【AI大模型】GPTS 与 Assistants API

前言

          2023 年 11 月 6 日，OpenAI DevDay 发表了一系列新能力，其中包括：GPT Store 和 Assistants API。

GPTs 和 Assistants API 本质是降低开发门槛

可操控性和易用性之间的权衡与折中：

1. 更多技术路线选择：原生 API、GPTs 和 Assistants API
2. GPTs 的示范，起到教育客户的作用，有助于打开市场
3. 要更大自由度，需要用 Assistants API 开发
4. 想极致调优，还得原生 API + RAG
5. 国内大模型的 Assistants API，参考 Minimax

Assistants API 的主要能力

已有能力：

1. 创建和管理 assistant，每个 assistant 有独立的配置
2. 支持无限长的多轮对话，对话历史保存在 OpenAI 的服务器上
3. 通过自有向量数据库支持基于文件的 RAG
4. 支持 Code Interpreter
   1. 在沙箱里编写并运行 Python 代码
   2. 自我修正代码
   3. 可传文件给 Code Interpreter
5. 支持 Function Calling
6. 支持在线调试的 Playground

承诺未来会有的能力：

1. 支持 DALL·E
2. 支持图片消息
3. 支持自定义调整 RAG 的配置项

收费：

1. 按 token 收费。无论多轮对话，还是 RAG，所有都按实际消耗的 token 收费
2. 如果对话历史过多超过大模型上下文窗口，会自动放弃最老的对话消息
3. 文件按数据大小和存放时长收费。1 GB 向量存储 一天收费 0.10 美元
4. Code interpreter 跑一次 $0.03

创建一个 Assistant

可以为每个应用，甚至应用中的每个有对话历史的使用场景，创建一个 assistant。

虽然可以用代码创建，也不复杂，例如：

from openai import OpenAI# 初始化 OpenAI 服务
client = OpenAI()# 创建助手
assistant = client.beta.assistants.create(name="小U",instructions="你叫小U，你是JAVA技术框架 UAP的助手，你负责回答用户关于UAP的问题。",model="gpt-4-turbo",
)

但是，更佳做法是，到 Playground 在线创建，因为：

1. 更方便调整
2. 更方便测试

样例 Assistant 的配置

Instructions:

你叫小U，你是JAVA技术框架 UAP的助手，你负责回答用户关于UAP的问题。

Functions:

{"name": "ask_database","description": "Use this function to answer user questions about course schedule. Output should be a fully formed SQL query.","parameters": {"type": "object","properties": {"query": {"type": "string","description": "SQL query extracting info to answer the user's question.\nSQL should be written using this database schema:\n\nCREATE TABLE Courses (\n\tid INT AUTO_INCREMENT PRIMARY KEY,\n\tcourse_date DATE NOT NULL,\n\tstart_time TIME NOT NULL,\n\tend_time TIME NOT NULL,\n\tcourse_name VARCHAR(255) NOT NULL,\n\tinstructor VARCHAR(255) NOT NULL\n);\n\nThe query should be returned in plain text, not in JSON.\nThe query should only contain grammars supported by SQLite."}},"required": ["query"]}
}

代码访问 Assistant

管理 thread

Threads：

1. Threads 里保存的是对话历史，即 messages
2. 一个 assistant 可以有多个 thread
3. 一个 thread 可以有无限条 message
4. 一个用户与 assistant 的多轮对话历史可以维护在一个 thread 里

import jsondef show_json(obj):"""把任意对象用排版美观的 JSON 格式打印出来"""print(json.dumps(json.loads(obj.model_dump_json()),indent=4,ensure_ascii=False))

from openai import OpenAI
import osfrom dotenv import load_dotenv, find_dotenv
_ = load_dotenv(find_dotenv())# 初始化 OpenAI 服务
client = OpenAI()   # openai >= 1.3.0 起，OPENAI_API_KEY 和 OPENAI_BASE_URL 会被默认使用# 创建 thread
thread = client.beta.threads.create()
show_json(thread)

