import wallaroo
from wallaroo.object import EntityNotFoundError

import pyarrow as pa
import pandas as pd
import time

# used to display dataframe information without truncating
from IPython.display import display
pd.set_option('display.max_colwidth', None)
pd.set_option('display.max_columns', None)

wl = wallaroo.Client()

workspace_name = f'edge-hf-summarization'
pipeline_name = 'edge-hf-summarization'
model_name = 'hf-summarization'
model_file_name = './models/model-auto-conversion_hugging-face_complex-pipelines_hf-summarisation-bart-large-samsun.zip'

workspace = wl.get_workspace(name=workspace_name, create_if_not_exist=True)

wl.set_current_workspace(workspace)

{'name': 'edge-hf-summarization', 'id': 1671, 'archived': False, 'created_by': '7d603858-88e0-472e-8f71-e41094afd7ec', 'created_at': '2025-05-16T16:26:15.723378+00:00', 'models': [], 'pipelines': []}

input_schema = pa.schema([
    pa.field('inputs', pa.string()),
    pa.field('return_text', pa.bool_()),
    pa.field('return_tensors', pa.bool_()),
    pa.field('clean_up_tokenization_spaces', pa.bool_()),
    # pa.field('generate_kwargs', pa.map_(pa.string(), pa.null())), # dictionaries are not currently supported by the engine
])

output_schema = pa.schema([
    pa.field('summary_text', pa.string()),
])

model = wl.upload_model(model_name, 
                        model_file_name, 
                        framework=wallaroo.framework.Framework.HUGGING_FACE_SUMMARIZATION, 
                        input_schema=input_schema, 
                        output_schema=output_schema,
                        convert_wait=False
                        )
model

while model.status() != "ready" and model.status() != "error":
    print(model.status())
    time.sleep(10)
print(model.status())

attempting_load_container
attempting_load_container
attempting_load_container
attempting_load_container
attempting_load_container
attempting_load_container
attempting_load_container
attempting_load_container
attempting_load_container
attempting_load_container
attempting_load_container
attempting_load_container
attempting_load_container
attempting_load_container
ready

deployment_config = wallaroo.DeploymentConfigBuilder() \
    .cpus(0.25).memory('1Gi') \
    .sidekick_cpus(model, 4) \
    .sidekick_memory(model, "8Gi") \
    .build()

pipeline = wl.build_pipeline(pipeline_name)
pipeline.clear()
pipeline.add_model_step(model)

pipeline.deploy(deployment_config=deployment_config, wait_for_status=False)

Deployment initiated for edge-hf-summarization. Please check pipeline status.

# check the pipeline status before performing an inference

while pipeline.status()['status'] != 'Running':
   time.sleep(15)
   display(pipeline.status()['status'])

pipeline.status()

'Starting'

'Starting'

'Starting'

'Starting'

'Running'

{'status': 'Running',
 'details': [],
 'engines': [{'ip': '10.4.2.58',
   'name': 'engine-684f588f6d-7vtf2',
   'status': 'Running',
   'reason': None,
   'details': [],
   'pipeline_statuses': {'pipelines': [{'id': 'edge-hf-summarization',
      'status': 'Running',
      'version': 'f4ba80ab-778a-4970-bdce-8f1d39310416'}]},
   'model_statuses': {'models': [{'model_version_id': 700,
      'name': 'hf-summarization',
      'sha': 'ee71d066a83708e7ca4a3c07caf33fdc528bb000039b6ca2ef77fa2428dc6268',
      'status': 'Running',
      'version': '4c724404-a130-442c-9633-47b270067aaa'}]}}],
 'engine_lbs': [{'ip': '10.4.2.59',
   'name': 'engine-lb-5f76cc9c94-bdjqg',
   'status': 'Running',
   'reason': None,
   'details': []}],
 'sidekicks': [{'ip': '10.4.8.3',
   'name': 'engine-sidekick-hf-summarization-700-8b847f7c6-5rrp2',
   'status': 'Running',
   'reason': None,
   'details': [],
   'statuses': '\n'}]}

input_data = {
        "inputs": ["LinkedIn (/lɪŋktˈɪn/) is a business and employment-focused social media platform that works through websites and mobile apps. It launched on May 5, 2003. It is now owned by Microsoft. The platform is primarily used for professional networking and career development, and allows jobseekers to post their CVs and employers to post jobs. From 2015 most of the company's revenue came from selling access to information about its members to recruiters and sales professionals. Since December 2016, it has been a wholly owned subsidiary of Microsoft. As of March 2023, LinkedIn has more than 900 million registered members from over 200 countries and territories. LinkedIn allows members (both workers and employers) to create profiles and connect with each other in an online social network which may represent real-world professional relationships. Members can invite anyone (whether an existing member or not) to become a connection. LinkedIn can also be used to organize offline events, join groups, write articles, publish job postings, post photos and videos, and more"], # required
        "return_text": [True], # optional: using the defaults, similar to not passing this parameter
        "return_tensors": [False], # optional: using the defaults, similar to not passing this parameter
        "clean_up_tokenization_spaces": [False], # optional: using the defaults, similar to not passing this parameter
}
dataframe = pd.DataFrame(input_data)
dataframe

