互联网的大部分功能都由RESTful API驱动。赋予GPT调用这些API的能力将开启无限可能。本笔记本展示了如何利用GPT智能调用API，它结合了OpenAPI规范与链式函数调用功能。
OpenAPI Specification (OAS) 是一个被广泛接受的标准，用于以机器可读和解释的格式描述RESTful API的细节。它使人类和计算机都能理解服务的能力，并可用于向GPT展示如何调用API。
本笔记本分为两个主要部分：
我们建议在继续之前先熟悉function-calling。
!pip install -q jsonref # for resolving $ref's in the OpenAPI spec
!pip install -q openai[33mDEPRECATION: textract 1.6.5 has a non-standard dependency specifier extract-msg<=0.29.*. pip 23.3 will enforce this behaviour change. A possible replacement is to upgrade to a newer version of textract or contact the author to suggest that they release a version with a conforming dependency specifiers. Discussion can be found at https://github.com/pypa/pip/issues/12063[0m[33m [0m [1m[[0m[34;49mnotice[0m[1;39;49m][0m[39;49m A new release of pip is available: [0m[31;49m23.2.1[0m[39;49m -> [0m[32;49m23.3.1[0m [1m[[0m[34;49mnotice[0m[1;39;49m][0m[39;49m To update, run: [0m[32;49mpip install --upgrade pip[0m [33mDEPRECATION: textract 1.6.5 has a non-standard dependency specifier extract-msg<=0.29.*. pip 23.3 will enforce this behaviour change. A possible replacement is to upgrade to a newer version of textract or contact the author to suggest that they release a version with a conforming dependency specifiers. Discussion can be found at https://github.com/pypa/pip/issues/12063[0m[33m [0m [1m[[0m[34;49mnotice[0m[1;39;49m][0m[39;49m A new release of pip is available: [0m[31;49m23.2.1[0m[39;49m -> [0m[32;49m23.3.1[0m [1m[[0m[34;49mnotice[0m[1;39;49m][0m[39;49m To update, run: [0m[32;49mpip install --upgrade pip[0m
import os
import json
import jsonref
from openai import OpenAI
import requests
from pprint import pp
client = OpenAI(api_key=os.environ.get("OPENAI_API_KEY", "<your OpenAI API key if not set as env var>"))我们在此使用的示例OpenAPI规范是通过gpt-4创建的。我们将把这个示例规范转换为一组函数定义，这些定义可以提供给聊天补全API。该模型会根据提供的用户指令，生成一个包含调用这些函数所需参数的JSON对象。
在继续之前，让我们检查这个生成的规范。OpenAPI规范包含有关API端点、它们支持的操作、接受的参数、可以处理的请求以及返回的响应的详细信息。该规范以JSON格式定义。
规范中的端点包括以下操作：
规范中的每个操作都有一个operationId，当我们将规范解析为函数规范时，将使用它作为函数名称。该规范还包括定义每个操作参数的数据类型和结构的模式。
你可以在这里查看架构：
with open('./data/example_events_openapi.json', 'r') as f:
openapi_spec = jsonref.loads(f.read()) # it's important to load with jsonref, as explained below
display(openapi_spec){'openapi': '3.0.0',
'info': {'version': '1.0.0',
'title': 'Event Management API',
'description': 'An API for managing event data'},
'paths': {'/events': {'get': {'summary': 'List all events',
'operationId': 'listEvents',
'responses': {'200': {'description': 'A list of events',
'content': {'application/json': {'schema': {'type': 'array',
'items': {'type': 'object',
'properties': {'id': {'type': 'string'},
'name': {'type': 'string'},
'date': {'type': 'string', 'format': 'date-time'},
'location': {'type': 'string'}},
'required': ['name', 'date', 'location']}}}}}}},
'post': {'summary': 'Create a new event',
'operationId': 'createEvent',
'requestBody': {'required': True,
'content': {'application/json': {'schema': {'type': 'object',
'properties': {'id': {'type': 'string'},
'name': {'type': 'string'},
'date': {'type': 'string', 'format': 'date-time'},
'location': {'type': 'string'}},
'required': ['name', 'date', 'location']}}}},
'responses': {'201': {'description': 'The event was created',
'content': {'application/json': {'schema': {'type': 'object',
'properties': {'id': {'type': 'string'},
'name': {'type': 'string'},
'date': {'type': 'string', 'format': 'date-time'},
'location': {'type': 'string'}},
'required': ['name', 'date', 'location']}}}}}}},
'/events/{id}': {'get': {'summary': 'Retrieve an event by ID',
'operationId': 'getEventById',
'parameters': [{'name': 'id',
'in': 'path',
'required': True,
'schema': {'type': 'string'}}],
'responses': {'200': {'description': 'The event',
'content': {'application/json': {'schema': {'type': 'object',
'properties': {'id': {'type': 'string'},
'name': {'type': 'string'},
'date': {'type': 'string', 'format': 'date-time'},
'location': {'type': 'string'}},
'required': ['name', 'date', 'location']}}}}}},
'delete': {'summary': 'Delete an event by ID',
'operationId': 'deleteEvent',
'parameters': [{'name': 'id',
'in': 'path',
'required': True,
'schema': {'type': 'string'}}],
'responses': {'204': {'description': 'The event was deleted'}}},