{"id": "thread_zkT0xybD8VslhJzJJNY3IHuX","created_at": 1716553797,"metadata": {},"object": "thread","tool_resources": {"code_interpreter": null,"file_search": null}
}

可以根据需要，自定义 metadata，比如创建 thread 时，把 thread 归属的用户信息存入。

thread = client.beta.threads.create(metadata={"fullname": "王卓然", "username": "taliux"}
)
show_json(thread)

{"id": "thread_1LMmbLMx2ZrRQjymDOGQGYGX","created_at": 1716553801,"metadata": {"fullname": "王卓然","username": "taliux"},"object": "thread","tool_resources": {"code_interpreter": null,"file_search": null}
}

Thread ID 如果保存下来，是可以在下次运行时继续对话的。

从 thread ID 获取 thread 对象的代码：

thread = client.beta.threads.retrieve(thread.id)
show_json(thread)

{"id": "thread_1LMmbLMx2ZrRQjymDOGQGYGX","created_at": 1716553801,"metadata": {"fullname": "王卓然","username": "taliux"},"object": "thread","tool_resources": {"code_interpreter": {"file_ids": []},"file_search": null}
}

此外，还有：

1. threads.modify() 修改 thread 的 metadata 和 tool_resources
2. threads.retrieve() 获取 thread
3. threads.delete() 删除 thread。

具体文档参考：https://platform.openai.com/docs/api-reference/threads

给 Threads 添加 Messages

这里的 messages 结构要复杂一些：

1. 不仅有文本，还可以有图片和文件
2. 也有 metadata

message = client.beta.threads.messages.create(thread_id=thread.id,  # message 必须归属于一个 threadrole="user",          # 取值是 user 或者 assistant。但 assistant 消息会被自动加入，我们一般不需要自己构造content="你都能做什么？",
)
show_json(message)

{"id": "msg_wDZxbO2oi2rAvk9Yxgqw0hVP","assistant_id": null,"attachments": [],"completed_at": null,"content": [{"text": {"annotations": [],"value": "你都能做什么？"},"type": "text"}],"created_at": 1716553809,"incomplete_at": null,"incomplete_details": null,"metadata": {},"object": "thread.message","role": "user","run_id": null,"status": null,"thread_id": "thread_1LMmbLMx2ZrRQjymDOGQGYGX"
}

还有如下函数：

1. threads.messages.retrieve() 获取 message
2. threads.messages.update() 更新 message 的 metadata
3. threads.messages.list() 列出给定 thread 下的所有 messages

具体文档参考：https://platform.openai.com/docs/api-reference/messages

也可以在创建 thread 同时初始化一个 message 列表：

thread = client.beta.threads.create(messages=[{"role": "user","content": "你好",},{"role": "assistant","content": "有什么可以帮您？",},{"role": "user","content": "你是谁？",},]
)show_json(thread)  # 显示 thread
print("-----")
show_json(client.beta.threads.messages.list(thread.id))  # 显示指定 thread 中的 message 列表

