Sınıflandırma - Vector Retrieval Service for Milvus - Alibaba Cloud Dokümantasyon Merkezi

AI_CLASSIFY, metinler, görseller veya videolar için aday etiketler kümesinden en uygun eşleşen etiketi seçer. Bilet yönlendirme, içerik denetleme veya ürün kategorisi etiketleme senaryolarında kullanın. Bir Koleksiyon İşlevi olarak yapılandırıldığında AI_CLASSIFY, veri yazma sırasında sınıflandırma alanını otomatik olarak doldurur.

Komut biçimi

İçeriği doğrudan sınıflandırmak için REST API'yi çağırın veya veri yazma sırasında otomatik sınıflandırma yapmak üzere bir Koleksiyon İşlevi yapılandırın. REST API iki uç noktayı destekler:

/v2/vectordb/ai/text_transform — İstek gövdesine "task": "ai_classify" ekleyin.
/v2/vectordb/ai/classify — task alanı gerekli değildir.

REST API

@id="cmdtabbcls001"

REST API

@id="c0004c9x7t"

Girdi içeriğini sınıflandırmak için aşağıdaki isteği gönderin:

POST /v2/vectordb/ai/text_transform
Content-Type: application/json

{
  "model_name": "<model name>",
  "task": "ai_classify",
  "texts": ["<text or media URL>"],
  "params": {"labels": ["<label1>", "<label2>"]}
}

@id="cmdrestscls01"

@id="cmdresthcls01"

Python

@id="cmdpyseccls01"

Python

@id="cmdpycodcls01"

Veri yazma sırasında içeriği otomatik olarak sınıflandırmak için bir Koleksiyon İşlevi tanımlayın:

schema = MilvusClient.create_schema(auto_id=True, enable_dynamic_field=False)
schema.add_field("id", DataType.INT64, is_primary=True)
schema.add_field("content", DataType.VARCHAR, max_length=4096)
schema.add_field("category", DataType.VARCHAR, max_length=64)
schema.add_field("dummy_vector", DataType.FLOAT_VECTOR, dim=2)
schema.add_function(
    Function(
        name="classify_content",
        function_type=texttransform_function_type(),
        input_field_names=["content"],
        output_field_names=["category"],
        params={
            "provider": "aliyun_milvus",
            "model_name": "<model name>",
            "task": "ai_classify",
            "labels": "accounts,inquiries,faults,billing",
            "prompt": "Classify by the topic of the customer's question.",
            "temperature": "0",
            "max_concurrency": "2",
        },
    )
)

@id="cmdpyhcls0001"

Parametreler

@id="p0046c9x7t" Parametre	@id="p0048c9x7t" Açıklama
@id="p0008c9x7t" `model_name`	@id="p0010c9x7t" Gereklidir. Model adıdır. Görseller ve videolar için yapılandırılmış çok modlu bir model seçin (örneğin `qwen3.7-plus`).
@id="p0013c9x7t" `texts`	@id="p0015c9x7t" REST API için gereklidir. Sınıflandırılacak içerik veya bir görsel ya da video URL'sidir.
@id="p0018c9x7t" `labels`	@id="p0020c9x7t" Gereklidir. Aday etiketlerdir; JSON dize dizisi veya virgülle ayrılmış dize olarak sağlanır. 2 ile 20 arasında etiket desteklenir.
@id="p0023c9x7t" `prompt`	@id="p0025c9x7t" İsteğe bağlıdır. Ek yönlendirme kurallarıdır, en fazla 5.000 karakter olabilir. `${...}` desteklenmez.
@id="p0028c9x7t" `media_type`	@id="p0030c9x7t" İsteğe bağlıdır. Girdinin bir medya URL'si olduğunu belirtmek için `image` veya `video` olarak ayarlayın.
@id="p0033c9x7t" `temperature` / `max_concurrency` / `timeout_sec`	@id="p0035c9x7t" İsteğe bağlıdır. Model kararlılığını, eşzamanlılığı ve zaman aşımını kontrol eder. Video sınıflandırma zaman alıcıdır. Zaman aşımını önlemek için `timeout_sec` değerini 300 veya daha yüksek ayarlayın.
@id="p0038c9x7t" `provider` / `task`	@id="p0040c9x7t" Yalnızca Koleksiyon İşlevi için gereklidir. Sabit değerler: `aliyun_milvus` ve `ai_classify`.

