Knowledge API

result = self.api.knowledge.search(...)

print(result.content)         # Text chunk
print(result.score)          # Similarity score (0-1)
print(result.metadata)       # Document metadata

def search(
    knowledge_base_uuid: str,
    query: str,
    top_k: int = 5,
    score_threshold: float = 0.0
) -> list[KnowledgeSearchResult]

from nadoo_plugin import NadooPlugin, tool

class MyPlugin(NadooPlugin):
    @tool(name="search_docs")
    def search_docs(self, question: str) -> dict:
        results = self.api.knowledge.search(
            knowledge_base_uuid="kb-uuid-123",
            query=question,
            top_k=3
        )

        # Format results
        answers = [
            {"content": r.content, "score": r.score}
            for r in results
        ]

        return {"results": answers}

@tool(name="find_relevant")
def find_relevant(self, query: str) -> dict:
    # Only return highly relevant results
    results = self.api.knowledge.search(
        knowledge_base_uuid=self.kb_uuid,
        query=query,
        top_k=10,
        score_threshold=0.7  # Min 70% relevance
    )

    return {"count": len(results), "results": [r.content for r in results]}

@tool(name="answer_with_context")
def answer_with_context(self, question: str) -> dict:
    # 1. Search knowledge base
    search_results = self.api.knowledge.search(
        knowledge_base_uuid=self.kb_uuid,
        query=question,
        top_k=3
    )

    # 2. Build context from results
    context = "\n\n".join([r.content for r in search_results])

    # 3. Ask LLM with context
    response = self.api.llm.invoke(
        messages=[
            {"role": "system", "content": f"Answer based on this context:\n{context}"},
            {"role": "user", "content": question}
        ]
    )

    return {
        "answer": response.content,
        "sources": [r.metadata for r in search_results]
    }