from gliner2 import GLiNER2 # Load model once, use everywhere extractor = GLiNER2.from_pretrained("fastino/gliner2-base-v1") # Extract entities in one line text = "Apple CEO Tim Cook announced iPhone 15 in Cupertino yesterday." result = extractor.extract_entities(text, ["company", "person", "product", "location"]) print(result) # {'entities': {'company': ['Apple'], 'person': ['Tim Cook'], 'product': ['iPhone 15'], 'location': ['Cupertino']}}

# fp16 model = GLiNER2.from_pretrained("fastino/gliner2-base-v1", map_location="cuda", quantize=True) # torch.compile (fused GPU kernels, first call triggers tracing) model = GLiNER2.from_pretrained("fastino/gliner2-base-v1", map_location="cuda", compile=True) # Both model = GLiNER2.from_pretrained("fastino/gliner2-base-v1", map_location="cuda", quantize=True, compile=True) # Or after loading model.quantize() model.compile()

from gliner2 import GLiNER2 # Access GLiNER XL 1B via API extractor = GLiNER2.from_api() # Uses PIONEER_API_KEY env variable result = extractor.extract_entities( "OpenAI CEO Sam Altman announced GPT-5 at their San Francisco headquarters.", ["company", "person", "product", "location"] ) # {'entities': {'company': ['OpenAI'], 'person': ['Sam Altman'], 'product': ['GPT-5'], 'location': ['San Francisco']}}

# Basic entity extraction entities = extractor.extract_entities( "Patient received 400mg ibuprofen for severe headache at 2 PM.", ["medication", "dosage", "symptom", "time"] ) # Output: {'entities': {'medication': ['ibuprofen'], 'dosage': ['400mg'], 'symptom': ['severe headache'], 'time': ['2 PM']}} # Enhanced with descriptions for medical accuracy entities = extractor.extract_entities( "Patient received 400mg ibuprofen for severe headache at 2 PM.", { "medication": "Names of drugs, medications, or pharmaceutical substances", "dosage": "Specific amounts like '400mg', '2 tablets', or '5ml'", "symptom": "Medical symptoms, conditions, or patient complaints", "time": "Time references like '2 PM', 'morning', or 'after lunch'" } ) # Same output but with higher accuracy due to context descriptions # With confidence scores entities = extractor.extract_entities( "Apple Inc. CEO Tim Cook announced iPhone 15 in Cupertino.", ["company", "person", "product", "location"], include_confidence=True ) # Output: { # 'entities': { # 'company': [{'text': 'Apple Inc.', 'confidence': 0.95}], # 'person': [{'text': 'Tim Cook', 'confidence': 0.92}], # 'product': [{'text': 'iPhone 15', 'confidence': 0.88}], # 'location': [{'text': 'Cupertino', 'confidence': 0.90}] # } # } # With character positions (spans) entities = extractor.extract_entities( "Apple Inc. CEO Tim Cook announced iPhone 15 in Cupertino.", ["company", "person", "product"], include_spans=True ) # Output: { # 'entities': { # 'company': [{'text': 'Apple Inc.', 'start': 0, 'end': 9}], # 'person': [{'text': 'Tim Cook', 'start': 15, 'end': 23}], # 'product': [{'text': 'iPhone 15', 'start': 35, 'end': 44}] # } # } # With both confidence and spans entities = extractor.extract_entities( "Apple Inc. CEO Tim Cook announced iPhone 15 in Cupertino.", ["company", "person", "product"], include_confidence=True, include_spans=True ) # Output: { # 'entities': { # 'company': [{'text': 'Apple Inc.', 'confidence': 0.95, 'start': 0, 'end': 9}], # 'person': [{'text': 'Tim Cook', 'confidence': 0.92, 'start': 15, 'end': 23}], # 'product': [{'text': 'iPhone 15', 'confidence': 0.88, 'start': 35, 'end': 44}] # } # }