Dönüş değerleri

data.output.outputs yalnızca etiketin kendisini içeren etiket metnini girdiyle aynı sırada döndürür. Şema, etiketi hedef metin alanına yazar.

Örnek 1: Müşteri biletlerini otomatik yönlendirme (metin)

Bir müşteri hizmetleri sistemi, arıza ve bilgi talebi biletlerini farklı kuyruklara yönlendirmelidir. Birleşik uç nokta /v2/vectordb/ai/text_transform çağrılırken isteğin en üst düzeyine task ekleyin.

REST API

@id="tab0057c9x7t"

REST API

@id="c0052c9x7t"

#!/usr/bin/env bash
set -euo pipefail

MILVUS_REST_BASE_URL="http://c-xxxx.milvus.aliyuncs.com:19530"
MILVUS_AUTH_TOKEN="<yourUsername>:<yourPassword>"

post_json() {
  local path="$1"
  local body="$2"
  curl -X POST \
    "$MILVUS_REST_BASE_URL$path" \
    -H "Authorization: Bearer $MILVUS_AUTH_TOKEN" \
    -H "Content-Type: application/json" \
    -d "$body"
}

BODY=$(cat <<'JSON'
{
  "model_name": "qwen3.7-max",
  "task": "ai_classify",
  "texts": [
    "Cannot log in to the Milvus console; verification code error keeps appearing.",
    "How do I enable public network access for a Serverless Milvus instance?"
  ],
  "params": {
    "labels": ["accounts", "inquiries", "faults", "billing"],
    "prompt": "Classify by the topic of the customer's question.",
    "temperature": 0,
    "max_concurrency": 2
  }
}
JSON
)
RESPONSE_BODY="$(post_json "/v2/vectordb/ai/text_transform" "$BODY")"
if command -v jq >/dev/null 2>&1; then
  echo "$RESPONSE_BODY" | jq .
  [ "$(echo "$RESPONSE_BODY" | jq -r '.code // -1')" = "0" ] || exit 1
else
  echo "$RESPONSE_BODY"
fi

@id="rt0058c9x7t"

@id="h0059c9x7t"

Python

@id="pt0060c9x7t"

Python

@id="c0053c9x7t"

from __future__ import annotations

from typing import Any

from pymilvus import DataType, Function, FunctionType, MilvusClient

MILVUS_URI = "http://c-xxxx.milvus.aliyuncs.com:19530"
MILVUS_TOKEN = "<yourUsername>:<yourPassword>"

DUMMY_VECTOR_DIM = 2
TEXTTRANSFORM_FUNCTION_TYPE = 9

def texttransform_function_type() -> Any:
    for type_name in ("TEXTTRANSFORM", "TEXT_TRANSFORM", "TextTransform"):
        function_type = getattr(FunctionType, type_name, None)
        if function_type is not None:
            return function_type
    # Alibaba Cloud Milvus provides TEXTTRANSFORM as a managed extension (function type value 9);
    # some pymilvus versions do not include this enum member, while Function(...) validates through FunctionType(...).
    existing = getattr(FunctionType, "_value2member_map_", {}).get(TEXTTRANSFORM_FUNCTION_TYPE)
    if existing is not None:
        return existing
    extension = int.__new__(FunctionType, TEXTTRANSFORM_FUNCTION_TYPE)
    extension._name_ = "TEXTTRANSFORM"
    extension._value_ = TEXTTRANSFORM_FUNCTION_TYPE
    FunctionType._value2member_map_[TEXTTRANSFORM_FUNCTION_TYPE] = extension
    FunctionType._member_map_["TEXTTRANSFORM"] = extension
    return extension

def add_id(schema: Any) -> None:
    schema.add_field("id", DataType.INT64, is_primary=True)

def add_dummy_vector(schema: Any) -> None:
    schema.add_field("dummy_vector", DataType.FLOAT_VECTOR, dim=DUMMY_VECTOR_DIM)