'patch': {'summary': "Update an event's details by ID",
'operationId': 'updateEventDetails',
'parameters': [{'name': 'id',
'in': 'path',
'required': True,
'schema': {'type': 'string'}}],
'requestBody': {'required': True,
'content': {'application/json': {'schema': {'type': 'object',
'properties': {'name': {'type': 'string'},
'date': {'type': 'string', 'format': 'date-time'},
'location': {'type': 'string'}},
'required': ['name', 'date', 'location']}}}},
'responses': {'200': {'description': "The event's details were updated",
'content': {'application/json': {'schema': {'type': 'object',
'properties': {'id': {'type': 'string'},
'name': {'type': 'string'},
'date': {'type': 'string', 'format': 'date-time'},
'location': {'type': 'string'}},
'required': ['name', 'date', 'location']}}}}}}}},
'components': {'schemas': {'Event': {'type': 'object',
'properties': {'id': {'type': 'string'},
'name': {'type': 'string'},
'date': {'type': 'string', 'format': 'date-time'},
'location': {'type': 'string'}},
'required': ['name', 'date', 'location']}}}}既然我们已经对OpenAPI规范有了很好的理解，接下来可以将其解析为函数规范。
我们可以编写一个简单的openapi_to_functions函数来生成定义列表，其中每个函数都表示为一个包含以下键的字典：
name: 这对应于OpenAPI规范中定义的API端点的操作标识符。description: 这是函数的简要描述或摘要，概述了该函数的功能。parameters: 这是一个定义函数预期输入参数的架构。它提供了每个参数的类型信息，说明该参数是必需还是可选，以及其他相关细节。对于模式中定义的每个端点，我们需要执行以下操作：
解析JSON引用: 在OpenAPI规范中，通常会使用JSON引用(也称为$ref)来避免重复。这些引用指向在多个位置使用的定义。例如，如果多个API端点返回相同的对象结构，该结构可以定义一次，然后在需要的地方引用。我们需要解析这些引用并用它们指向的内容进行替换。
提取函数名称： 我们将直接使用operationId作为函数名称。或者，也可以使用端点路径和操作作为函数名称。
提取描述和参数： 我们将遍历description、summary、requestBody和parameters字段来填充函数的描述和参数。
以下是实现方式：
def openapi_to_functions(openapi_spec):
functions = []
for path, methods in openapi_spec["paths"].items():
for method, spec_with_ref in methods.items():
# 1. Resolve JSON references.
spec = jsonref.replace_refs(spec_with_ref)
# 2. Extract a name for the functions.
function_name = spec.get("operationId")
# 3. Extract a description and parameters.
desc = spec.get("description") or spec.get("summary", "")
schema = {"type": "object", "properties": {}}
req_body = (
spec.get("requestBody", {})
.get("content", {})
.get("application/json", {})
.get("schema")
)
if req_body:
schema["properties"]["requestBody"] = req_body
params = spec.get("parameters", [])
if params:
param_properties = {
param["name"]: param["schema"]
for param in params
if "schema" in param
}
schema["properties"]["parameters"] = {
"type": "object",
"properties": param_properties,
}
functions.append(
{"type": "function", "function": {"name": function_name, "description": desc, "parameters": schema}}
)
return functions
functions = openapi_to_functions(openapi_spec)
for function in functions:
pp(function)
print()
{'type': 'function',
'function': {'name': 'listEvents',
'description': 'List all events',
'parameters': {'type': 'object', 'properties': {}}}}
{'type': 'function',
'function': {'name': 'createEvent',
'description': 'Create a new event',
'parameters': {'type': 'object',
'properties': {'requestBody': {'type': 'object',
'properties': {'id': {'type': 'string'},
'name': {'type': 'string'},
'date': {'type': 'string',
'format': 'date-time'},
'location': {'type': 'string'}},
'required': ['name',
'date',
'location']}}}}}
{'type': 'function',
'function': {'name': 'getEventById',
'description': 'Retrieve an event by ID',
'parameters': {'type': 'object',
'properties': {'parameters': {'type': 'object',
'properties': {'id': {'type': 'string'}}}}}}}
{'type': 'function',
'function': {'name': 'deleteEvent',
'description': 'Delete an event by ID',
'parameters': {'type': 'object',
'properties': {'parameters': {'type': 'object',
'properties': {'id': {'type': 'string'}}}}}}}
{'type': 'function',
'function': {'name': 'updateEventDetails',
'description': "Update an event's details by ID",
'parameters': {'type': 'object',
'properties': {'requestBody': {'type': 'object',
'properties': {'name': {'type': 'string'},
'date': {'type': 'string',
'format': 'date-time'},
'location': {'type': 'string'}},
'required': ['name',
'date',
'location']},
'parameters': {'type': 'object',
'properties': {'id': {'type': 'string'}}}}}}}
现在我们有了这些函数定义，可以利用GPT根据用户输入智能地调用它们。
需要注意的是，聊天补全API并不会执行函数，而是生成您可以在自己代码中用于调用函数的JSON。
如需了解更多关于函数调用的信息，请参阅我们的专用函数调用指南。
SYSTEM_MESSAGE = """
You are a helpful assistant.
