import wallaroo
from wallaroo.object import EntityNotFoundError
from wallaroo.framework import Framework
from wallaroo.deployment_config import DeploymentConfigBuilder

from IPython.display import display

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

import pyarrow as pa
import json
import datetime
import time
import zipfile

wl = wallaroo.Client(request_timeout=120)

workspace_name = "sentiment-analysis-tutorial"  

wl.set_current_workspace(wl.get_workspace(workspace_name, create_if_not_exist=True))

{'name': 'sentiment-analysis-tutorial', 'id': 16, 'archived': False, 'created_by': 'john.hansarick@wallaroo.ai', 'created_at': '2025-05-01T19:38:22.227711+00:00', 'models': [], 'pipelines': [{'name': 'sentiment-analysis', 'create_time': datetime.datetime(2025, 5, 1, 19, 45, 26, 228651, tzinfo=tzutc()), 'definition': '[]'}]}

pipeline.undeploy()

# upload the sentiment analyzer

input_schema = pa.schema([
     pa.field('inputs', pa.string()), # required
     pa.field('top_k', pa.int64()),  
])

output_schema = pa.schema([
     pa.field('label', pa.list_(pa.string(), list_size=6)), # list with a number of items same as top_k, list_size can be skipped but may lead in worse performance
     pa.field('score', pa.list_(pa.float64(), list_size=6)), # list with a number of items same as top_k, list_size can be skipped but may lead in worse performance
])

framework=Framework.HUGGING_FACE_TEXT_CLASSIFICATION
model_name = "toxic-bert-analysis"
model_file_name = './models/unitary-toxic-bert.zip'

bert_model = wl.upload_model(model_name,
                         model_file_name,
                         framework=framework,
                         input_schema=input_schema,
                         output_schema=output_schema,
                         convert_wait=False)

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

pending_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

# this is the summarizer config 
deployment_config = wallaroo.DeploymentConfigBuilder() \
    .cpus(0.25).memory('1Gi') \
    .sidekick_cpus(bert_model, 4) \
    .sidekick_memory(bert_model, "8Gi") \
    .build()

pipeline_name = 'sentiment-analysis'
pipeline=wl.build_pipeline(pipeline_name)
pipeline.clear()
pipeline.add_model_step(bert_model)

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

Deployment initiated for sentiment-analysis. Please check pipeline status.

time.sleep(15)

while pipeline.status()['status'] != 'Running':
    time.sleep(15)
    print("Waiting for deployment.")
    display(pipeline.status()['status'])
display(pipeline.status()['status'])

Waiting for deployment.

'Running'

'Running'

results = pipeline.infer_from_file("./data/sample_input.json")
results

import models.postprocess
import importlib
importlib.reload(models.postprocess)

df = pd.DataFrame(models.postprocess.process_data(results))
df

pipeline.undeploy()