Relations & Classification

GLiREL and GLiClass models extract relationships and classify text with zero-shot label support.

Relation Extraction

GLiREL models extract relationships between entities. Relation types are passed via the labels parameter. Entities must be pre-extracted (e.g. with GLiNER) and passed in item.metadata:

Python

from sie_sdk import SIEClient
from sie_sdk.types import Item

client = SIEClient("http://localhost:8080")

text = "Tim Cook is the CEO of Apple Inc."

# Step 1: Extract entities with GLiNER
ner_result = client.extract(
    "urchade/gliner_multi-v2.1",
    Item(text=text),
    labels=["person", "organization"]
)

# Step 2: Pass entities to GLiREL for relation extraction
result = client.extract(
    "jackboyla/glirel-large-v0",
    Item(text=text, metadata={"entities": ner_result["entities"]}),
    labels=["works_for", "ceo_of", "founded"]
)

for relation in result["relations"]:
    print(f"{relation['head']} --{relation['relation']}--> {relation['tail']}")
# Tim Cook --ceo_of--> Apple Inc.

TypeScript

// The TypeScript SDK does not yet support relation extraction.
// Use the Python SDK or the HTTP API directly:

const text = "Tim Cook is the CEO of Apple Inc.";

// Step 1: Extract entities with GLiNER
const nerResponse = await fetch("http://localhost:8080/v1/extract/urchade/gliner_multi-v2.1", {
  method: "POST",
  headers: { "Content-Type": "application/json", "Accept": "application/json" },
  body: JSON.stringify({
    items: [{ text }],
    params: { labels: ["person", "organization"] },
  }),
});
const nerData = await nerResponse.json();

// Step 2: Pass entities to GLiREL for relation extraction
const response = await fetch("http://localhost:8080/v1/extract/jackboyla/glirel-large-v0", {
  method: "POST",
  headers: { "Content-Type": "application/json", "Accept": "application/json" },
  body: JSON.stringify({
    items: [{ text, metadata: { entities: nerData.items[0].entities } }],
    params: { labels: ["works_for", "ceo_of", "founded"] },
  }),
});

const data = await response.json();
for (const relation of data.items[0].relations) {
  console.log(`${relation.head} --${relation.relation}--> ${relation.tail}`);
}
// Tim Cook --ceo_of--> Apple Inc.

Relation Fields

Field	Type	Description
head	str	Source entity
tail	str	Target entity
relation	str	Relation type
score	float	Confidence score

Text Classification

GLiClass models classify text into categories:

Python

result = client.extract(
    "knowledgator/gliclass-base-v1.0",
    Item(text="I absolutely loved this movie! The acting was superb."),
    labels=["positive", "negative", "neutral"]
)

for classification in result["classifications"]:
    print(f"{classification['label']}: {classification['score']:.2f}")
# positive: 0.94
# neutral: 0.04
# negative: 0.02

TypeScript

const result = await client.extract(
  "knowledgator/gliclass-base-v1.0",
  { text: "I absolutely loved this movie! The acting was superb." },
  { labels: ["positive", "negative", "neutral"] }
);

// Classification results are returned as entities with label scores
for (const entity of result.entities) {
  console.log(`${entity.label}: ${entity.score.toFixed(2)}`);
}
// positive: 0.94
// neutral: 0.04
// negative: 0.02

Recommended Models

NER Models

Model	Languages	Notes
urchade/gliner_multi-v2.1	Multilingual	General-purpose NER
urchade/gliner_large-v2.1	English	Larger model (459M params)
numind/NuNER_Zero	English	Zero-shot NER
urchade/gliner_multi_pii-v1	Multilingual	PII detection

Classification Models

Model	Notes
knowledgator/gliclass-base-v1.0	Zero-shot classification
knowledgator/gliclass-small-v1.0	Faster, smaller

See Full model catalog for the complete list.

What’s Next

• NER & Entity Extraction — named entity recognition
• Vision Tasks — image captioning, OCR, and document understanding
• Full model catalog — all supported models