请求
将工单作为state 发送，并为每个决策提出一个问题。问题名称（queue、urgency、needs_human）由你定义，它们会作为 answers 下的键返回。
curl -X POST https://api.fastino.ai/v1/systemone \
-H "X-API-Key: $FASTINO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "fastino/GLiDE",
"state": {
"subject": "Charged twice this month??",
"plan": "Pro, 14 seats",
"message": "Our card was billed $1,190 twice on Oct 1. Finance wants it fixed today before they freeze the card. The invoice download button just spins, too."
},
"questions": {
"queue": {
"type": "choice",
"instructions": "Which support queue should this ticket go to?",
"criteria": {
"billing": "Charges, refunds, and invoices",
"technical": "Something in the product is broken",
"account": "Logins, seats, and permissions"
}
},
"urgency": {
"type": "score",
"instructions": "How urgent is this ticket?",
"criteria": [
"Low: no deadline or business impact",
"Normal: needs an answer within a few days",
"High: blocks money or work today",
"Urgent: an outage or a security incident"
]
},
"needs_human": {
"type": "noul",
"instructions": "Should a person reply instead of an automated assistant?",
"criteria": {
"true": "A person should reply",
"false": "An automated reply is enough"
}
}
}
}'
请求 schema
| 字段 | 类型 | 在本示例中 |
|---|---|---|
model | string | fastino/GLiDE。 |
state | string、object 或 array | 工单内容。使用对象可以让主题、套餐和消息保持清晰的标签。 |
questions.queue | Choice | criteria 是一个对象。每个键是一个结果，每个值说明该结果何时适用。 |
questions.urgency | Score | criteria 是一个有序数组，最低级别在前。 |
questions.needs_human | Noul | 一个是/否问题。criteria 描述 true 和 false 两侧。 |
questions.*.instructions | string | GLiDE 针对 state 回答的问题。 |
响应
基于https://api.fastino.ai 实测。置信度值在不同调用之间会略有差异。
{
"model": "glide_v2",
"answers": {
"queue": {
"type": "choice",
"choice": "billing",
"confidence": 0.993,
"probabilities": {
"billing": 0.996,
"technical": 0.004,
"account": 0.0
}
},
"urgency": {
"type": "score",
"score": 2,
"expected_level": 2.001,
"confidence": 0.991,
"probabilities": {
"0": 0.0,
"1": 0.002,
"2": 0.994,
"3": 0.004
},
"legend": {
"0": "Low: no deadline or business impact",
"1": "Normal: needs an answer within a few days",
"2": "High: blocks money or work today",
"3": "Urgent: an outage or a security incident"
}
},
"needs_human": {
"type": "noul",
"noul": 0.987,
"confidence": 0.974
}
},
"usage": {
"input_tokens": 422,
"output_tokens": 0
}
}
响应 schema
| 字段 | 类型 | 含义 |
|---|---|---|
answers.queue.choice | string | 胜出的 criteria 键。此处为 billing。 |
answers.queue.probabilities | object | 每个结果的概率，总和为 1。 |
answers.urgency.score | integer | 胜出级别的索引，从 0 开始计数。此处 2 表示 “High”。 |
answers.urgency.expected_level | number | 按概率加权的级别，可用于比 score 更精细的阈值。 |
answers.urgency.legend | object | 你提供的级别描述，以索引为键。 |
answers.needs_human.noul | number | true 一侧成立的概率，范围为 0 到 1。 |
answers.*.confidence | number | GLiDE 对该答案的确定程度，范围为 0 到 1。 |
usage.input_tokens | integer | 该请求计费的 token 数。 |
根据答案执行操作
import os
import requests
response = requests.post(
"https://api.fastino.ai/v1/systemone",
headers={"X-API-Key": os.environ["FASTINO_API_KEY"]},
json=body, # the request body above
timeout=300,
)
response.raise_for_status()
answers = response.json()["answers"]
queue = answers["queue"]
urgency = answers["urgency"]["score"]
needs_human = answers["needs_human"]["noul"] >= 0.5
if queue["confidence"] < 0.7:
queue_name = "general" # let a person pick the queue
else:
queue_name = queue["choice"]
priority = {0: "low", 1: "normal", 2: "high", 3: "urgent"}[urgency]
assign(ticket, queue=queue_name, priority=priority, auto_reply=not needs_human)
0.7 和 0.5 阈值作为起点，并用你自己的工单样本进行检验。
调整示例
- 使用真实的队列名称作为
criteria键，并描述每个队列负责的内容。决定效果的是这些描述。 - 可以自由增减紧急程度级别。响应始终按你发送的顺序从
0开始为其编号。 - 将 GLiDE 应考虑的客户事实（例如套餐、合同等级或未结事件）放入
state。 - 在同一请求中提出更多问题，例如
language或sentiment。每个问题都会在answers中增加一项。
分类指南
设计 Choice 问题并处理不确定的标签。
GLiDE API 参考
POST /v1/systemone 的所有字段、限制和错误。