Respond to the following prompt by using function_call and then summarize actions.
Ask for clarification if a user request is ambiguous.
"""
# Maximum number of function calls allowed to prevent infinite or lengthy loops
MAX_CALLS = 5
def get_openai_response(functions, messages):
return client.chat.completions.create(
model="gpt-3.5-turbo-16k",
tools=functions,
tool_choice="auto", # "auto" means the model can pick between generating a message or calling a function.
temperature=0,
messages=messages,
)
def process_user_instruction(functions, instruction):
num_calls = 0
messages = [
{"content": SYSTEM_MESSAGE, "role": "system"},
{"content": instruction, "role": "user"},
]
while num_calls < MAX_CALLS:
response = get_openai_response(functions, messages)
message = response.choices[0].message
print(message)
try:
print(f"\n>> Function call #: {num_calls + 1}\n")
pp(message.tool_calls)
messages.append(message)
# For the sake of this example, we'll simply add a message to simulate success.
# Normally, you'd want to call the function here, and append the results to messages.
messages.append(
{
"role": "tool",
"content": "success",
"tool_call_id": message.tool_calls[0].id,
}
)
num_calls += 1
except:
print("\n>> Message:\n")
print(message.content)
break
if num_calls >= MAX_CALLS:
print(f"Reached max chained function calls: {MAX_CALLS}")
USER_INSTRUCTION = """
Instruction: Get all the events.
Then create a new event named AGI Party.
Then delete event with id 2456.
"""
process_user_instruction(functions, USER_INSTRUCTION)
ChatCompletionMessage(content=None, role='assistant', function_call=None, tool_calls=[ChatCompletionMessageToolCall(id='call_jmlvEyMRMvOtB80adX9RbqIV', function=Function(arguments='{}', name='listEvents'), type='function')])
>> Function call #: 1
[ChatCompletionMessageToolCall(id='call_jmlvEyMRMvOtB80adX9RbqIV', function=Function(arguments='{}', name='listEvents'), type='function')]
ChatCompletionMessage(content=None, role='assistant', function_call=None, tool_calls=[ChatCompletionMessageToolCall(id='call_OOPOY7IHMq3T7Ib71JozlUQJ', function=Function(arguments='{\n "requestBody": {\n "id": "1234",\n "name": "AGI Party",\n "date": "2022-12-31",\n "location": "New York"\n }\n}', name='createEvent'), type='function')])
>> Function call #: 2
[ChatCompletionMessageToolCall(id='call_OOPOY7IHMq3T7Ib71JozlUQJ', function=Function(arguments='{\n "requestBody": {\n "id": "1234",\n "name": "AGI Party",\n "date": "2022-12-31",\n "location": "New York"\n }\n}', name='createEvent'), type='function')]
ChatCompletionMessage(content=None, role='assistant', function_call=None, tool_calls=[ChatCompletionMessageToolCall(id='call_Kxluu3fJSOsZNNCn3JIlWAAM', function=Function(arguments='{\n "parameters": {\n "id": "2456"\n }\n}', name='deleteEvent'), type='function')])
>> Function call #: 3
[ChatCompletionMessageToolCall(id='call_Kxluu3fJSOsZNNCn3JIlWAAM', function=Function(arguments='{\n "parameters": {\n "id": "2456"\n }\n}', name='deleteEvent'), type='function')]
ChatCompletionMessage(content='Here are the actions I performed:\n\n1. Retrieved all the events.\n2. Created a new event named "AGI Party" with the ID "1234", scheduled for December 31, 2022, in New York.\n3. Deleted the event with the ID "2456".', role='assistant', function_call=None, tool_calls=None)
>> Function call #: 4
None
>> Message:
Here are the actions I performed:
1. Retrieved all the events.
2. Created a new event named "AGI Party" with the ID "1234", scheduled for December 31, 2022, in New York.
3. Deleted the event with the ID "2456".
我们已经展示了如何将OpenAPI规范转换为函数规范，以便提供给GPT智能调用，并演示了如何将这些函数串联起来执行复杂操作。
该系统的可能扩展包括处理需要条件逻辑或循环的更复杂用户指令，与实际API集成以执行实际操作，以及改进错误处理和验证以确保指令可行且函数调用成功。