{"id": "thread_Qf32rY62YZrpW8d3nEm51mLn","created_at": 1716553813,"metadata": {},"object": "thread","tool_resources": {"code_interpreter": null,"file_search": null}
}
-----
{"data": [{"id": "msg_MkAm2f87yE3ynnLOzXCLq5XR","assistant_id": null,"attachments": [],"completed_at": null,"content": [{"text": {"annotations": [],"value": "你是谁？"},"type": "text"}],"created_at": 1716553813,"incomplete_at": null,"incomplete_details": null,"metadata": {},"object": "thread.message","role": "user","run_id": null,"status": null,"thread_id": "thread_Qf32rY62YZrpW8d3nEm51mLn"},{"id": "msg_tTgI3MS6t19pzQM7ItFJkZaA","assistant_id": null,"attachments": [],"completed_at": null,"content": [{"text": {"annotations": [],"value": "有什么可以帮您？"},"type": "text"}],"created_at": 1716553813,"incomplete_at": null,"incomplete_details": null,"metadata": {},"object": "thread.message","role": "assistant","run_id": null,"status": null,"thread_id": "thread_Qf32rY62YZrpW8d3nEm51mLn"},{"id": "msg_imlUh5ckePY0SaBmE6dDB3AY","assistant_id": null,"attachments": [],"completed_at": null,"content": [{"text": {"annotations": [],"value": "你好"},"type": "text"}],"created_at": 1716553813,"incomplete_at": null,"incomplete_details": null,"metadata": {},"object": "thread.message","role": "user","run_id": null,"status": null,"thread_id": "thread_Qf32rY62YZrpW8d3nEm51mLn"}],"object": "list","first_id": "msg_MkAm2f87yE3ynnLOzXCLq5XR","last_id": "msg_imlUh5ckePY0SaBmE6dDB3AY","has_more": false
}

开始 Run

• 用 run 把 assistant 和 thread 关联，进行对话
• 一个 prompt 就是一次 run

直接运行

assistant_id = "asst_pxKAiBW0VB62glWPjeRDA7mR"  # 从 Playground 中拷贝run = client.beta.threads.runs.create_and_poll(thread_id=thread.id,assistant_id=assistant_id,
)

if run.status == 'completed':messages = client.beta.threads.messages.list(thread_id=thread.id)show_json(messages)
else:print(run.status)

Run 的状态

Run 的底层是个异步调用，意味着它不等大模型处理完，就返回。我们通过 run.status 了解大模型的工作进展情况，来判断下一步该干什么。

run.status 有的状态，和状态之间的转移关系如图。

流式运行

1. 创建回调函数

from typing_extensions import override
from openai import AssistantEventHandlerclass EventHandler(AssistantEventHandler):@overridedef on_text_created(self, text) -> None:"""响应输出创建事件"""print(f"\nassistant > ", end="", flush=True)@overridedef on_text_delta(self, delta, snapshot):"""响应输出生成的流片段"""print(delta.value, end="", flush=True)

     2. 运行 run

# 添加新一轮的 user message
message = client.beta.threads.messages.create(thread_id=thread.id,role="user",content="你说什么？",
)
# 使用 stream 接口并传入 EventHandler
with client.beta.threads.runs.stream(thread_id=thread.id,assistant_id=assistant_id,event_handler=EventHandler(),
) as stream:stream.until_done()

还有如下函数：

1. threads.runs.list() 列出 thread 归属的 run
2. threads.runs.retrieve() 获取 run
3. threads.runs.update() 修改 run 的 metadata
4. threads.runs.cancel() 取消 in_progress 状态的 run

具体文档参考：https://platform.openai.com/docs/api-reference/runs

使用 Tools

创建 Assistant 时声明 Code_Interpreter

如果用代码创建：

assistant = client.beta.assistants.create(name="Demo Assistant",instructions="你是人工智能助手。你可以通过代码回答很多数学问题。",tools=[{"type": "code_interpreter"}],model="gpt-4-turbo"
)

在回调中加入 code_interpreter 的事件响应

from typing_extensions import override
from openai import AssistantEventHandlerclass EventHandler(AssistantEventHandler):@overridedef on_text_created(self, text) -> None:"""响应输出创建事件"""print(f"\nassistant > ", end="", flush=True)@overridedef on_text_delta(self, delta, snapshot):"""响应输出生成的流片段"""print(delta.value, end="", flush=True)@overridedef on_tool_call_created(self, tool_call):"""响应工具调用"""print(f"\nassistant > {tool_call.type}\n", flush=True)@overridedef on_tool_call_delta(self, delta, snapshot):"""响应工具调用的流片段"""if delta.type == 'code_interpreter':if delta.code_interpreter.input:print(delta.code_interpreter.input, end="", flush=True)if delta.code_interpreter.outputs:print(f"\n\noutput >", flush=True)for output in delta.code_interpreter.outputs:if output.type == "logs":print(f"\n{output.logs}", flush=True)