# Sentiment analysis result = extractor.classify_text( "This laptop has amazing performance but terrible battery life!", {"sentiment": ["positive", "negative", "neutral"]} ) # Output: {'sentiment': 'negative'} # Multi-aspect classification result = extractor.classify_text( "Great camera quality, decent performance, but poor battery life.", { "aspects": { "labels": ["camera", "performance", "battery", "display", "price"], "multi_label": True, "cls_threshold": 0.4 } } ) # Output: {'aspects': ['camera', 'performance', 'battery']} # With confidence scores result = extractor.classify_text( "This laptop has amazing performance but terrible battery life!", {"sentiment": ["positive", "negative", "neutral"]}, include_confidence=True ) # Output: {'sentiment': {'label': 'negative', 'confidence': 0.82}} # Multi-label with confidence schema = extractor.create_schema().classification( "topics", ["technology", "business", "health", "politics", "sports"], multi_label=True, cls_threshold=0.3 ) text = "Apple announced new health monitoring features in their latest smartwatch, boosting their stock price." results = extractor.extract(text, schema, include_confidence=True) # Output: { # 'topics': [ # {'label': 'technology', 'confidence': 0.92}, # {'label': 'business', 'confidence': 0.78}, # {'label': 'health', 'confidence': 0.65} # ] # }

# Product information extraction text = "iPhone 15 Pro Max with 256GB storage, A17 Pro chip, priced at $1199. Available in titanium and black colors." result = extractor.extract_json( text, { "product": [ "name::str::Full product name and model", "storage::str::Storage capacity like 256GB or 1TB", "processor::str::Chip or processor information", "price::str::Product price with currency", "colors::list::Available color options" ] } ) # Output: { # 'product': [{ # 'name': 'iPhone 15 Pro Max', # 'storage': '256GB',  # 'processor': 'A17 Pro chip', # 'price': '$1199', # 'colors': ['titanium', 'black'] # }] # } # Multiple structured entities text = "Apple Inc. headquarters in Cupertino launched iPhone 15 for $999 and MacBook Air for $1299." result = extractor.extract_json( text, { "company": [ "name::str::Company name", "location::str::Company headquarters or office location" ], "products": [ "name::str::Product name and model", "price::str::Product retail price" ] } ) # Output: { # 'company': [{'name': 'Apple Inc.', 'location': 'Cupertino'}], # 'products': [ # {'name': 'iPhone 15', 'price': '$999'}, # {'name': 'MacBook Air', 'price': '$1299'} # ] # } # With confidence scores result = extractor.extract_json( "The MacBook Pro costs $1999 and features M3 chip, 16GB RAM, and 512GB storage.", { "product": [ "name::str", "price", "features" ] }, include_confidence=True ) # Output: { # 'product': [{ # 'name': {'text': 'MacBook Pro', 'confidence': 0.95}, # 'price': [{'text': '$1999', 'confidence': 0.92}], # 'features': [ # {'text': 'M3 chip', 'confidence': 0.88}, # {'text': '16GB RAM', 'confidence': 0.90}, # {'text': '512GB storage', 'confidence': 0.87} # ] # }] # } # With character positions (spans) result = extractor.extract_json( "The MacBook Pro costs $1999 and features M3 chip.", { "product": [ "name::str", "price" ] }, include_spans=True ) # Output: { # 'product': [{ # 'name': {'text': 'MacBook Pro', 'start': 4, 'end': 15}, # 'price': [{'text': '$1999', 'start': 22, 'end': 27}] # }] # } # With both confidence and spans result = extractor.extract_json( "The MacBook Pro costs $1999 and features M3 chip, 16GB RAM, and 512GB storage.", { "product": [ "name::str", "price", "features" ] }, include_confidence=True, include_spans=True ) # Output: { # 'product': [{ # 'name': {'text': 'MacBook Pro', 'confidence': 0.95, 'start': 4, 'end': 15}, # 'price': [{'text': '$1999', 'confidence': 0.92, 'start': 22, 'end': 27}], # 'features': [ # {'text': 'M3 chip', 'confidence': 0.88, 'start': 32, 'end': 39}, # {'text': '16GB RAM', 'confidence': 0.90, 'start': 41, 'end': 49}, # {'text': '512GB storage', 'confidence': 0.87, 'start': 55, 'end': 68} # ] # }] # }