def run_texttransform_example(*, client, collection_name, input_fields, output_field, function_name, function_params, rows) -> None:
    if client.has_collection(collection_name):
        client.drop_collection(collection_name)
    schema = MilvusClient.create_schema(auto_id=True, enable_dynamic_field=False)
    add_id(schema)
    for name, data_type, max_length in input_fields:
        field_params = {"max_length": max_length} if max_length is not None else {}
        schema.add_field(name, data_type, **field_params)
    output_name, output_data_type, output_max_length = output_field
    output_params = {"max_length": output_max_length} if output_max_length is not None else {}
    schema.add_field(output_name, output_data_type, **output_params)
    add_dummy_vector(schema)
    schema.add_function(
        Function(
            name=function_name,
            function_type=texttransform_function_type(),
            input_field_names=[name for name, _, _ in input_fields],
            output_field_names=[output_name],
            params=function_params,
        )
    )
    index_params = client.prepare_index_params()
    index_params.add_index(field_name="dummy_vector", index_type="AUTOINDEX", metric_type="COSINE")
    client.create_collection(collection_name=collection_name, schema=schema, index_params=index_params)
    client.insert(collection_name, rows)
    client.flush(collection_name)
    fields = [name for name, _, _ in input_fields] + [output_name]
    for row in client.query(collection_name, filter="", output_fields=fields, limit=len(rows)):
        print(row)

client = MilvusClient(uri=MILVUS_URI, token=MILVUS_TOKEN)

run_texttransform_example(
    client=client,
    collection_name="simple_ai_classify",
    input_fields=[("content", DataType.VARCHAR, 4096)],
    output_field=("category", DataType.VARCHAR, 64),
    function_name="simple_ai_classify_fn",
    function_params={"provider": "aliyun_milvus", "model_name": "qwen3.7-max", "task": "ai_classify", "labels": "accounts,inquiries,faults,billing", "prompt": "Classify by the topic of the customer's question.", "temperature": "0", "max_concurrency": "2"},
    rows=[{"content": "Cannot log in to the Milvus console; verification code error keeps appearing.", "dummy_vector": [0.1, 0.2]}, {"content": "How do I enable public network access for a Serverless Milvus instance?", "dummy_vector": [0.1, 0.2]}],
)

@id="h0061c9x7t"

Beklenen sonuç: Her REST girdisi için bir aday etiket döndürülür (testte: accounts ve inquiries). Python kayıtlarındaki category alanı ilgili aday etiketi tutar. Oturum açma ve doğrulama kodu sorunları, modelin yargısına bağlı olarak accounts veya faults kategorisine yönlendirilir.

Örnek 2: Ürün görsellerini sınıflandırma (görsel)

Bir içerik denetleme sisteminin görselleri otomatik olarak giyim, yiyecek, manzara veya hayvan kategorilerine ataması gerekir.

REST API

@id="tab0068c9x7t"

REST API

@id="c0063c9x7t"

#!/usr/bin/env bash
set -euo pipefail

MILVUS_REST_BASE_URL="http://c-xxxx.milvus.aliyuncs.com:19530"
MILVUS_AUTH_TOKEN="<yourUsername>:<yourPassword>"

post_json() {
  local path="$1"
  local body="$2"
  curl -X POST \
    "$MILVUS_REST_BASE_URL$path" \
    -H "Authorization: Bearer $MILVUS_AUTH_TOKEN" \
    -H "Content-Type: application/json" \
    -d "$body"
}

BODY=$(cat <<JSON
{"model_name":"qwen3.7-plus","texts":["https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260415/hynnff/wan-video-edit-clothes.webp"],"params":{"media_type":"image","labels":["clothing","food","landscape","animal"],"temperature":0}}
JSON
)
RESPONSE_BODY="$(post_json "/v2/vectordb/ai/classify" "$BODY")"
if command -v jq >/dev/null 2>&1; then
  echo "$RESPONSE_BODY" | jq .
  [ "$(echo "$RESPONSE_BODY" | jq -r '.code // -1')" = "0" ] || exit 1
else
  echo "$RESPONSE_BODY"
fi

@id="rt0069c9x7t"

@id="h0070c9x7t"

Python

@id="pt0071c9x7t"

Python

@id="c0064c9x7t"

from __future__ import annotations

from typing import Any

from pymilvus import DataType, Function, FunctionType, MilvusClient

MILVUS_URI = "http://c-xxxx.milvus.aliyuncs.com:19530"
MILVUS_TOKEN = "<yourUsername>:<yourPassword>"

