 LangChain
pip3 install LangChain# Importing the LangChain objects
from langchain.chat_models import ChatOpenAI
from langchain.chains import LLMChain
from langchain.prompts.chat import ChatPromptTemplate
from langchain.chains.openai_functions import create_structured_output_chain
# Setting the proper instance of the OpenAI model
#llm ChatOpenAI(model gpt-3.5-turbo-0613)**#model 格式发生改变如果用ChatOpenAI(model gpt-4)系统会给警告
llm ChatOpenAI(model_kwargs{engine: gpt-4})**# Setting a LangChain ChatPromptTemplate
chat_prompt_template ChatPromptTemplate.from_template({my_prompt})# Setting the JSON schema for extracting vehicle information
langchain_json_schema {name: extract_vehicle_info,description: Extract the make and model of the person\s car,type: object,properties: {vehicle_make: {title: Vehicle Make,type: string,description: Make of the person\s vehicle},vehicle_model: {title: Vehicle Model,type: string,description: Model of the person\s vehicle}}
}
# Defining the LangChain chain object for function calling
chain create_structured_output_chain(output_schema langchain_json_schema,llm llm,prompt chat_prompt_template)
# Getting results with a demo prompt
print(chain.run(my_prompt about_me))输出如下
rootubuntu0:~/python# python3 fc0.py
{vehicle_make: Audi, vehicle_model: A3}小结
有几个和原文配置不一样的地方 结合Azure Openai 的内容将 API 的设置按照 Azure 给的方式结合文件放 key,同时准备一个about-me.txt #../keys/openai-keys.yaml
API_KEY: 06332xxxxxxcd4e70bxxxxxx6ee135#../data/about-me.txt
Hello! My name is zhang san. I am an Azure cloud engineer at Microsoft. I enjoy learning about AI and teaching what I learn back to others. I have two sons and a daughter. I drive a Audi A3, and my favorite video game series is The Legend of Zelda.基本配置按照 AOAI 的格式 openai.api_version 2023-07-01-preview
openai.api_type azure
openai.api_base https://aoaifr01.openai.azure.com/
#Applying our API key
openai.api_key keys_yaml[API_KEY]
os.environ[OPENAI_API_KEY] keys_yaml[API_KEY] #后面的多样本测试要用Function Call 的配置将 model ‘gpt-3.5-turbo’ 改为 engine“gpt-4” openai_response openai.ChatCompletion.create(
enginegpt-4,
messages [{role: user, content: about_me}],
functions my_custom_functions,
function_call auto OpenAI Function Calling with LangChain 先要安装 LangChain pip3 install LangChainmodel 格式发生改变如果用原文的ChatOpenAI(model ‘gpt-4’)系统会给警告 llm ChatOpenAI(model_kwargs{engine: gpt-4})
