Introduction to JumpStart - Named Entity Recognition

This notebook’s CI test result for us-west-2 is as follows. CI test results in other regions can be found at the end of the notebook.

Set Up
Select a model
Retrieve JumpStart Artifacts & Deploy an Endpoint
Query endpoint and parse response
Clean up the endpoint

Note: This notebook was tested on ml.t3.medium instance in Amazon SageMaker Studio with Python 3 (Data Science) kernel and in Amazon SageMaker Notebook instance with conda_python3 kernel.

1. Set Up

[ ]:

! pip install sagemaker ipywidgets --upgrade --quiet

Permissions and environment variables

[ ]:

import sagemaker, boto3, json
from sagemaker import get_execution_role

aws_role = get_execution_role()
aws_region = boto3.Session().region_name
sess = sagemaker.Session()

2. Select a model

Here, we download jumpstart model_manifest file from the jumpstart s3 bucket, filter-out all the Named Entity Recognition models and select a model for inference. ***

[ ]:

from ipywidgets import Dropdown

# download JumpStart model_manifest file.
boto3.client("s3").download_file(
    f"jumpstart-cache-prod-{aws_region}", "models_manifest.json", "models_manifest.json"
)
with open("models_manifest.json", "rb") as json_file:
    model_list = json.load(json_file)

# filter-out all the Named Entity Recognition models from the manifest list.
ner_models = []
for model in model_list:
    model_id = model["model_id"]
    if "-ner-" in model_id and model_id not in ner_models:
        ner_models.append(model_id)

# display the model-ids in a dropdown to select a model for inference.
model_dropdown = Dropdown(
    options=ner_models,
    value="huggingface-ner-distilbert-base-cased-finetuned-conll03-english",
    description="Select a model",
    style={"description_width": "initial"},
    layout={"width": "max-content"},
)

Chose a model for Inference

[ ]:

display(model_dropdown)

[ ]:

# model_version="*" fetches the latest version of the model
model_id, model_version = model_dropdown.value, "*"

3. Retrieve JumpStart Artifacts & Deploy an Endpoint

[ ]:

from sagemaker.jumpstart.model import JumpStartModel

model = JumpStartModel(model_id=model_id)
model_predictor = model.deploy()

4. Query endpoint and parse response

[ ]:

def query(model_predictor, text):
    """Query the model predictor."""

    encoded_text = text.encode("utf-8")

    query_response = model_predictor.predict(
        encoded_text,
        {
            "ContentType": "application/x-text",
            "Accept": "application/json",
        },
    )
    return query_response


def parse_response(query_response):
    """Parse response and return predicted entities."""

    model_predictions = query_response
    translation_text = model_predictions["predictions"]
    return translation_text

[ ]:

newline, bold, unbold = "\n", "\033[1m", "\033[0m"

input_text = "My name is Wolfgang and I live in Berlin"

query_response = query(model_predictor, input_text)

model_predictions = parse_response(query_response)

print(
    f"Input text: {input_text}{newline}"
    f"Model prediction: {bold}{model_predictions}{unbold}{newline}"
)

5. Clean up the endpoint

[ ]:

# Delete the SageMaker endpoint
model_predictor.delete_model()
model_predictor.delete_endpoint()

This notebook was tested in multiple regions. The test results are as follows, except for us-west-2 which is shown at the top of the notebook.