DUMMY_VECTOR_DIM = 2
TEXTTRANSFORM_FUNCTION_TYPE = 9

def texttransform_function_type() -> Any:
    for type_name in ("TEXTTRANSFORM", "TEXT_TRANSFORM", "TextTransform"):
        function_type = getattr(FunctionType, type_name, None)
        if function_type is not None:
            return function_type
    # Alibaba Cloud Milvus provides TEXTTRANSFORM as a managed extension (function type value 9);
    # some pymilvus versions do not include this enum member, while Function(...) validates through FunctionType(...).
    existing = getattr(FunctionType, "_value2member_map_", {}).get(TEXTTRANSFORM_FUNCTION_TYPE)
    if existing is not None:
        return existing
    extension = int.__new__(FunctionType, TEXTTRANSFORM_FUNCTION_TYPE)
    extension._name_ = "TEXTTRANSFORM"
    extension._value_ = TEXTTRANSFORM_FUNCTION_TYPE
    FunctionType._value2member_map_[TEXTTRANSFORM_FUNCTION_TYPE] = extension
    FunctionType._member_map_["TEXTTRANSFORM"] = extension
    return extension

def add_id(schema: Any) -> None:
    schema.add_field("id", DataType.INT64, is_primary=True)

def add_dummy_vector(schema: Any) -> None:
    schema.add_field("dummy_vector", DataType.FLOAT_VECTOR, dim=DUMMY_VECTOR_DIM)

def run_texttransform_example(*, client, collection_name, input_fields, output_field, function_name, function_params, rows) -> None:
    if client.has_collection(collection_name):
        client.drop_collection(collection_name)
    schema = MilvusClient.create_schema(auto_id=True, enable_dynamic_field=False)
    add_id(schema)
    for name, data_type, max_length in input_fields:
        field_params = {"max_length": max_length} if max_length is not None else {}
        schema.add_field(name, data_type, **field_params)
    output_name, output_data_type, output_max_length = output_field
    output_params = {"max_length": output_max_length} if output_max_length is not None else {}
    schema.add_field(output_name, output_data_type, **output_params)
    add_dummy_vector(schema)
    schema.add_function(
        Function(
            name=function_name,
            function_type=texttransform_function_type(),
            input_field_names=[name for name, _, _ in input_fields],
            output_field_names=[output_name],
            params=function_params,
        )
    )
    index_params = client.prepare_index_params()
    index_params.add_index(field_name="dummy_vector", index_type="AUTOINDEX", metric_type="COSINE")
    client.create_collection(collection_name=collection_name, schema=schema, index_params=index_params)
    client.insert(collection_name, rows)
    client.flush(collection_name)
    fields = [name for name, _, _ in input_fields] + [output_name]
    for row in client.query(collection_name, filter="", output_fields=fields, limit=len(rows)):
        print(row)

client = MilvusClient(uri=MILVUS_URI, token=MILVUS_TOKEN)

run_texttransform_example(
    client=client,
    collection_name="simple_ai_classify_image",
    input_fields=[("image_url", DataType.VARCHAR, 4096)],
    output_field=("category", DataType.VARCHAR, 64),
    function_name="simple_ai_classify_image_fn",
    function_params={"provider": "aliyun_milvus", "model_name": "qwen3.7-plus", "task": "ai_classify", "media_type": "image", "labels": "clothing,food,landscape,animal", "temperature": "0"},
    rows=[{"image_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260415/hynnff/wan-video-edit-clothes.webp", "dummy_vector": [0.1, 0.2]}],
)

@id="h0072c9x7t"

Beklenen sonuç:category alanı clothing, food, landscape veya animal değerlerinden birini döndürür (testte: clothing).

Örnek 3: Video materyallerini sınıflandırma (video)

Bir video operasyon ekibinin materyalleri moda, spor, seyahat ve animasyon kategorilerine göre filtrelemesi gerekir. Video çıkarımı zaman alıcıdır. timeout_sec değerini 300 veya daha yüksek ayarlayın.

REST API

@id="tab0079c9x7t"

REST API

@id="c0074c9x7t"

#!/usr/bin/env bash
set -euo pipefail

MILVUS_REST_BASE_URL="http://c-xxxx.milvus.aliyuncs.com:19530"
MILVUS_AUTH_TOKEN="<yourUsername>:<yourPassword>"

post_json() {
  local path="$1"
  local body="$2"
  curl -X POST \
    "$MILVUS_REST_BASE_URL$path" \
    -H "Authorization: Bearer $MILVUS_AUTH_TOKEN" \
    -H "Content-Type: application/json" \
    -d "$body"
}

BODY=$(cat <<JSON
{"model_name":"qwen3.7-plus","texts":["https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260409/dozxak/Wan_Video_Edit_33_1.mp4"],"params":{"media_type":"video","labels":["fashion","sports","travel","animation"],"temperature":0,"timeout_sec":300}}
JSON
)
RESPONSE_BODY="$(post_json "/v2/vectordb/ai/classify" "$BODY")"
if command -v jq >/dev/null 2>&1; then
  echo "$RESPONSE_BODY" | jq .
  [ "$(echo "$RESPONSE_BODY" | jq -r '.code // -1')" = "0" ] || exit 1
else
  echo "$RESPONSE_BODY"
fi