# Basic relation extraction text = "John works for Apple Inc. and lives in San Francisco. Apple Inc. is located in Cupertino." result = extractor.extract_relations( text, ["works_for", "lives_in", "located_in"] ) # Output: { # 'relation_extraction': { # 'works_for': [('John', 'Apple Inc.')], # 'lives_in': [('John', 'San Francisco')], # 'located_in': [('Apple Inc.', 'Cupertino')] # } # } # With descriptions for better accuracy schema = extractor.create_schema().relations({ "works_for": "Employment relationship where person works at organization", "founded": "Founding relationship where person created organization", "acquired": "Acquisition relationship where company bought another company", "located_in": "Geographic relationship where entity is in a location" }) text = "Elon Musk founded SpaceX in 2002. SpaceX is located in Hawthorne, California." results = extractor.extract(text, schema) # Output: { # 'relation_extraction': { # 'founded': [('Elon Musk', 'SpaceX')], # 'located_in': [('SpaceX', 'Hawthorne, California')] # } # } # With confidence scores results = extractor.extract_relations( "John works for Apple Inc. and lives in San Francisco.", ["works_for", "lives_in"], include_confidence=True ) # Output: { # 'relation_extraction': { # 'works_for': [{ # 'head': {'text': 'John', 'confidence': 0.95}, # 'tail': {'text': 'Apple Inc.', 'confidence': 0.92} # }], # 'lives_in': [{ # 'head': {'text': 'John', 'confidence': 0.94}, # 'tail': {'text': 'San Francisco', 'confidence': 0.91} # }] # } # } # With character positions (spans) results = extractor.extract_relations( "John works for Apple Inc. and lives in San Francisco.", ["works_for", "lives_in"], include_spans=True ) # Output: { # 'relation_extraction': { # 'works_for': [{ # 'head': {'text': 'John', 'start': 0, 'end': 4}, # 'tail': {'text': 'Apple Inc.', 'start': 15, 'end': 25} # }], # 'lives_in': [{ # 'head': {'text': 'John', 'start': 0, 'end': 4}, # 'tail': {'text': 'San Francisco', 'start': 33, 'end': 46} # }] # } # } # With both confidence and spans results = extractor.extract_relations( "John works for Apple Inc. and lives in San Francisco.", ["works_for", "lives_in"], include_confidence=True, include_spans=True ) # Output: { # 'relation_extraction': { # 'works_for': [{ # 'head': {'text': 'John', 'confidence': 0.95, 'start': 0, 'end': 4}, # 'tail': {'text': 'Apple Inc.', 'confidence': 0.92, 'start': 15, 'end': 25} # }], # 'lives_in': [{ # 'head': {'text': 'John', 'confidence': 0.94, 'start': 0, 'end': 4}, # 'tail': {'text': 'San Francisco', 'confidence': 0.91, 'start': 33, 'end': 46} # }] # } # }

# Use create_schema() for multi-task scenarios schema = (extractor.create_schema() # Extract key entities .entities({ "person": "Names of people, executives, or individuals", "company": "Organization, corporation, or business names", "product": "Products, services, or offerings mentioned" }) # Classify the content .classification("sentiment", ["positive", "negative", "neutral"]) .classification("category", ["technology", "business", "finance", "healthcare"]) # Extract relationships .relations(["works_for", "founded", "located_in"]) # Extract structured product details .structure("product_info") .field("name", dtype="str") .field("price", dtype="str") .field("features", dtype="list") .field("availability", dtype="str", choices=["in_stock", "pre_order", "sold_out"]) ) # Comprehensive extraction in one pass text = "Apple CEO Tim Cook unveiled the revolutionary iPhone 15 Pro for $999. The device features an A17 Pro chip and titanium design. Tim Cook works for Apple, which is located in Cupertino." results = extractor.extract(text, schema) # Output: { # 'entities': { # 'person': ['Tim Cook'],  # 'company': ['Apple'],  # 'product': ['iPhone 15 Pro'] # }, # 'sentiment': 'positive', # 'category': 'technology', # 'relation_extraction': { # 'works_for': [('Tim Cook', 'Apple')], # 'located_in': [('Apple', 'Cupertino')] # }, # 'product_info': [{ # 'name': 'iPhone 15 Pro', # 'price': '$999', # 'features': ['A17 Pro chip', 'titanium design'], # 'availability': 'in_stock' # }] # }