发个 Code Interpreter 请求：

# 创建 thread
thread = client.beta.threads.create()# 添加新一轮的 user message
message = client.beta.threads.messages.create(thread_id=thread.id,role="user",content="用代码计算 1234567 的平方根",
)
# 使用 stream 接口并传入 EventHandler
with client.beta.threads.runs.stream(thread_id=thread.id,assistant_id=assistant_id,event_handler=EventHandler(),
) as stream:stream.until_done()

assistant > code_interpreterimport math# 计算 1234567 的平方根
square_root = math.sqrt(1234567)
square_rootoutput >1111.1107055554814assistant > 1234567 的平方根是约 1111.11。

Code_Interpreter 操作文件

# 上传文件到 OpenAI
file = client.files.create(file=open("mydata.csv", "rb"),purpose='assistants'
)# 创建 assistant
my_assistant = client.beta.assistants.create(name="CodeInterpreterWithFileDemo",instructions="你是数据分析师，按要求分析数据。",model="gpt-4-turbo",tools=[{"type": "code_interpreter"}],tool_resources={"code_interpreter": {"file_ids": [file.id]  # 为 code_interpreter 关联文件}}
)

# 创建 thread
thread = client.beta.threads.create()# 添加新一轮的 user message
message = client.beta.threads.messages.create(thread_id=thread.id,role="user",content="统计总销售额",
)
# 使用 stream 接口并传入 EventHandler
with client.beta.threads.runs.stream(thread_id=thread.id,assistant_id=my_assistant.id,event_handler=EventHandler(),
) as stream:stream.until_done()

关于文件操作，还有如下函数：

1. client.files.list() 列出所有文件
2. client.files.retrieve() 获取文件对象
3. client.files.delete() 删除文件
4. client.files.content() 读取文件内容

具体文档参考：https://platform.openai.com/docs/api-reference/files

创建 Assistant 时声明 Function

如果用代码创建：'''
python
assistant = client.beta.assistants.create(instructions="你叫瓜瓜。你是AGI课堂的助手。你只回答跟AI大模型有关的问题。不要跟学生闲聊。每次回答问题前，你要拆解问题并输出一步一步的思考过程。",model="gpt-4o",tools=[{"type": "function","function": {"name": "ask_database","description": "Use this function to answer user questions about course schedule. Output should be a fully formed SQL query.","parameters": {"type": "object","properties": {"query": {"type": "string","description": "SQL query extracting info to answer the user's question.\nSQL should be written using this database schema:\n\nCREATE TABLE Courses (\n\tid INT AUTO_INCREMENT PRIMARY KEY,\n\tcourse_date DATE NOT NULL,\n\tstart_time TIME NOT NULL,\n\tend_time TIME NOT NULL,\n\tcourse_name VARCHAR(255) NOT NULL,\n\tinstructor VARCHAR(255) NOT NULL\n);\n\nThe query should be returned in plain text, not in JSON.\nThe query should only contain grammars supported by SQLite."}},"required": ["query"]}}]
)
'''

 创建一个 Function

# 定义本地函数和数据库import sqlite3# 创建数据库连接
conn = sqlite3.connect(':memory:')
cursor = conn.cursor()# 创建orders表
cursor.execute("""
CREATE TABLE Courses (id INT AUTO_INCREMENT PRIMARY KEY,course_date DATE NOT NULL,start_time TIME NOT NULL,end_time TIME NOT NULL,course_name VARCHAR(255) NOT NULL,instructor VARCHAR(255) NOT NULL
);
""")# 插入5条明确的模拟记录
timetable = [('2024-01-23', '20:00', '22:00', 'aaaaa', '张三'),('2024-01-25', '20:00', '22:00', 'bbbbbbbb', '张三'),('2024-01-29', '20:00', '22:00', 'ccccc', '张三'),('2024-02-20', '20:00', '22:00', 'dddddd', '张三'),('2024-02-22', '20:00', '22:00', 'eeeeeee', '李四'),]for record in timetable:cursor.execute('''INSERT INTO Courses (course_date, start_time, end_time, course_name, instructor)VALUES (?, ?, ?, ?, ?)''', record)# 提交事务
conn.commit()def ask_database(query):cursor.execute(query)records = cursor.fetchall()return str(records)# 可以被回调的函数放入此字典
available_functions = {"ask_database": ask_database,
}

