OpenAI 在其 API 中引入了结构化输出功能,这意味着模型的输出可以可靠地遵循开发人员提供的 JSON 模式。
对复杂 JSON 模式进行评估时,具有结构化输出的新模型 gpt-4o-2024-08-06 得分为 100%。相比之下,gpt-4-0613 得分不到 40%。
这一功能包括两种形式:
- 函数调用:通过在函数定义中设置
strict: true
可以使用工具的结构化输出。此功能适用于支持工具的所有型号大模型,包括所有型号 gpt-4-0613 和 gpt-3.5-turbo-0613 及更高版本。启用结构化输出后,模型输出将与提供的工具定义匹配。 -
response_format
参数新选项:开发人员现在可以使用新参数 JSON 模式json_schema
。此功能适用于最新的 GPT-4o 模型:gpt-4o-2024-08-06
、gpt-4o-mini-2024-07-18
。当response_format
设定strict: true
,模型输出将与提供的模式匹配。
函数调用通过在函数定义中设置结构化输出,使模型输出与提供的工具定义相匹配,适用于所有支持工具的模型。参数 response_format
允许开发人员通过提供 JSON 模式来约束模型的响应格式,适用于最新的 GPT-4o 模型。此外,新的结构化输出功能遵循 OpenAI 的安全政策,允许模型拒绝不安全的请求,并通过新的字符串值 refusal
在 API 响应中允许开发人员以编程方式检测模型的拒绝。
同时 OpenAI 还提供了原生 SDK 支持结构化输出,包括 Python 和 Node SDK,简化了开发过程。结构化输出还支持从非结构化数据中提取结构化数据,如会议记录中的待办事项和截止日期。为了实现这一功能,OpenAI 采用了基于上下文无关语法 (CFG) 的受限解码方法,而不是传统的有限状态机 (FSM) 或正则表达式,以处理更复杂的嵌套或递归数据结构。具体原理可以查看官方博客深入了解:https://openai.com/index/introducing-structured-outputs-in-the-api
结构化输出目前已在 API 中正式推出,支持所有支持函数调用的模型,包括 GPT-4o 和 GPT-4o-mini 系列,以及之后的所有模型。此功能还与视觉输入兼容,并且可以在 chat.completion API、助手 API 和批处理 API 上使用。结构化输出的引入有助于开发人员构建更可靠的 AI 应用程序,并且可以节省输入输出费用。
简单看一下示例:
1、Function Calling:
POST /v1/chat/completions
{
"model": "gpt-4o-2024-08-06",
"messages": [
{
"role": "system",
"content": "You are a helpful assistant. The current date is August 6, 2024. You help users query for the data they are looking for by calling the query function."
},
{
"role": "user",
"content": "look up all my orders in may of last year that were fulfilled but not delivered on time"
}
],
"tools": [
{
"type": "function",
"function": {
"name": "query",
"description": "Execute a query.",
"strict": true,
"parameters": {
"type": "object",
"properties": {
"table_name": {
"type": "string",
"enum": ["orders"]
},
"columns": {
"type": "array",
"items": {
"type": "string",
"enum": [
"id",
"status",
"expected_delivery_date",
"delivered_at",
"shipped_at",
"ordered_at",
"canceled_at"
]
}
},
"conditions": {
"type": "array",
"items": {
"type": "object",
"properties": {
"column": {
"type": "string"
},
"operator": {
"type": "string",
"enum": ["=", ">", "<", ">=", "<=", "!="]
},
"value": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"type": "object",
"properties": {
"column_name": {
"type": "string"
}
},
"required": ["column_name"],
"additionalProperties": false
}
]
}
},
"required": ["column", "operator", "value"],
"additionalProperties": false
}
},
"order_by": {
"type": "string",
"enum": ["asc", "desc"]
}
},
"required": ["table_name", "columns", "conditions", "order_by"],
"additionalProperties": false
}
}
}
]
}
格式化输出:
{
"table_name": "orders",
"columns": ["id", "status", "expected_delivery_date", "delivered_at"],
"conditions": [
{
"column": "status",
"operator": "=",
"value": "fulfilled"
},
{
"column": "ordered_at",
"operator": ">=",
"value": "2023-05-01"
},
{
"column": "ordered_at",
"operator": "<",
"value": "2023-06-01"
},
{
"column": "delivered_at",
"operator": ">",
"value": {
"column_name": "expected_delivery_date"
}
}
],
"order_by": "asc"
}
2、response_format
参数方式:
POST /v1/chat/completions
{
"model": "gpt-4o-2024-08-06",
"messages": [
{
"role": "system",
"content": "You are a helpful math tutor."
},
{
"role": "user",
"content": "solve 8x + 31 = 2"
}
],
"response_format": {
"type": "json_schema",
"json_schema": {
"name": "math_response",
"strict": true,
"schema": {
"type": "object",
"properties": {
"steps": {
"type": "array",
"items": {
"type": "object",
"properties": {
"explanation": {
"type": "string"
},
"output": {
"type": "string"
}
},
"required": ["explanation", "output"],
"additionalProperties": false
}
},
"final_answer": {
"type": "string"
}
},
"required": ["steps", "final_answer"],
"additionalProperties": false
}
}
}
}
格式化输出:
{
"steps": [
{
"explanation": "Subtract 31 from both sides to isolate the term with x.",
"output": "8x + 31 - 31 = 2 - 31"
},
{
"explanation": "This simplifies to 8x = -29.",
"output": "8x = -29"
},
{
"explanation": "Divide both sides by 8 to solve for x.",
"output": "x = -29 / 8"
}
],
"final_answer": "x = -29 / 8"
}
最后再来看一下当前世面上的一些格式化输出框架: