Coba Gemini 1.5 Pro, model multimodal kami yang paling canggih di Vertex AI, dan lihat apa yang dapat Anda bangun dengan jendela konteks token 1 juta. Coba Gemini 1.5 Pro, model multimodal kami yang paling canggih di Vertex AI, dan lihat apa yang dapat Anda bangun dengan jendela konteks token 1 juta.

Bermigrasi ke Library Klien Python v0.25.1

Library Klien untuk Python v0.25.1 menyertakan beberapa perubahan signifikan terkait cara mendesain library klien sebelumnya. Perubahan ini dapat dirangkum sebagai berikut:

Konsolidasi modul menjadi lebih sedikit jenis
Mengganti parameter tanpa jenis dengan kelas dan enumerasi yang berjenis kuat

Topik ini memberikan detail tentang perubahan yang perlu Anda lakukan pada kode Python untuk library klien Cloud Vision API agar dapat menggunakan library klien Python v0.25.1.

Menjalankan library klien versi sebelumnya

Anda tidak perlu mengupgrade library klien Python ke v0.25.1. Jika ingin terus menggunakan library klien Python versi sebelumnya dan tidak ingin memigrasikan kode, Anda harus menentukan versi library klien Python yang digunakan oleh aplikasi Anda. Untuk menentukan versi library tertentu, edit file requirements.txt seperti yang ditunjukkan:

google-cloud-vision==0.25

Modul yang Dihapus

Modul berikut telah dihapus di paket Python Library Klien v0.25.1.

google.cloud.vision.annotations
google.cloud.vision.batch
google.cloud.vision.client
google.cloud.vision.color
google.cloud.vision.crop_hint
google.cloud.vision.entity
google.cloud.vision.face
google.cloud.vision.feature
google.cloud.vision.geometry
google.cloud.vision.image
google.cloud.vision.likelihood
google.cloud.vision.safe_search
google.cloud.vision.text
google.cloud.vision.web

Perubahan Kode yang Diperlukan

Impor

Sertakan modul google.cloud.vision.types baru untuk mengakses jenis baru di Library Klien Python v0.25.1.

Modul types berisi kelas baru yang diperlukan untuk membuat permintaan, seperti types.Image.

from google.cloud import vision

Selain itu, modul google.cloud.vision.enums baru berisi enumerasi yang berguna untuk mengurai dan memahami respons API, seperti enums.Likelihood.UNLIKELY dan enums.FaceAnnotation.Landmark.Type.LEFT_EYE.

Membuat klien

Kelas Client telah diganti dengan kelas ImageAnnotatorClient. Ganti referensi ke kelas Client dengan ImageAnnotatorClient.

Library klien versi sebelumnya:

old_client = vision.Client()

Library Klien Python v0.25.1:

client = vision.ImageAnnotatorClient()

Membuat objek yang merepresentasikan konten gambar

Untuk mengidentifikasi konten gambar dari file lokal, dari Google Cloud Storage URI, atau dari web URI, gunakan kelas Image yang baru.

Membuat objek yang merepresentasikan konten gambar dari file lokal

Contoh berikut menunjukkan cara baru untuk menampilkan konten gambar dari file lokal.

Library klien versi sebelumnya:

with io.open(file_name, 'rb') as image_file:
    content = image_file.read()

image = old_client.image(content=content)

Library Klien Python v0.25.1:

with open(path, "rb") as image_file:
    content = image_file.read()

image = vision.Image(content=content)

Membuat objek yang merepresentasikan konten gambar dari URI

Contoh berikut menunjukkan cara baru untuk menampilkan konten gambar dari Google Cloud Storage URI atau web URI. uri adalah URI ke file gambar di Google Cloud Storage atau di web.

Library klien versi sebelumnya:

image = old_client.image(source_uri=uri)

Library Klien Python v0.25.1:

image = vision.Image()
image.source.image_uri = uri

Membuat permintaan dan memproses respons

Dengan Library Klien Python v.0.25.1, metode API seperti face_detection menjadi bagian dari objek ImageAnnotatorClient, bukan objek Image.

Nilai yang ditampilkan berbeda untuk beberapa metode seperti yang dijelaskan di bawah ini.

Khususnya, verteks kotak pembatas kini disimpan di bounding_poly.vertices bukan bounds.vertices. Koordinat setiap verteks disimpan di vertex.x dan vertex.y bukan vertex.x_coordinate dan vertex.y_coordinate.

Perubahan kotak pembatas memengaruhi face_detection, logo_detection, text_detection, document_text_detection, dan crop_hints.

Membuat permintaan deteksi wajah dan memproses respons

Kemungkinan emosi kini ditampilkan sebagai enumerasi yang disimpan di face.surprise_likelihood, bukan face.emotions.surprise. Nama label kemungkinan dapat dipulihkan dengan mengimpor google.cloud.vision.enums.Likelihood.

