from langchain.tools import tool
from langchain.embeddings.ollama import OllamaEmbeddings
from langchain.vectorstores import Chroma
import os

@tool("search_local_kb")
def search_local_kb(query: str, top_k: int = 3) -> str:
    """Semantic search in local ChromaDB."""
    persist_dir = os.getenv("CHROMA_DB_DIR", "./chroma_db")
    embeddings = OllamaEmbeddings(model="nomic-embed-text")
    db = Chroma(embedding_function=embeddings, persist_directory=persist_dir)
    docs = db.similarity_search(query, k=top_k)
    return "\n".join([d.page_content for d in docs]) + f"\n[Source: chromadb]"

@tool("web_search")
def web_search(query: str) -> str:
    from tavily import TavilyClient
    client = TavilyClient(api_key=os.getenv("TAVILY_API_KEY"))
    result = client.search(query, max_results=3)
    return "\n".join([r['content'] for r in result]) + f"\n[Source: tavily]"