financial_text = """ Transaction Report: Goldman Sachs processed a $2.5M equity trade for Tesla Inc.  on March 15, 2024. Commission: $1,250. Status: Completed. """ # Extract structured financial data result = extractor.extract_json( financial_text, { "transaction": [ "broker::str::Financial institution or brokerage firm", "amount::str::Transaction amount with currency", "security::str::Stock, bond, or financial instrument", "date::str::Transaction date", "commission::str::Fees or commission charged", "status::str::Transaction status", "type::[equity|bond|option|future|forex]::str::Type of financial instrument" ] } ) # Output: { # 'transaction': [{ # 'broker': 'Goldman Sachs', # 'amount': '$2.5M',  # 'security': 'Tesla Inc.', # 'date': 'March 15, 2024', # 'commission': '$1,250', # 'status': 'Completed', # 'type': 'equity' # }] # }

medical_record = """ Patient: Sarah Johnson, 34, presented with acute chest pain and shortness of breath. Prescribed: Lisinopril 10mg daily, Metoprolol 25mg twice daily. Follow-up scheduled for next Tuesday. """ result = extractor.extract_json( medical_record, { "patient_info": [ "name::str::Patient full name", "age::str::Patient age", "symptoms::list::Reported symptoms or complaints" ], "prescriptions": [ "medication::str::Drug or medication name", "dosage::str::Dosage amount and frequency", "frequency::str::How often to take the medication" ] } ) # Output: { # 'patient_info': [{ # 'name': 'Sarah Johnson', # 'age': '34', # 'symptoms': ['acute chest pain', 'shortness of breath'] # }], # 'prescriptions': [ # {'medication': 'Lisinopril', 'dosage': '10mg', 'frequency': 'daily'}, # {'medication': 'Metoprolol', 'dosage': '25mg', 'frequency': 'twice daily'} # ] # }

contract_text = """ Service Agreement between TechCorp LLC and DataSystems Inc., effective January 1, 2024. Monthly fee: $15,000. Contract term: 24 months with automatic renewal. Termination clause: 30-day written notice required. """ # Multi-task extraction for comprehensive analysis schema = (extractor.create_schema() .entities(["company", "date", "duration", "fee"]) .classification("contract_type", ["service", "employment", "nda", "partnership"]) .relations(["signed_by", "involves", "dated"]) .structure("contract_terms") .field("parties", dtype="list") .field("effective_date", dtype="str") .field("monthly_fee", dtype="str") .field("term_length", dtype="str") .field("renewal", dtype="str", choices=["automatic", "manual", "none"]) .field("termination_notice", dtype="str") ) results = extractor.extract(contract_text, schema) # Output: { # 'entities': { # 'company': ['TechCorp LLC', 'DataSystems Inc.'], # 'date': ['January 1, 2024'], # 'duration': ['24 months'], # 'fee': ['$15,000'] # }, # 'contract_type': 'service', # 'relation_extraction': { # 'involves': [('TechCorp LLC', 'DataSystems Inc.')], # 'dated': [('Service Agreement', 'January 1, 2024')] # }, # 'contract_terms': [{ # 'parties': ['TechCorp LLC', 'DataSystems Inc.'], # 'effective_date': 'January 1, 2024', # 'monthly_fee': '$15,000', # 'term_length': '24 months',  # 'renewal': 'automatic', # 'termination_notice': '30-day written notice' # }] # }

# Extract entities and relations for knowledge graph building text = """ Elon Musk founded SpaceX in 2002. SpaceX is located in Hawthorne, California. SpaceX acquired Swarm Technologies in 2021. Many engineers work for SpaceX. """ schema = (extractor.create_schema() .entities(["person", "organization", "location", "date"]) .relations({ "founded": "Founding relationship where person created organization", "acquired": "Acquisition relationship where company bought another company", "located_in": "Geographic relationship where entity is in a location", "works_for": "Employment relationship where person works at organization" }) ) results = extractor.extract(text, schema) # Output: { # 'entities': { # 'person': ['Elon Musk', 'engineers'], # 'organization': ['SpaceX', 'Swarm Technologies'], # 'location': ['Hawthorne, California'], # 'date': ['2002', '2021'] # }, # 'relation_extraction': { # 'founded': [('Elon Musk', 'SpaceX')], # 'acquired': [('SpaceX', 'Swarm Technologies')], # 'located_in': [('SpaceX', 'Hawthorne, California')], # 'works_for': [('engineers', 'SpaceX')] # } # }