deploy_url = pipeline._deployment._url()

headers = wl.auth.auth_header()

headers['Content-Type']='application/json; format=pandas-records'
# headers['Content-Type']='application/json; format=pandas-records'
headers['Accept']='application/json; format=pandas-records'

dataFile = './data/test_summarization.df.json'

!curl -X POST {deploy_url} \
     -H "Authorization:{headers['Authorization']}" \
     -H "Content-Type:{headers['Content-Type']}" \
     -H "Accept:{headers['Accept']}" \
     --data-binary @{dataFile}

[{"time":1747413364849,"in":{"clean_up_tokenization_spaces":false,"inputs":"LinkedIn (/lɪŋktˈɪn/) is a business and employment-focused social media platform that works through websites and mobile apps. It launched on May 5, 2003. It is now owned by Microsoft. The platform is primarily used for professional networking and career development, and allows jobseekers to post their CVs and employers to post jobs. From 2015 most of the company's revenue came from selling access to information about its members to recruiters and sales professionals. Since December 2016, it has been a wholly owned subsidiary of Microsoft. As of March 2023, LinkedIn has more than 900 million registered members from over 200 countries and territories. LinkedIn allows members (both workers and employers) to create profiles and connect with each other in an online social network which may represent real-world professional relationships. Members can invite anyone (whether an existing member or not) to become a connection. LinkedIn can also be used to organize offline events, join groups, write articles, publish job postings, post photos and videos, and more","return_tensors":false,"return_text":true},"out":{"summary_text":"LinkedIn is a business and employment-focused social media platform that works through websites and mobile apps. It launched on May 5, 2003. LinkedIn allows members (both workers and employers) to create profiles and connect with each other in an online social network which may represent real-world professional relationships."},"anomaly":{"count":0},"metadata":{"last_model":"{\"model_name\":\"hf-summarization\",\"model_sha\":\"ee71d066a83708e7ca4a3c07caf33fdc528bb000039b6ca2ef77fa2428dc6268\"}","pipeline_version":"f4ba80ab-778a-4970-bdce-8f1d39310416","elapsed":[1778419,5123862000],"dropped":[],"partition":"engine-684f588f6d-7vtf2"}}]

pipeline.undeploy()

Waiting for undeployment - this will take up to 45s .................................... ok

## This may still show an error status despite but if both containers show running it should be good to go
pipeline.publish(deployment_config)

Waiting for pipeline publish... It may take up to 600 sec.
....................... Published.

wl.list_pipelines(workspace_name=workspace_name)

pipeline.publishes()

curl localhost:8080/pipelines
{"pipelines":[{"id":"edge-cv-retail","status":"Running"}]}

!curl testboy.local:8080/pipelines

{"pipelines":[{"id":"edge-hf-summarization","status":"Running"}]}

curl localhost:8080/models
{"models":[{"name":"resnet-50","sha":"c6c8869645962e7711132a7e17aced2ac0f60dcdc2c7faa79b2de73847a87984","status":"Running","version":"693e19b5-0dc7-4afb-9922-e3f7feefe66d"}]}

!curl testboy.local:8080/models

{"models":[{"name":"hf-summarization","version":"add06bd2-054e-4562-b25e-ee692c6e472c","sha":"ee71d066a83708e7ca4a3c07caf33fdc528bb000039b6ca2ef77fa2428dc6268","status":"Running"}]}

import json
import requests
import pandas as pd

# set the content type and accept headers
headers = {
    'Content-Type': 'application/json; format=pandas-records'
}

# Submit arrow file
dataFile="./data/test_summarization.df.json"

data = json.load(open(dataFile))

host = 'http://testboy.local:8080'

deployurl = f'{host}/infer'

response = requests.post(
                    deployurl, 
                    headers=headers, 
                    json=data, 
                    verify=True
                )

# display(response)
display(pd.DataFrame(response.json()).loc[0, ['outputs']][0][0]['String']['data'][0])

'LinkedIn is a business and employment-focused social media platform that works through websites and mobile apps. It launched on May 5, 2003. LinkedIn allows members (both workers and employers) to create profiles and connect with each other in an online social network which may represent real-world professional relationships.'