Google LangExtract完全ガイド：LLMで非構造テキストから構造化抽出、ソース位置も追跡

import langextract as lx

result = lx.extract(
    text_or_documents=input_text,
    prompt_description="Extract characters and emotions...",
    examples=[lx.data.ExampleData(...)],
    model_id="gemini-2.5-flash",
)

# 各 extraction には char_interval が付き、原文上の位置が分かる
for ext in result.extractions:
    print(ext.extraction_class, ext.extraction_text, ext.char_interval)

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?",
        extractions=[
            lx.data.Extraction(
                extraction_class="character",
                extraction_text="ROMEO",
                attributes={"emotional_state": "wonder"},
            ),
        ],
    )
]

input_text = "Lady Juliet gazed longingly at the stars, her heart aching"

result = lx.extract(
    text_or_documents=input_text,
    prompt_description=prompt,
    examples=examples,
    model_id="gemini-2.5-flash",
)

# 結果保存
lx.io.save_annotated_documents([result],
    output_name="extraction_results.jsonl", output_dir=".")

# 対話型HTMLにレンダリング
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)

result = lx.extract(
    text_or_documents="https://www.gutenberg.org/files/1513/1513-0.txt",
    prompt_description=prompt,
    examples=examples,
    model_id="gemini-2.5-flash",
    extraction_passes=3,    # 多パスで再現率を上げる
    max_workers=20,         # 並列ワーカー数
    max_char_buffer=1000,   # チャンクサイズ（小さいほど精度↑、コール数↑）
)

import langextract as lx

input_text = "Patient took 400 mg PO Ibuprofen q4h for two days."

prompt_description = (
    "Extract medication information including medication name, dosage, "
    "route, frequency, and duration in the order they appear in the text."
)

examples = [
    lx.data.ExampleData(
        text="Patient was given 250 mg IV Cefazolin TID for one week.",
        extractions=[
            lx.data.Extraction(extraction_class="dosage",     extraction_text="250 mg"),
            lx.data.Extraction(extraction_class="route",      extraction_text="IV"),
            lx.data.Extraction(extraction_class="medication", extraction_text="Cefazolin"),
            lx.data.Extraction(extraction_class="frequency",  extraction_text="TID"),
            lx.data.Extraction(extraction_class="duration",   extraction_text="for one week"),
        ],
    )
]

result = lx.extract(
    text_or_documents=input_text,
    prompt_description=prompt_description,
    examples=examples,
    model_id="gemini-2.5-pro",
)

input_text = """
The patient was prescribed Lisinopril and Metformin last month.
He takes the Lisinopril 10mg daily for hypertension, but often misses
his Metformin 500mg dose which should be taken twice daily for diabetes.
"""

prompt_description = """
Extract medications with their details, using attributes to group related information:

1. Extract entities in the order they appear in the text
2. Each entity must have a 'medication_group' attribute linking it to its medication
3. All details about a medication should share the same medication_group value
"""

examples = [
    lx.data.ExampleData(
        text="Patient takes Aspirin 100mg daily for heart health and Simvastatin 20mg at bedtime.",
        extractions=[
            lx.data.Extraction(extraction_class="medication", extraction_text="Aspirin",
                attributes={"medication_group": "Aspirin"}),
            lx.data.Extraction(extraction_class="dosage", extraction_text="100mg",
                attributes={"medication_group": "Aspirin"}),
            lx.data.Extraction(extraction_class="frequency", extraction_text="daily",
                attributes={"medication_group": "Aspirin"}),
            lx.data.Extraction(extraction_class="condition", extraction_text="heart health",
                attributes={"medication_group": "Aspirin"}),
            lx.data.Extraction(extraction_class="medication", extraction_text="Simvastatin",
                attributes={"medication_group": "Simvastatin"}),
            lx.data.Extraction(extraction_class="dosage", extraction_text="20mg",
                attributes={"medication_group": "Simvastatin"}),
            lx.data.Extraction(extraction_class="frequency", extraction_text="at bedtime",
                attributes={"medication_group": "Simvastatin"}),
        ],
    )
]

import langextract as lx
from langextract.core import tokenizer

input_text = "東京出身の田中さんはGoogleで働いています。"
prompt_description = "Extract named entities including Person, Location, and Organization."

examples = [
    lx.data.ExampleData(
        text="大阪の山田さんはソニーに入社しました。",
        extractions=[
            lx.data.Extraction(extraction_class="Location",     extraction_text="大阪"),
            lx.data.Extraction(extraction_class="Person",       extraction_text="山田"),
            lx.data.Extraction(extraction_class="Organization", extraction_text="ソニー"),
        ],
    )
]

unicode_tokenizer = tokenizer.UnicodeTokenizer()

result = lx.extract(
    text_or_documents=input_text,
    prompt_description=prompt_description,
    examples=examples,
    model_id="gemini-2.5-flash",
    tokenizer=unicode_tokenizer,
)

result = lx.extract(
    text_or_documents=input_text,
    prompt_description=prompt,
    examples=examples,
    model_id="gemma2:2b",
    model_url="http://localhost:11434",
)

result = lx.extract(
    text_or_documents=input_text,
    prompt_description=prompt,
    examples=examples,
    model_id="gpt-4o",   # 自動でOpenAIプロバイダーが選ばれる
)