# High-precision extraction for critical fields result = extractor.extract_json( text, { "financial_data": [ "account_number::str::Bank account number", # default threshold "amount::str::Transaction amount", # default threshold  "routing_number::str::Bank routing number" # default threshold ] }, threshold=0.9 # High confidence for all fields ) # Per-field thresholds using schema builder (for multi-task scenarios) schema = (extractor.create_schema() .structure("sensitive_data") .field("ssn", dtype="str", threshold=0.95) # Highest precision .field("email", dtype="str", threshold=0.8) # Medium precision  .field("phone", dtype="str", threshold=0.7) # Lower precision )

# Structured extraction with choices and types result = extractor.extract_json( "Premium subscription at $99/month with mobile and web access.", { "subscription": [ "tier::[basic|premium|enterprise]::str::Subscription level", "price::str::Monthly or annual cost", "billing::[monthly|annual]::str::Billing frequency", "features::[mobile|web|api|analytics]::list::Included features" ] } ) # Output: { # 'subscription': [{ # 'tier': 'premium', # 'price': '$99/month',  # 'billing': 'monthly', # 'features': ['mobile', 'web'] # }] # }

from gliner2 import GLiNER2, RegexValidator extractor = GLiNER2.from_pretrained("fastino/gliner2-base-v1") # Email validation email_validator = RegexValidator(r"^[\w\.-]+@[\w\.-]+\.\w+$") schema = (extractor.create_schema() .structure("contact") .field("email", dtype="str", validators=[email_validator]) ) text = "Contact: john@company.com, not-an-email, jane@domain.org" results = extractor.extract(text, schema) # Output: {'contact': [{'email': 'john@company.com'}]} # Only valid emails # Phone number validation (US format) phone_validator = RegexValidator(r"\(\d{3}\)\s\d{3}-\d{4}", mode="partial") schema = (extractor.create_schema() .structure("contact") .field("phone", dtype="str", validators=[phone_validator]) ) text = "Call (555) 123-4567 or 5551234567" results = extractor.extract(text, schema) # Output: {'contact': [{'phone': '(555) 123-4567'}]} # Second number filtered out # URL validation url_validator = RegexValidator(r"^https?://", mode="partial") schema = (extractor.create_schema() .structure("links") .field("url", dtype="list", validators=[url_validator]) ) text = "Visit https://example.com or www.site.com" results = extractor.extract(text, schema) # Output: {'links': [{'url': ['https://example.com']}]} # www.site.com filtered out # Exclude test data import re no_test_validator = RegexValidator(r"^(test|demo|sample)", exclude=True, flags=re.IGNORECASE) schema = (extractor.create_schema() .structure("products") .field("name", dtype="list", validators=[no_test_validator]) ) text = "Products: iPhone, Test Phone, Samsung Galaxy" results = extractor.extract(text, schema) # Output: {'products': [{'name': ['iPhone', 'Samsung Galaxy']}]} # Test Phone excluded # Multiple validators (all must pass) username_validators = [ RegexValidator(r"^[a-zA-Z0-9_]+$"), # Alphanumeric + underscore RegexValidator(r"^.{3,20}$"), # 3-20 characters RegexValidator(r"^(?!admin)", exclude=True, flags=re.IGNORECASE) # No "admin" ] schema = (extractor.create_schema() .structure("user") .field("username", dtype="str", validators=username_validators) ) text = "Users: ab, john_doe, user@domain, admin, valid_user123" results = extractor.extract(text, schema) # Output: {'user': [{'username': 'john_doe'}]} # Only valid usernames

import os os.environ["USE_FLASHDEBERTA"] = "1" # set before importing gliner2 from gliner2 import GLiNER2 extractor = GLiNER2.from_pretrained("fastino/gliner2-base-v1") # Prints: "Using FlashDeberta backend." result = extractor.extract_entities( "Apple CEO Tim Cook announced iPhone 15 in Cupertino.", ["company", "person", "product", "location"] )

