Function generate_knowledge_graph

docs/examples/quickstart_async.py:459–491

()

    print("you may observe an even more significant speed advantage for Crawl4AI.")

async def generate_knowledge_graph():
    class Entity(BaseModel):
        name: str
        description: str
        
    class Relationship(BaseModel):
        entity1: Entity
        entity2: Entity
        description: str
        relation_type: str

    class KnowledgeGraph(BaseModel):
        entities: List[Entity]
        relationships: List[Relationship]

    extraction_strategy = LLMExtractionStrategy(
            provider='openai/gpt-4o-mini', # Or any other provider, including Ollama and open source models
            api_token=os.getenv('OPENAI_API_KEY'), # In case of Ollama just pass "no-token"
            schema=KnowledgeGraph.model_json_schema(),
            extraction_type="schema",
            instruction="""Extract entities and relationships from the given text."""
    )
    async with AsyncWebCrawler() as crawler:
        url = "https://paulgraham.com/love.html"
        result = await crawler.arun(
            url=url,
            bypass_cache=True,
            extraction_strategy=extraction_strategy,
            # magic=True
        )
        # print(result.extracted_content)
        with open(os.path.join(__location__, "kb.json"), "w") as f:
            f.write(result.extracted_content)

async def fit_markdown_remove_overlay():
    async with AsyncWebCrawler(headless = False) as crawler: