💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
Python agentsaiai-agentsembeddingsinformation-retrievallanguage-modellarge-language-modelsllmnlppythonragretrieval-augmented-generationsearchsearch-enginesemantic-searchsentence-embeddingstransformerstxtaivector-databasevector-search
"""
Entity module tests
"""
import unittest
from txtai.pipeline import Entity
class TestEntity(unittest.TestCase):
"""
Entity tests.
"""
@classmethod
def setUpClass(cls):
"""
Create entity instance.
"""
cls.entity = Entity("dslim/bert-base-NER")
def testEntity(self):
"""
Test entity
"""
# Run entity extraction
entities = self.entity("Canada's last fully intact ice shelf has suddenly collapsed, forming a Manhattan-sized iceberg")
self.assertEqual([e[0] for e in entities], ["Canada", "Manhattan"])
def testEntityFlatten(self):
"""
Test entity with flattened output
"""
# Test flatten
entities = self.entity("Canada's last fully intact ice shelf has suddenly collapsed, forming a Manhattan-sized iceberg", flatten=True)
self.assertEqual(entities, ["Canada", "Manhattan"])
# Test flatten with join
entities = self.entity(
"Canada's last fully intact ice shelf has suddenly collapsed, forming a Manhattan-sized iceberg", flatten=True, join=True
)
self.assertEqual(entities, "Canada Manhattan")
def testEntityZeroThreshold(self):
"""
Test zero-threshold flattened and joined entity outputs
"""
text = "Canada's last fully intact ice shelf has suddenly collapsed, forming a Manhattan-sized iceberg"
self.assertEqual(self.entity(text, flatten=0.0), ["Canada", "Manhattan"])
self.assertEqual(self.entity([text], flatten=0.0), [["Canada", "Manhattan"]])
self.assertEqual(self.entity(text, flatten=0.0, join=True), "Canada Manhattan")
self.assertEqual(self.entity(text, labels=["LOC"], flatten=0.0), ["Canada"])
# Boolean False keeps scored tuples, even when joining is requested.
self.assertEqual(self.entity(text, flatten=False, join=True), self.entity(text))
def testEntityTypes(self):
"""
Test entity type filtering
"""
# Run entity extraction
entities = self.entity("Canada's last fully intact ice shelf has suddenly collapsed, forming a Manhattan-sized iceberg", labels=["PER"])
self.assertFalse(entities)
def testGliner(self):
"""
Test entity pipeline with a GLiNER model
"""
entity = Entity("neuml/gliner-bert-tiny")
entities = entity("My name is John Smith.", flatten=True)
self.assertEqual(entities, ["John Smith"])