LLM 기반 비정형 텍스트 구조화 추출 Python 라이브러리 (Google 제작, Gemini/OpenAI/Ollama 지원)

pip install langextract

export LANGEXTRACT_API_KEY="your-api-key-here"

python - <<'EOF'
import langextract as lx
import textwrap

prompt = textwrap.dedent("""\
    Extract characters, emotions, and relationships in order of appearance.
    Use exact text for extractions. Do not paraphrase or overlap entities.
    Provide meaningful attributes for each entity to add context.""")

examples = [
    lx.data.ExampleData(
        text="ROMEO. But soft! What light through yonder window breaks? It is the east, and Juliet is the sun.",
        extractions=[
            lx.data.Extraction(extraction_class="character", extraction_text="ROMEO", attributes={"emotional_state": "wonder"}),
        ]
    )
]

result = lx.extract(
    text_or_documents="Lady Juliet gazed longingly at the stars, her heart aching for Romeo",
    prompt_description=prompt,
    examples=examples,
    model_id="gemini-3.5-flash",
)
print(result)
EOF

python - <<'EOF'
import langextract as lx
lx.io.save_annotated_documents([result], output_name="extraction_results.jsonl", output_dir=".")
html_content = lx.visualize("extraction_results.jsonl")
with open("visualization.html", "w") as f:
    f.write(html_content.data if hasattr(html_content, 'data') else html_content)
EOF