Library klien versi sebelumnya::

with io.open(file_name, 'rb') as image_file:
    content = image_file.read()

image = old_client.image(content=content)

faces = image.detect_faces()

for face in faces:
    print('anger: {}'.format(face.emotions.anger))
    print('joy: {}'.format(face.emotions.joy))
    print('surprise: {}'.format(face.emotions.surprise))

    vertices = (['({},{})'.format(bound.x_coordinate, bound.y_coordinate)
                for bound in face.bounds.vertices])

    print('face bounds: {}'.format(','.join(vertices)))

Library Klien Python v0.25.1:

with open(path, "rb") as image_file:
    content = image_file.read()

image = vision.Image(content=content)

response = client.face_detection(image=image)
faces = response.face_annotations

# Names of likelihood from google.cloud.vision.enums
likelihood_name = (
    "UNKNOWN",
    "VERY_UNLIKELY",
    "UNLIKELY",
    "POSSIBLE",
    "LIKELY",
    "VERY_LIKELY",
)
print("Faces:")

for face in faces:
    print(f"anger: {likelihood_name[face.anger_likelihood]}")
    print(f"joy: {likelihood_name[face.joy_likelihood]}")
    print(f"surprise: {likelihood_name[face.surprise_likelihood]}")

    vertices = [
        f"({vertex.x},{vertex.y})" for vertex in face.bounding_poly.vertices
    ]

    print("face bounds: {}".format(",".join(vertices)))

if response.error.message:
    raise Exception(
        "{}\nFor more info on error messages, check: "
        "https://cloud.google.com/apis/design/errors".format(response.error.message)
    )

Membuat permintaan deteksi label dan memproses respons

Library klien versi sebelumnya::

with io.open(file_name, 'rb') as image_file:
    content = image_file.read()

image = old_client.image(content=content)

labels = image.detect_labels()

for label in labels:
    print(label.description)

Library Klien Python v0.25.1:

with open(path, "rb") as image_file:
    content = image_file.read()

image = vision.Image(content=content)

response = client.label_detection(image=image)
labels = response.label_annotations
print("Labels:")

for label in labels:
    print(label.description)

if response.error.message:
    raise Exception(
        "{}\nFor more info on error messages, check: "
        "https://cloud.google.com/apis/design/errors".format(response.error.message)
    )

Membuat permintaan deteksi penanda dan memproses respons

Library klien versi sebelumnya::

Lintang dan bujur lokasi penanda sekarang disimpan di location.lat_lng.latitude dan location.lat_lng.longitude, bukan di location.latitude dan location.longitude.

with io.open(file_name, 'rb') as image_file:
    content = image_file.read()

image = old_client.image(content=content)

landmarks = image.detect_landmarks()

for landmark in landmarks:
    print(landmark.description, landmark.score)
    for location in landmark.locations:
        print('Latitude'.format(location.latitude))
        print('Longitude'.format(location.longitude))

Library Klien Python v0.25.1:

with open(path, "rb") as image_file:
    content = image_file.read()

image = vision.Image(content=content)

response = client.landmark_detection(image=image)
landmarks = response.landmark_annotations
print("Landmarks:")

for landmark in landmarks:
    print(landmark.description)
    for location in landmark.locations:
        lat_lng = location.lat_lng
        print(f"Latitude {lat_lng.latitude}")
        print(f"Longitude {lat_lng.longitude}")

if response.error.message:
    raise Exception(
        "{}\nFor more info on error messages, check: "
        "https://cloud.google.com/apis/design/errors".format(response.error.message)
    )

Membuat permintaan deteksi logo dan memproses respons

Library klien versi sebelumnya::

with io.open(file_name, 'rb') as image_file:
    content = image_file.read()

image = old_client.image(content=content)

logos = image.detect_logos()

for logo in logos:
    print(logo.description, logo.score)

Library Klien Python v0.25.1:

with open(path, "rb") as image_file:
    content = image_file.read()

image = vision.Image(content=content)

response = client.logo_detection(image=image)
logos = response.logo_annotations
print("Logos:")

for logo in logos:
    print(logo.description)

if response.error.message:
    raise Exception(
        "{}\nFor more info on error messages, check: "
        "https://cloud.google.com/apis/design/errors".format(response.error.message)
    )

Membuat permintaan deteksi SafeSearch dan memproses respons

Kemungkinan SafeSearch kini ditampilkan sebagai enumerasi. Nama label kemungkinan dapat dipulihkan dengan mengimpor google.cloud.vision.enums.Likelihood.

