[Python] How to configure HuggingFaceEndpoint in Langchain

I'm trying to use this model

from langchain_huggingface import HuggingFaceEndpoint
repo_id="google/flan-t5-large"
huggingface_llm = HuggingFaceEndpoint(
huggingfacehub_api_token=HUGGINGFACEHUB_API_TOKEN,
repo_id=repo_id,
temperature=0,
max_new_tokens=200)

from langchain.prompts import PromptTemplate
def flan_process(tema, pregunta):
template = "Eres un experto asistente en {tema}. Responde a la siguiente pregunta: {pregunta}"
prompt=PromptTemplate(template=template,input_variables=["tema","pregunta"])

flan_chain = prompt | huggingface_llm

respuesta=flan_chain.invoke({"tema":tema, "pregunta"regunta})

return respuesta

tema=input("Ingrese el tema: ")
pregunta=input("Ingrese la pregunta: ")

flan_reply=flan_process(tema, pregunta)
print(f"Respuesta Flan: {flan_reply}")


But I always get this error The following model_kwargs are not used by the model: ['return_full_text', 'watermark', 'stop_sequences', 'stop'] (note: typos in the generate arguments will also show up in this list)

Any idea please?

Thanks

Continue reading...