请求
curl -X POST https://api.fastino.ai/v1/chat/completions \
-H "Authorization: Bearer $FASTINO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "fastino/gliner2.5-multi-v1",
"messages": [
{
"role": "user",
"content": "Lena Vogel works for Siemens in Munich. Siemens acquired Altair Engineering in 2025."
}
],
"schema": {
"entities": [
{
"name": "person",
"description": "full name of a person"
},
{
"name": "organization",
"description": "company or institution"
},
{
"name": "location",
"description": "city or country"
}
],
"relations": {
"works_for": {
"description": "a person is employed by an organization"
},
"located_in": {
"description": "an organization or person is based in a place"
},
"acquired": {
"description": "one organization bought another"
}
}
},
"threshold": 0.5,
"store": false
}'
请求 schema
| 字段 | 类型 | 在本示例中 |
|---|---|---|
model | string | fastino/gliner2.5-multi-v1。 |
messages | array | 一条包含待读取文本的 user 消息。 |
schema.entities | array | 关系所连接的实体标签。 |
schema.relations | object | 每种关系类型一个键。description 说明该关系的含义，包括其方向。 |
threshold | number | 最低置信度，范围为 0 到 1。默认值为 0.5。 |
store | boolean | 默认为 true，即保存本次推理。设为 false 可选择不保存。 |
响应
GLiNER 以 JSON 字符串的形式在choices[0].message.content 中返回结果。解析后如下所示。基于 https://api.fastino.ai 实测；置信度值在不同调用之间会略有差异。
{
"entities": {
"person": [
{
"text": "Lena Vogel",
"confidence": 1.0,
"start": 0,
"end": 10
}
],
"organization": [
{
"text": "Siemens",
"confidence": 0.996,
"start": 21,
"end": 28
},
{
"text": "Siemens",
"confidence": 0.992,
"start": 40,
"end": 47
},
{
"text": "Altair Engineering",
"confidence": 0.973,
"start": 57,
"end": 75
}
],
"location": [
{
"text": "Munich",
"confidence": 1.0,
"start": 32,
"end": 38
}
]
},
"relation_extraction": {
"works_for": [
{
"head": {
"text": "Lena Vogel",
"start": 0,
"end": 10,
"confidence": 0.988
},
"tail": {
"text": "Siemens",
"start": 21,
"end": 28,
"confidence": 0.988
}
}
],
"located_in": [
{
"head": {
"text": "Siemens",
"start": 40,
"end": 47,
"confidence": 0.977
},
"tail": {
"text": "Munich",
"start": 32,
"end": 38,
"confidence": 0.977
}
}
],
"acquired": [
{
"head": {
"text": "Siemens",
"start": 40,
"end": 47,
"confidence": 0.938
},
"tail": {
"text": "Altair Engineering",
"start": 57,
"end": 75,
"confidence": 0.938
}
}
]
}
}
响应 schema
| 字段 | 类型 | 含义 |
|---|---|---|
relation_extraction | object | 你定义的每种关系类型对应一个键。 |
relation_extraction.<type>[].head | object | 关系的起点实体，包含 text、confidence、start 和 end。 |
relation_extraction.<type>[].tail | object | 关系指向的实体，包含相同的字段。 |
relation_extraction 下，而不是 relations 下。
根据答案执行操作
import json
result = json.loads(response.json()["choices"][0]["message"]["content"])
facts = [
(pair["head"]["text"], relation, pair["tail"]["text"])
for relation, pairs in result["relation_extraction"].items()
for pair in pairs
if min(pair["head"]["confidence"], pair["tail"]["confidence"]) >= 0.5
]
for head, relation, tail in facts:
graph.add_edge(head, tail, type=relation)
调整示例
- 在每条描述中说明方向，例如 “a person is employed by an organization”，使头实体和尾实体的方向正确。
- 为关系所连接的每类事物定义实体标签，使结果中的实体带有类型。
- 调优时降低
threshold以查看近似匹配，然后在代码中按头实体和尾实体的置信度进行过滤。 - 为每条事实保存
start和end，以便追溯到其来源句子。
调用 GLiNER
所有 GLiNER schema 类型及其结果的读取方式。
Chat Completions API 参考
POST /v1/chat/completions 的所有字段、限制和错误。