Library klien versi sebelumnya::

with io.open(file_name, 'rb') as image_file:
    content = image_file.read()

image = old_client.image(content=content)

safe = image.detect_safe_search()
print('Safe search:')
print('adult: {}'.format(safe.adult))
print('medical: {}'.format(safe.medical))
print('spoofed: {}'.format(safe.spoof))
print('violence: {}'.format(safe.violence))

Library Klien Python v0.25.1:

with open(path, "rb") as image_file:
    content = image_file.read()

image = vision.Image(content=content)

response = client.safe_search_detection(image=image)
safe = response.safe_search_annotation

# Names of likelihood from google.cloud.vision.enums
likelihood_name = (
    "UNKNOWN",
    "VERY_UNLIKELY",
    "UNLIKELY",
    "POSSIBLE",
    "LIKELY",
    "VERY_LIKELY",
)
print("Safe search:")

print(f"adult: {likelihood_name[safe.adult]}")
print(f"medical: {likelihood_name[safe.medical]}")
print(f"spoofed: {likelihood_name[safe.spoof]}")
print(f"violence: {likelihood_name[safe.violence]}")
print(f"racy: {likelihood_name[safe.racy]}")

if response.error.message:
    raise Exception(
        "{}\nFor more info on error messages, check: "
        "https://cloud.google.com/apis/design/errors".format(response.error.message)
    )

Membuat permintaan deteksi teks dan memproses respons

Library klien versi sebelumnya::

with io.open(file_name, 'rb') as image_file:
    content = image_file.read()

image = old_client.image(content=content)

texts = image.detect_text()

for text in texts:
    print('\n"{}"'.format(text.description))

    vertices = (['({},{})'.format(bound.x_coordinate, bound.y_coordinate)
                for bound in text.bounds.vertices])

    print('bounds: {}'.format(','.join(vertices)))

Library Klien Python v0.25.1:

with open(path, "rb") as image_file:
    content = image_file.read()

image = vision.Image(content=content)

response = client.text_detection(image=image)
texts = response.text_annotations
print("Texts:")

for text in texts:
    print(f'\n"{text.description}"')

    vertices = [
        f"({vertex.x},{vertex.y})" for vertex in text.bounding_poly.vertices
    ]

    print("bounds: {}".format(",".join(vertices)))

if response.error.message:
    raise Exception(
        "{}\nFor more info on error messages, check: "
        "https://cloud.google.com/apis/design/errors".format(response.error.message)
    )

Membuat permintaan deteksi teks dokumen dan memproses respons

Library klien versi sebelumnya::

with io.open(file_name, 'rb') as image_file:
    content = image_file.read()

image = old_client.image(content=content)

document = image.detect_full_text()

for page in document.pages:
    for block in page.blocks:
        block_words = []
        for paragraph in block.paragraphs:
            block_words.extend(paragraph.words)

        block_symbols = []
        for word in block_words:
            block_symbols.extend(word.symbols)

        block_text = ''
        for symbol in block_symbols:
            block_text = block_text + symbol.text

        print('Block Content: {}'.format(block_text))
        print('Block Bounds:\n {}'.format(block.bounding_box))

Library Klien Python v0.25.1:

with open(path, "rb") as image_file:
    content = image_file.read()

image = vision.Image(content=content)

response = client.document_text_detection(image=image)

for page in response.full_text_annotation.pages:
    for block in page.blocks:
        print(f"\nBlock confidence: {block.confidence}\n")

        for paragraph in block.paragraphs:
            print("Paragraph confidence: {}".format(paragraph.confidence))

            for word in paragraph.words:
                word_text = "".join([symbol.text for symbol in word.symbols])
                print(
                    "Word text: {} (confidence: {})".format(
                        word_text, word.confidence
                    )
                )

                for symbol in word.symbols:
                    print(
                        "\tSymbol: {} (confidence: {})".format(
                            symbol.text, symbol.confidence
                        )
                    )

if response.error.message:
    raise Exception(
        "{}\nFor more info on error messages, check: "
        "https://cloud.google.com/apis/design/errors".format(response.error.message)
    )

Membuat permintaan properti gambar dan memproses respons

Informasi warna dominan kini disimpan di props.dominant_colors.colors, bukan props.colors.

