MLServer 入門¶

pip install mlserver spacy wikipedia-api

python -m spacy download en_core_web_lg

mkdir -p similarity_model

import spacy

nlp = spacy.load("en_core_web_lg")

import wikipediaapi

wiki_wiki = wikipediaapi.Wikipedia('MyMovieEval (example@example.com)', 'en')

barbie = wiki_wiki.page('Barbie_(film)').summary

oppenheimer = wiki_wiki.page('Oppenheimer_(film)').summary

print(barbie)
print()
print(oppenheimer)

Barbie is a 2023 American fantasy comedy film directed by Greta Gerwig and written by Gerwig and Noah Baumbach. Based on the Barbie fashion dolls by Mattel, it is the first live-action Barbie film after numerous computer-animated direct-to-video and streaming television films. The film stars Margot Robbie as Barbie and Ryan Gosling as Ken, and follows the two on a journey of self-discovery following an existential crisis. The film also features an ensemble cast that includes America Ferrera, Kate McKinnon, Issa Rae, Rhea Perlman, and Will Ferrell...

Oppenheimer is a 2023 biographical thriller film written and directed by Christopher Nolan. Based on the 2005 biography American Prometheus by Kai Bird and Martin J. Sherwin, the film chronicles the life of J. Robert Oppenheimer, a theoretical physicist who was pivotal in developing the first nuclear weapons as part of the Manhattan Project, and thereby ushering in the Atomic Age. Cillian Murphy stars as Oppenheimer, with Emily Blunt as Oppenheimer's wife Katherine "Kitty" Oppenheimer; Matt Damon as General Leslie Groves, director of the Manhattan Project; and Robert Downey Jr. as Lewis Strauss, a senior member of the United States Atomic Energy Commission. The ensemble supporting cast includes Florence Pugh, Josh Hartnett, Casey Affleck, Rami Malek, Gary Oldman and Kenneth Branagh...

doc1 = nlp(barbie)
doc2 = nlp(oppenheimer)

print(doc1.similarity(doc2))

0.9866910567224084

# similarity_model/my_model.py

from mlserver.codecs import decode_args
from mlserver import MLModel
from typing import List
import numpy as np
import spacy

class MyKulModel(MLModel):

    async def load(self):
        self.model = spacy.load("en_core_web_lg")

    @decode_args
    async def predict(self, docs: List[str]) -> np.ndarray:

        doc1 = self.model(docs[0])
        doc2 = self.model(docs[1])

        return np.array(doc1.similarity(doc2))

{
    "name": "doc-sim-model",
    "implementation": "my_model.MyKulModel"
}

mlserver start similarity_model/

from mlserver.codecs import StringCodec
import requests

inference_request = {
    "inputs": [
        StringCodec.encode_input(name='docs', payload=[barbie, oppenheimer], use_bytes=False).model_dump()
    ]
}

print(inference_request)

{'inputs': [{'name': 'docs',
   'shape': [2, 1],
   'datatype': 'BYTES',
   'parameters': {'content_type': 'str'},
   'data': [
        'Barbie is a 2023 American fantasy comedy...',
        'Oppenheimer is a 2023 biographical thriller...'
        ]
    }]
}

r = requests.post('http://0.0.0.0:8080/v2/models/doc-sim-model/infer', json=inference_request)

print(r.json())

{'model_name': 'doc-sim-model',
    'id': 'a4665ddb-1868-4523-bd00-a25902d9b124',
    'parameters': {},
    'outputs': [{'name': 'output-0',
    'shape': [1],
    'datatype': 'FP64',
    'parameters': {'content_type': 'np'},
    'data': [0.9866910567224084]}]}

print(f"Our movies are {round(r.json()['outputs'][0]['data'][0] * 100, 4)}% similar!")

Our movies are 98.6691% similar

{
    "parallel_workers": 3
}

deep_impact    = wiki_wiki.page('Deep_Impact_(film)').summary
armageddon     = wiki_wiki.page('Armageddon_(1998_film)').summary

antz           = wiki_wiki.page('Antz').summary
a_bugs_life    = wiki_wiki.page("A_Bug's_Life").summary

the_dark_night = wiki_wiki.page('The_Dark_Knight').summary
mamma_mia      = wiki_wiki.page('Mamma_Mia!_(film)').summary

def get_sim_score(movie1, movie2):
    response = requests.post(
        'http://0.0.0.0:8080/v2/models/doc-sim-model/infer',
        json={
            "inputs": [
                StringCodec.encode_input(name='docs', payload=[movie1, movie2], use_bytes=False).model_dump()
            ]
        })
    return response.json()['outputs'][0]['data'][0]

get_sim_score(deep_impact, armageddon)

0.9569279450151813

results = list(
    map(get_sim_score, (deep_impact, antz, the_dark_night), (armageddon, a_bugs_life, mamma_mia))
)

print(results)

[0.9569279450151813, 0.9725374771538605, 0.9626173937217876]

for movie1, movie2 in zip((deep_impact, antz, the_dark_night), (armageddon, a_bugs_life, mamma_mia)):
    print(get_sim_score(movie1, movie2))

0.9569279450151813
0.9725374771538605
0.9626173937217876

mlserver
spacy==3.6.0
https://github.com/explosion/spacy-models/releases/download/en_core_web_lg-3.6.0/en_core_web_lg-3.6.0-py3-none-any.whl

mlserver build similarity_model/ -t 'fancy_ml_service'

docker images

docker run -it --rm -p 8080:8080 fancy_ml_service