Temporal Extraction

from remem.information_extraction.temporal_extraction_openai import TemporalExtraction
from remem.llm.openai_gpt import CacheOpenAI

llm_model = CacheOpenAI(model="gpt-4")
extractor = TemporalExtraction(llm_model=llm_model, global_config=config)

def batch_openie(
    self,
    chunks: Dict[str, ChunkInfo]
) -> Dict[str, TemporalRawOutput]

from remem.information_extraction.temporal_extraction_openai import TemporalExtraction
from remem.llm.openai_gpt import CacheOpenAI

# Initialize the extractor
llm_model = CacheOpenAI(model="gpt-4")
config = type('Config', (), {
    'seed': 42,
    'temperature': 0.0
})()

extractor = TemporalExtraction(llm_model=llm_model, global_config=config)

# Prepare temporal chunks
chunks = {
    "event_1": {
        "metadata": {
            "timestamp": "2024-01-15",
            "content": "Marie Curie won the Nobel Prize in Physics in 1903 and the Nobel Prize in Chemistry in 1911. She worked at the University of Paris from 1906 to 1934."
        },
        "num_tokens": 70,
        "content": "Marie Curie won the Nobel Prize...",
        "chunk_order": [(0, 1)],
        "full_doc_ids": ["doc_789"]
    }
}

# Extract temporal facts
results = extractor.batch_openie(chunks)

# Access results
for chunk_id, output in results.items():
    print(f"\nTemporal facts in {chunk_id}:")
    for fact in output.facts:
        print(f"  Subject: {fact['subject']}")
        print(f"  Predicate: {fact['predicate']}")
        print(f"  Object: {fact['object']}")
        print(f"  Temporal: {fact['temporal_qualifier']}")
        print()

# Output:
#   Subject: Marie Curie
#   Predicate: won
#   Object: Nobel Prize in Physics
#   Temporal: 1903
#
#   Subject: Marie Curie
#   Predicate: won
#   Object: Nobel Prize in Chemistry
#   Temporal: 1911
#
#   Subject: Marie Curie
#   Predicate: worked at
#   Object: University of Paris
#   Temporal: from 1906 to 1934

# Build temporal knowledge representation
for fact in temporal_facts:
    kg.add_edge(
        fact['subject'],
        fact['object'],
        relation=fact['predicate'],
        timestamp=fact['temporal_qualifier']
    )

# Create chronological event sequences
events = sorted(
    temporal_facts,
    key=lambda f: parse_date(f['temporal_qualifier'])
)

# Query: "When did Marie Curie win the Nobel Prize?"
matching_facts = [
    f for f in temporal_facts
    if f['subject'] == 'Marie Curie'
    and 'Nobel Prize' in f['object']
]
print(matching_facts[0]['temporal_qualifier'])  # "1903"

# Extract facts within a time range
recent_facts = [
    f for f in temporal_facts
    if is_within_range(f['temporal_qualifier'], start='2020-01-01', end='2024-12-31')
]