# Batch entity extraction texts = [ "Google's Sundar Pichai unveiled Gemini AI in Mountain View.", "Microsoft CEO Satya Nadella announced Copilot at Build 2023.", "Amazon's Andy Jassy revealed new AWS services in Seattle." ] results = extractor.batch_extract_entities( texts, ["company", "person", "product", "location"], batch_size=8 ) # Returns list of results, one per input text # Batch relation extraction texts = [ "John works for Microsoft and lives in Seattle.", "Sarah founded TechStartup in 2020.", "Bob reports to Alice at Google." ] results = extractor.batch_extract_relations( texts, ["works_for", "founded", "reports_to", "lives_in"], batch_size=8 ) # Returns list of relation extraction results for each text # All requested relation types appear in each result, even if empty # Batch with confidence and spans results = extractor.batch_extract_entities( texts, ["company", "person"], include_confidence=True, include_spans=True, batch_size=8 )

from gliner2 import GLiNER2 from gliner2.training.data import InputExample from gliner2.training.trainer import GLiNER2Trainer, TrainingConfig # 1. Prepare training data examples = [ InputExample( text="John works at Google in California.", entities={"person": ["John"], "company": ["Google"], "location": ["California"]} ), InputExample( text="Apple released iPhone 15.", entities={"company": ["Apple"], "product": ["iPhone 15"]} ), # Add more examples... ] # 2. Configure training model = GLiNER2.from_pretrained("fastino/gliner2-base-v1") config = TrainingConfig( output_dir="./output", num_epochs=10, batch_size=8, encoder_lr=1e-5, task_lr=5e-4 ) # 3. Train trainer = GLiNER2Trainer(model, config) trainer.train(train_data=examples)

from gliner2 import GLiNER2 from gliner2.training.trainer import GLiNER2Trainer, TrainingConfig # Load model and train from JSONL file model = GLiNER2.from_pretrained("fastino/gliner2-base-v1") config = TrainingConfig(output_dir="./output", num_epochs=10) trainer = GLiNER2Trainer(model, config) trainer.train(train_data="train.jsonl") # Path to your JSONL file

from gliner2 import GLiNER2 from gliner2.training.data import InputExample from gliner2.training.trainer import GLiNER2Trainer, TrainingConfig # Prepare domain-specific data legal_examples = [ InputExample( text="Apple Inc. filed a lawsuit against Samsung Electronics.", entities={"company": ["Apple Inc.", "Samsung Electronics"]} ), # Add more examples... ] # Configure LoRA training model = GLiNER2.from_pretrained("fastino/gliner2-base-v1") config = TrainingConfig( output_dir="./legal_adapter", num_epochs=10, batch_size=8, encoder_lr=1e-5, task_lr=5e-4, # LoRA settings use_lora=True, # Enable LoRA lora_r=8, # Rank (4, 8, 16, 32) lora_alpha=16.0, # Scaling factor (usually 2*r) lora_dropout=0.0, # Dropout for LoRA layers save_adapter_only=True # Save only adapter (~5MB vs ~450MB) ) # Train adapter trainer = GLiNER2Trainer(model, config) trainer.train(train_data=legal_examples) # Use the adapter model.load_adapter("./legal_adapter/final") results = model.extract_entities(legal_text, ["company", "law"])

from gliner2 import GLiNER2 from gliner2.training.data import InputExample, TrainingDataset from gliner2.training.trainer import GLiNER2Trainer, TrainingConfig # Prepare training data train_examples = [ InputExample( text="Tim Cook is the CEO of Apple Inc., based in Cupertino, California.", entities={ "person": ["Tim Cook"], "company": ["Apple Inc."], "location": ["Cupertino", "California"] }, entity_descriptions={ "person": "Full name of a person", "company": "Business organization name", "location": "Geographic location or place" } ), # Add more examples... ] # Create and validate dataset train_dataset = TrainingDataset(train_examples) train_dataset.validate(strict=True, raise_on_error=True) train_dataset.print_stats() # Split into train/validation train_data, val_data, _ = train_dataset.split( train_ratio=0.8, val_ratio=0.2, test_ratio=0.0, shuffle=True, seed=42 ) # Configure training model = GLiNER2.from_pretrained("fastino/gliner2-base-v1") config = TrainingConfig( output_dir="./ner_model", experiment_name="ner_training", num_epochs=15, batch_size=16, encoder_lr=1e-5, task_lr=5e-4, warmup_ratio=0.1, scheduler_type="cosine", fp16=True, eval_strategy="epoch", save_best=True, early_stopping=True, early_stopping_patience=3 ) # Train trainer = GLiNER2Trainer(model, config) trainer.train(train_data=train_data, val_data=val_data) # Load best model model = GLiNER2.from_pretrained("./ner_model/best")