@id="rt0080c9x7t"

@id="h0081c9x7t"

Python

@id="pt0082c9x7t"

Python

@id="c0075c9x7t"

from __future__ import annotations

from typing import Any

from pymilvus import DataType, Function, FunctionType, MilvusClient

MILVUS_URI = "http://c-xxxx.milvus.aliyuncs.com:19530"
MILVUS_TOKEN = "<yourUsername>:<yourPassword>"

DUMMY_VECTOR_DIM = 2
TEXTTRANSFORM_FUNCTION_TYPE = 9

def texttransform_function_type() -> Any:
    for type_name in ("TEXTTRANSFORM", "TEXT_TRANSFORM", "TextTransform"):
        function_type = getattr(FunctionType, type_name, None)
        if function_type is not None:
            return function_type
    # Alibaba Cloud Milvus provides TEXTTRANSFORM as a managed extension (function type value 9);
    # some pymilvus versions do not include this enum member, while Function(...) validates through FunctionType(...).
    existing = getattr(FunctionType, "_value2member_map_", {}).get(TEXTTRANSFORM_FUNCTION_TYPE)
    if existing is not None:
        return existing
    extension = int.__new__(FunctionType, TEXTTRANSFORM_FUNCTION_TYPE)
    extension._name_ = "TEXTTRANSFORM"
    extension._value_ = TEXTTRANSFORM_FUNCTION_TYPE
    FunctionType._value2member_map_[TEXTTRANSFORM_FUNCTION_TYPE] = extension
    FunctionType._member_map_["TEXTTRANSFORM"] = extension
    return extension

def add_id(schema: Any) -> None:
    schema.add_field("id", DataType.INT64, is_primary=True)

def add_dummy_vector(schema: Any) -> None:
    schema.add_field("dummy_vector", DataType.FLOAT_VECTOR, dim=DUMMY_VECTOR_DIM)

def run_texttransform_example(*, client, collection_name, input_fields, output_field, function_name, function_params, rows) -> None:
    if client.has_collection(collection_name):
        client.drop_collection(collection_name)
    schema = MilvusClient.create_schema(auto_id=True, enable_dynamic_field=False)
    add_id(schema)
    for name, data_type, max_length in input_fields:
        field_params = {"max_length": max_length} if max_length is not None else {}
        schema.add_field(name, data_type, **field_params)
    output_name, output_data_type, output_max_length = output_field
    output_params = {"max_length": output_max_length} if output_max_length is not None else {}
    schema.add_field(output_name, output_data_type, **output_params)
    add_dummy_vector(schema)
    schema.add_function(
        Function(
            name=function_name,
            function_type=texttransform_function_type(),
            input_field_names=[name for name, _, _ in input_fields],
            output_field_names=[output_name],
            params=function_params,
        )
    )
    index_params = client.prepare_index_params()
    index_params.add_index(field_name="dummy_vector", index_type="AUTOINDEX", metric_type="COSINE")
    client.create_collection(collection_name=collection_name, schema=schema, index_params=index_params)
    client.insert(collection_name, rows)
    client.flush(collection_name)
    fields = [name for name, _, _ in input_fields] + [output_name]
    for row in client.query(collection_name, filter="", output_fields=fields, limit=len(rows)):
        print(row)

client = MilvusClient(uri=MILVUS_URI, token=MILVUS_TOKEN)

run_texttransform_example(
    client=client,
    collection_name="simple_ai_classify_video",
    input_fields=[("video_url", DataType.VARCHAR, 4096)],
    output_field=("category", DataType.VARCHAR, 64),
    function_name="simple_ai_classify_video_fn",
    function_params={"provider": "aliyun_milvus", "model_name": "qwen3.7-plus", "task": "ai_classify", "media_type": "video", "labels": "fashion,sports,travel,animation", "temperature": "0", "timeout_sec": "300"},
    rows=[{"video_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260409/dozxak/Wan_Video_Edit_33_1.mp4", "dummy_vector": [0.1, 0.2]}],
)

@id="h0083c9x7t"

Beklenen sonuç:category alanı fashion, sports, travel veya animation değerlerinden birini döndürür (testte: animation). {"code":10001,"message":"request timeout"} yanıtı alınırsa timeout_sec değerini artırın.