Error querying SageMaker endpoint

[lshang0311]

Link to the notebook
[Retrieval-Augmented Generation: Question Answering based on Custom Dataset with Open-sourced LangChain Library](https://sagemaker-examples.readthedocs.io/en/latest/introduction_to_amazon_algorithms/jumpstart-foundation-models/question_answering_retrieval_augmented_generation/question_answering_langchain_jumpstart.html)

Describe the bug
Query the endpoint

payload = {
    "text_inputs": question,
    "max_length": 100,
    "num_return_sequences": 1,
    "top_k": 50,
    "top_p": 0.95,
    "do_sample": True,
}

list_of_LLMs = list(_MODEL_CONFIG_.keys())
list_of_LLMs.remove("huggingface-textembedding-gpt-j-6b")  # remove the embedding model


for model_id in list_of_LLMs:
    endpoint_name = _MODEL_CONFIG_[model_id]["endpoint_name"]
    query_response = query_endpoint_with_json_payload(
        json.dumps(payload).encode("utf-8"), endpoint_name=endpoint_name
    )
    generated_texts = _MODEL_CONFIG_[model_id]["parse_function"](query_response)
    print(f"For model: {model_id}, the generated output is: {generated_texts[0]}\n")

Gives the following error:

ModelError: An error occurred (ModelError) when calling the InvokeEndpoint operation: Received client error (400) from primary with message "{
  "code": 400,
  "type": "InternalServerException",
  "message": "model_fn() takes 1 positional argument but 2 were given"
}

To reproduce
Dependencies:
!pip install sagemaker==2.181 !pip install ipywidgets==7.0.0 --quiet !pip install langchain==0.0.148 --quiet !pip install faiss-cpu --quiet

Logs

[lshang0311]

Screenshot of the error:

[HubGab-Git]

Hi @lshang0311 I have changed deployment to Jumpstart approach please find below my code:

from sagemaker import Session
from sagemaker.utils import name_from_base
from sagemaker.jumpstart.model import JumpStartModel

sagemaker_session = Session()

_MODEL_CONFIG_ = {
    "huggingface-text2text-flan-t5-xxl": {
        "model_version": "2.*",
        "instance type": "ml.g5.12xlarge"
    },

    # Got error: "DeprecatedJumpStartModelError:
    # This model is no longer available. Please try another model."
    # for GPT-J Emedings models at the time of testing it
    # "huggingface-textembedding-gpt-j-6b": {
    #     "model_version": "1.*",
    #     "instance type": "ml.g5.24xlarge"
    # },

    "huggingface-textembedding-all-MiniLM-L6-v2": {
        "model_version": "1.*",
        "instance type": "ml.g5.24xlarge"
    }
    # "huggingface-textembedding-all-MiniLM-L6-v2": {
    #     "model_version": "3.*",
    #     "instance type": "ml.g5.12xlarge"
    # },
    # "huggingface-text2text-flan-ul2-bf16": {
    #     "model_version": "2.*",
    #     "instance type": "ml.g5.24xlarge"
    # }
}

for model_id in _MODEL_CONFIG_:
    endpoint_name = name_from_base(f'jumpstart-example-raglc-{model_id}')
    inference_instance_type = _MODEL_CONFIG_[model_id]['instance type']
    model_version = _MODEL_CONFIG_[model_id]['model_version']

    print(f'Deploying {model_id}...')

    model = JumpStartModel(
        model_id=model_id,
        model_version=model_version
    )

    try:
        predictor = model.deploy(
            initial_instance_count=1,
            instance_type=inference_instance_type,
            endpoint_name=name_from_base(
                f"jumpstart-example-raglc-{model_id}"
            )
        )
        print(f"Deployed endpoint: {predictor.endpoint_name}")
        _MODEL_CONFIG_[model_id]['predictor'] = predictor
    except Exception as e:
        print(f"Error deploying {model_id}: {str(e)}")

print("Deployment process completed.")

question = "Which instances can I use with Managed Spot Training in SageMaker?"`

list_of_LLMs = list(_MODEL_CONFIG_.keys())
list_of_LLMs = [model for model in list_of_LLMs if "textembedding" not in model]

for model_id in list_of_LLMs:
    predictor = _MODEL_CONFIG_[model_id]["predictor"]
    response = predictor.predict({
        "inputs": question
    })
    print(f"For model: {model_id}, the generated output is:\n")
    print(f"{response[0]['generated_text']}\n")

I'm happy to create Pull request to improve notebook, can some one more experienced check if this is ok?