增加回调事件的响应

from typing_extensions import override
from openai import AssistantEventHandlerclass EventHandler(AssistantEventHandler):@overridedef on_text_created(self, text) -> None:"""响应回复创建事件"""print(f"\nassistant > ", end="", flush=True)@overridedef on_text_delta(self, delta, snapshot):"""响应输出生成的流片段"""print(delta.value, end="", flush=True)@overridedef on_tool_call_created(self, tool_call):"""响应工具调用"""print(f"\nassistant > {tool_call.type}\n", flush=True)@overridedef on_tool_call_delta(self, delta, snapshot):"""响应工具调用的流片段"""if delta.type == 'code_interpreter':if delta.code_interpreter.input:print(delta.code_interpreter.input, end="", flush=True)if delta.code_interpreter.outputs:print(f"\n\noutput >", flush=True)for output in delta.code_interpreter.outputs:if output.type == "logs":print(f"\n{output.logs}", flush=True)@overridedef on_event(self, event):"""响应 'requires_action' 事件"""if event.event == 'thread.run.requires_action':run_id = event.data.id  # 获取 run IDself.handle_requires_action(event.data, run_id)def handle_requires_action(self, data, run_id):tool_outputs = []for tool in data.required_action.submit_tool_outputs.tool_calls:arguments = json.loads(tool.function.arguments)print(f"{tool.function.name}({arguments})",flush=True)# 运行 functiontool_outputs.append({"tool_call_id": tool.id,"output": available_functions[tool.function.name](**arguments)})# 提交 function 的结果，并继续运行 runself.submit_tool_outputs(tool_outputs, run_id)def submit_tool_outputs(self, tool_outputs, run_id):"""提交function结果，并继续流"""with client.beta.threads.runs.submit_tool_outputs_stream(thread_id=self.current_run.thread_id,run_id=self.current_run.id,tool_outputs=tool_outputs,event_handler=EventHandler(),) as stream:stream.until_done()

# 创建 thread
thread = client.beta.threads.create()# 添加 user message
message = client.beta.threads.messages.create(thread_id=thread.id,role="user",content="平均一堂课多长时间",
)
# 使用 stream 接口并传入 EventHandler
with client.beta.threads.runs.stream(thread_id=thread.id,assistant_id=assistant_id,event_handler=EventHandler(),
) as stream:stream.until_done()

两个无依赖的 function 会在一次请求中一起被调用

# 创建 thread
thread = client.beta.threads.create()# 添加 user message
message = client.beta.threads.messages.create(thread_id=thread.id,role="user",content="张三上几堂课，比李四多上几堂",
)
# 使用 stream 接口并传入 EventHandler
with client.beta.threads.runs.stream(thread_id=thread.id,assistant_id=assistant_id,event_handler=EventHandler(),
) as stream:stream.until_done()

assistant > functionassistant > functionask_database({'query': "SELECT COUNT(*) AS count FROM Courses WHERE instructor = '张三';"})
ask_database({'query': "SELECT COUNT(*) AS count FROM Courses WHERE instructor = '李四';"})assistant > 张三上了4堂课，而李四上了1堂课。因此，张三比李四多上了3堂课。

更多流中的 Event： https://platform.openai.com/docs/api-reference/assistants-streaming/events