LangChain with HuggingFace model and DuckDuckSearch not working

I'm trying to create an agent that uses HuggingFace models and also uses internet search to answer the queries

import osimport getpassfrom langchain.agents import load_toolsfrom langchain.agents import initialize_agentfrom langchain.llms import OpenAIfrom langchain.agents import load_huggingface_toolfrom langchain import PromptTemplate, HuggingFaceHub, LLMChainos.environ\["HUGGINGFACEHUB_API_TOKEN"\] = getpass.getpass("HF Token:")llm = HuggingFaceHub(repo_id="huggingfaceh4/zephyr-7b-alpha",model_kwargs={"temperature": 0.5, "max_length": 64, "max_new_tokens": 512},)tools = load_tools(\["ddg-search"\], llm=llm)agent = initialize_agent(tools, llm, agent="zero-shot-react-description", verbose=True)agent.run("What is LangChain and how does it work? ")

But I keep getting Observation: the action to take, should be one of [duckduckgo_search] is not a valid tool, try one of [duckduckgo_search]. and it just keeps looping without any useful error. How can I fix this?

Thank you