from langchain.tools import tool
from vector_store import QdrantStore
from chunker import get_chunks

store = QdrantStore()

@tool
def search_knowledge_base(query: str, max_results: int = 5) -> str:
    """Semantic search in knowledge base."""
    results = store.search(query, limit=max_results)
    return "\n".join([f"{i+1}. {r['metadata']['title']} – {r['metadata']['content'][:200]}..." for i,r in enumerate(results)])

@tool
def add_to_knowledge_base(content: str, title: str) -> str:
    """Add document to knowledge base."""
    chunks = get_chunks(content, title)
    store.add_documents(chunks)
    return f"Added {len(chunks)} chunks for '{title}'."