想学做网站 应该学宁波人才网

一、前言

0.1、从轰动一时的 OpenAI DevDay 说起

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

这一波操作一度被认为是创业公司终结者

0.2、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

0.3、Assistants API 的主要能力

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

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

二、Assistants API

!pip install --upgrade openai

2.1、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。

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="AGIClass Demo",instructions="你叫瓜瓜，你是AGI课堂的智能助理。你负责回答与AGI课堂有关的问题。",model="gpt-4o",
)
print(assistant.id)

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

asst_xi4KvqarumvNarFA2jdwmzkb

2.2、样例 Assistant 的配置

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。

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"]}
}

三、代码访问 Assistant

3.1、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_OARH7c8gXNgOWE3jBVhBkBjh","created_at": 1723097175,"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": "wzr"}
)
show_json(thread)

{"id": "thread_yHexybuAqnucf8qfrPflETEf","created_at": 1723097179,"metadata": {"fullname": "王卓然","username": "wzr"},"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_yHexybuAqnucf8qfrPflETEf","created_at": 1723097179,"metadata": {"fullname": "王卓然","username": "wzr"},"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

3.2、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_srQF1npndSQGbPHpPenRLmuN","assistant_id": null,"attachments": [],"completed_at": null,"content": [{"text": {"annotations": [],"value": "你都能做什么？"},"type": "text"}],"created_at": 1723097207,"incomplete_at": null,"incomplete_details": null,"metadata": {},"object": "thread.message","role": "user","run_id": null,"status": null,"thread_id": "thread_yHexybuAqnucf8qfrPflETEf"
}

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_OutYgPBocoMQL0U9nbSET469","created_at": 1723097223,"metadata": {},"object": "thread","tool_resources": {"code_interpreter": null,"file_search": null}
}
-----
{"data": [{"id": "msg_JvbHlkhDNuScmJRroev14ITO","assistant_id": null,"attachments": [],"completed_at": null,"content": [{"text": {"annotations": [],"value": "你是谁？"},"type": "text"}],"created_at": 1723097223,"incomplete_at": null,"incomplete_details": null,"metadata": {},"object": "thread.message","role": "user","run_id": null,"status": null,"thread_id": "thread_OutYgPBocoMQL0U9nbSET469"},{"id": "msg_6zAx2bWsTHhBFSdfn8vPnTWk","assistant_id": null,"attachments": [],"completed_at": null,"content": [{"text": {"annotations": [],"value": "有什么可以帮您？"},"type": "text"}],"created_at": 1723097223,"incomplete_at": null,"incomplete_details": null,"metadata": {},"object": "thread.message","role": "assistant","run_id": null,"status": null,"thread_id": "thread_OutYgPBocoMQL0U9nbSET469"},{"id": "msg_CLea9Quz8CeLXQBWBlwVvPm0","assistant_id": null,"attachments": [],"completed_at": null,"content": [{"text": {"annotations": [],"value": "你好"},"type": "text"}],"created_at": 1723097223,"incomplete_at": null,"incomplete_details": null,"metadata": {},"object": "thread.message","role": "user","run_id": null,"status": null,"thread_id": "thread_OutYgPBocoMQL0U9nbSET469"}],"object": "list","first_id": "msg_JvbHlkhDNuScmJRroev14ITO","last_id": "msg_CLea9Quz8CeLXQBWBlwVvPm0","has_more": false
}

3.3、开始 Run

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

3.1、直接运行

assistant_id = "asst_VtH1Ty9fCMzs5wPQxfNR5d0v"  # 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)

{"data": [{"id": "msg_BVhyxciLowMUtYRRLAuSycX6","assistant_id": "asst_VtH1Ty9fCMzs5wPQxfNR5d0v","attachments": [],"completed_at": null,"content": [{"text": {"annotations": [],"value": "我是瓜瓜，AGI课堂的智能助理。我可以帮助你解答与AGI课堂相关的问题，包括课程安排、内容查询等。如果你有任何问题，请随时告诉我！"},"type": "text"}],"created_at": 1723097246,"incomplete_at": null,"incomplete_details": null,"metadata": {},"object": "thread.message","role": "assistant","run_id": "run_EVqVA1PrpvxMHkUz8r6fTIpf","status": null,"thread_id": "thread_OutYgPBocoMQL0U9nbSET469"},{"id": "msg_JvbHlkhDNuScmJRroev14ITO","assistant_id": null,"attachments": [],"completed_at": null,"content": [{"text": {"annotations": [],"value": "你是谁？"},"type": "text"}],"created_at": 1723097223,"incomplete_at": null,"incomplete_details": null,"metadata": {},"object": "thread.message","role": "user","run_id": null,"status": null,"thread_id": "thread_OutYgPBocoMQL0U9nbSET469"},{"id": "msg_6zAx2bWsTHhBFSdfn8vPnTWk","assistant_id": null,"attachments": [],"completed_at": null,"content": [{"text": {"annotations": [],"value": "有什么可以帮您？"},"type": "text"}],"created_at": 1723097223,"incomplete_at": null,"incomplete_details": null,"metadata": {},"object": "thread.message","role": "assistant","run_id": null,"status": null,"thread_id": "thread_OutYgPBocoMQL0U9nbSET469"},{"id": "msg_CLea9Quz8CeLXQBWBlwVvPm0","assistant_id": null,"attachments": [],"completed_at": null,"content": [{"text": {"annotations": [],"value": "你好"},"type": "text"}],"created_at": 1723097223,"incomplete_at": null,"incomplete_details": null,"metadata": {},