分类 - 向量检索服务 Milvus 版

AI_CLASSIFY 函数可从给定标签中为文本、图片或视频选择最匹配的一项，适用于工单分流、内容审核和商品类目打标等场景。写入时可自动填充分类字段。

命令格式

REST 接口

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

{
  "model_name": "<模型名>",
  "task": "ai_classify",
  "texts": ["<文本或媒体URL>"],
  "params": {"labels": ["<标签1>", "<标签2>"]}
}

Python

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": "<模型名>",
            "task": "ai_classify",
            "labels": "账号,咨询,故障,计费",
            "prompt": "根据客户问题所属主题分类。",
            "temperature": "0",
            "max_concurrency": "2",
        },
    )
)

参数说明

参数	说明
`model_name`	必填。模型名称；图片和视频须选择已配置多模态模型（如 `qwen3.7-plus`）。
`texts`	REST 必填。待分类内容，或图片/视频 URL。
`labels`	必填。候选标签，支持 JSON 字符串数组或逗号分隔字符串，数量为 2~20。
`prompt`	选填。补充分流规则，最大 5000 字符，不支持 `${...}`。
`media_type`	选填。取值为 `image` 或 `video`，表示输入为媒体 URL。
`temperature` / `max_concurrency` / `timeout_sec`	选填。模型稳定性、并发和超时设置。视频分类耗时较长，建议将 `timeout_sec` 设为 300 以上，避免超时。
`provider` / `task`	仅 Collection Function 必填，固定为 `aliyun_milvus` 与 `ai_classify`。

返回值说明

data.output.outputs 返回与输入同序的标签文本，且只包含标签本身。Schema 会将标签写入目标文本字段。

示例一：客户工单自动分流（文本）

客服系统需要把故障和咨询类问题分配给不同队列。统一入口 /v2/vectordb/ai/text_transform 调用时在请求顶层增加 task。

REST 接口

#!/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=$(cat <<'JSON'
{
  "model_name": "qwen3.7-max",
  "task": "ai_classify",
  "texts": [
    "无法登录 Milvus 控制台，一直提示验证码错误。",
    "请问 Serverless Milvus 实例怎么开启公网访问？"
  ],
  "params": {
    "labels": ["账号", "咨询", "故障", "计费"],
    "prompt": "根据客户问题所属主题分类。",
    "temperature": 0,
    "max_concurrency": 2
  }
}
JSON
)
RESPONSE_BODY="$(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

Python

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
    # 阿里云 Milvus 将 TEXTTRANSFORM 作为托管扩展(函数类型值 9)提供;
    # 部分 pymilvus 版本尚未内置该枚举成员,而 Function(...) 通过 FunctionType(...) 校验。
    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": "账号,咨询,故障,计费", "prompt": "根据客户问题所属主题分类。", "temperature": "0", "max_concurrency": "2"},
    rows=[{"content": "无法登录 Milvus 控制台，一直提示验证码错误。", "dummy_vector": [0.1, 0.2]}, {"content": "请问 Serverless Milvus 实例怎么开启公网访问？", "dummy_vector": [0.1, 0.2]}],
)

预期结果：两条 REST 输入依次返回一个候选标签（实测为 账号、咨询）;Python 记录的 category 为对应候选标签（登录/验证码类问题会分到 账号 或 故障，以模型判断为准）。

示例二：为商品图片分类（图片）

审核系统需要将图片自动分入服饰、食品、风景或动物类别。

REST 接口

#!/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

Python

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
    # 阿里云 Milvus 将 TEXTTRANSFORM 作为托管扩展(函数类型值 9)提供;
    # 部分 pymilvus 版本尚未内置该枚举成员,而 Function(...) 通过 FunctionType(...) 校验。
    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]}],
)

预期结果：category 返回 clothing、food、landscape 或 animal 中的一个值（实测为 clothing）。

示例三：为视频素材分类（视频）

视频运营需要按时尚、运动、旅行和动画类目筛选素材。视频推理耗时较长，timeout_sec 建议设为 300 以上。

REST 接口

#!/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

Python

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
    # 阿里云 Milvus 将 TEXTTRANSFORM 作为托管扩展(函数类型值 9)提供;
    # 部分 pymilvus 版本尚未内置该枚举成员,而 Function(...) 通过 FunctionType(...) 校验。
    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]}],
)

预期结果：category 返回 fashion、sports、travel 或 animation 中的一个值（实测为 animation）。若返回 {"code":10001,"message":"request timeout"}，请调大 timeout_sec。