Library klien versi sebelumnya::

with io.open(file_name, 'rb') as image_file:
    content = image_file.read()

image = old_client.image(content=content)

props = image.detect_properties()

for color in props.colors:
    print('fraction: {}'.format(color.pixel_fraction))
    print('\tr: {}'.format(color.color.red))
    print('\tg: {}'.format(color.color.green))
    print('\tb: {}'.format(color.color.blue))
    print('\ta: {}'.format(color.color.alpha))

Library Klien Python v0.25.1:

with open(path, "rb") as image_file:
    content = image_file.read()

image = vision.Image(content=content)

response = client.image_properties(image=image)
props = response.image_properties_annotation
print("Properties:")

for color in props.dominant_colors.colors:
    print(f"fraction: {color.pixel_fraction}")
    print(f"\tr: {color.color.red}")
    print(f"\tg: {color.color.green}")
    print(f"\tb: {color.color.blue}")
    print(f"\ta: {color.color.alpha}")

if response.error.message:
    raise Exception(
        "{}\nFor more info on error messages, check: "
        "https://cloud.google.com/apis/design/errors".format(response.error.message)
    )

Membuat permintaan deteksi web dan memproses respons

Library klien versi sebelumnya::

with io.open(file_name, 'rb') as image_file:
    content = image_file.read()

image = old_client.image(content=content)

notes = image.detect_web()

if notes.pages_with_matching_images:
    print('\n{} Pages with matching images retrieved')

    for page in notes.pages_with_matching_images:
        print('Score : {}'.format(page.score))
        print('Url   : {}'.format(page.url))

if notes.full_matching_images:
    print ('\n{} Full Matches found: '.format(
           len(notes.full_matching_images)))

    for image in notes.full_matching_images:
        print('Score:  {}'.format(image.score))
        print('Url  : {}'.format(image.url))

if notes.partial_matching_images:
    print ('\n{} Partial Matches found: '.format(
           len(notes.partial_matching_images)))

    for image in notes.partial_matching_images:
        print('Score: {}'.format(image.score))
        print('Url  : {}'.format(image.url))

if notes.web_entities:
    print ('\n{} Web entities found: '.format(len(notes.web_entities)))

    for entity in notes.web_entities:
        print('Score      : {}'.format(entity.score))
        print('Description: {}'.format(entity.description))

Library Klien Python v0.25.1:

with open(path, "rb") as image_file:
    content = image_file.read()

image = vision.Image(content=content)

response = client.web_detection(image=image)
annotations = response.web_detection

if annotations.best_guess_labels:
    for label in annotations.best_guess_labels:
        print(f"\nBest guess label: {label.label}")

if annotations.pages_with_matching_images:
    print(
        "\n{} Pages with matching images found:".format(
            len(annotations.pages_with_matching_images)
        )
    )

    for page in annotations.pages_with_matching_images:
        print(f"\n\tPage url   : {page.url}")

        if page.full_matching_images:
            print(
                "\t{} Full Matches found: ".format(len(page.full_matching_images))
            )

            for image in page.full_matching_images:
                print(f"\t\tImage url  : {image.url}")

        if page.partial_matching_images:
            print(
                "\t{} Partial Matches found: ".format(
                    len(page.partial_matching_images)
                )
            )

            for image in page.partial_matching_images:
                print(f"\t\tImage url  : {image.url}")

if annotations.web_entities:
    print("\n{} Web entities found: ".format(len(annotations.web_entities)))

    for entity in annotations.web_entities:
        print(f"\n\tScore      : {entity.score}")
        print(f"\tDescription: {entity.description}")

if annotations.visually_similar_images:
    print(
        "\n{} visually similar images found:\n".format(
            len(annotations.visually_similar_images)
        )
    )

    for image in annotations.visually_similar_images:
        print(f"\tImage url    : {image.url}")

if response.error.message:
    raise Exception(
        "{}\nFor more info on error messages, check: "
        "https://cloud.google.com/apis/design/errors".format(response.error.message)
    )

Membuat permintaan petunjuk pangkas dan memproses respons

Library klien versi sebelumnya::

with io.open(file_name, 'rb') as image_file:
    content = image_file.read()

image = old_client.image(content=content)

hints = image.detect_crop_hints(aspect_ratios=[1.77])

for n, hint in enumerate(hints):
    print('\nCrop Hint: {}'.format(n))

    vertices = (['({},{})'.format(bound.x_coordinate, bound.y_coordinate)
                for bound in hint.bounds.vertices])

    print('bounds: {}'.format(','.join(vertices)))

Library Klien Python v0.25.1:

with open(path, "rb") as image_file:
    content = image_file.read()
image = vision.Image(content=content)

crop_hints_params = vision.CropHintsParams(aspect_ratios=[1.77])
image_context = vision.ImageContext(crop_hints_params=crop_hints_params)

response = client.crop_hints(image=image, image_context=image_context)
hints = response.crop_hints_annotation.crop_hints

for n, hint in enumerate(hints):
    print(f"\nCrop Hint: {n}")

    vertices = [
        f"({vertex.x},{vertex.y})" for vertex in hint.bounding_poly.vertices
    ]

    print("bounds: {}".format(",".join(vertices)))

if response.error.message:
    raise Exception(
        "{}\nFor more info on error messages, check: "
        "https://cloud.google.com/apis/design/errors".format(response.error.message)
    )

Perhatikan bahwa rasio aspek harus dimasukkan melalui CropHintsParams dan ImageContext.