Assistants API
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:
- 更多技术路线选择:原生 API、GPTs 和 Assistants API
- GPTs 的示范,起到教育客户的作用,有助于打开市场
- 要更大自由度,需要用 Assistants API 开发
- 想极致调优,还得原生 API + RAG
0.3、Assistants API 的主要能力
- 创建和管理 assistant,每个 assistant 有独立的配置
- 支持无限长的多轮对话,对话历史保存在 OpenAI 的服务器上
- 通过自有向量数据库支持基于文件的 RAG
- 支持 Code Interpreter
- 在沙箱里编写并运行 Python 代码
- 自我修正代码
- 可传文件给 Code Interpreter
- 支持 Function Calling
- 支持在线调试的 Playground
收费:
- 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
- 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
- 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
- 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:
- 更方便调整
- 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:
- Threads 里保存的是对话历史,即 messages
- 一个 assistant 可以有多个 thread
- 一个 thread 可以有无限条 message
- 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:
threads.modify()
修改 thread 的metadata
和tool_resources
threads.retrieve()
获取 threadthreads.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:
- 不仅有文本,还可以有图片和文件
- 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:
threads.messages.retrieve()
获取 messagethreads.messages.update()
更新 message 的metadata
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": {},