命名实体识别 - 向量检索服务 Milvus 版

AI_ENTITY_EXTRACT 函数可从文本、图片或视频中识别人名、组织、地点、时间和金额等命名实体，适用于新闻索引、媒体资产标注和事件检索等场景。

命令格式

REST 接口

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

{
  "model_name": "<模型名>",
  "texts": ["<文本或媒体URL>"],
  "params": {"entity_types": ["PERSON", "ORGANIZATION"]}
}

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("entities", DataType.JSON)
schema.add_field("dummy_vector", DataType.FLOAT_VECTOR, dim=2)
schema.add_function(
    Function(
        name="extract_entities",
        function_type=texttransform_function_type(),
        input_field_names=["content"],
        output_field_names=["entities"],
        params={
            "provider": "aliyun_milvus",
            "model_name": "<模型名>",
            "task": "ai_entity_extract",
            "entity_types": "PERSON,ORGANIZATION,LOCATION,DATE,PRODUCT",
            "temperature": "0",
        },
    )
)

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。待识别文本，或可被模型访问的图片/视频 URL。
`entity_types`	选填。目标实体类型，支持数组或逗号分隔字符串，数量为 1~30。省略时默认识别人、组织、地点、产品、事件、日期、时间、金额、百分比、URL、邮箱、电话和 IP。
`prompt`	选填。补充识别规则，最大 5000 字符，不支持 `${...}`。媒体场景建议明确要求“不根据外观猜测身份、品牌或地点”。
`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。
`provider` / `task`	仅 Collection Function 必填，固定为 `aliyun_milvus` 与 `ai_entity_extract`。

返回值说明

每项输出是 {"entities":[{"text":"实体文本","type":"实体类型"}]} 形式的 JSON 对象或可解析为该对象的 JSON 字符串。entities 的每项应含非空 text 和请求中的 type；未识别到符合条件的命名实体时，{"entities":[ ]} 是合法且更真实的结果。Schema 会将合法 JSON 写入输出字段。

示例一：为新闻建立实体索引（文本）

内容平台从新闻中抽取明确出现的人物、机构、地点、日期和产品，作为检索过滤条件。示例验证 JSON 结构和类型，不要求模型返回完全相同的实体列表。

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=$(cat <<JSON
{
  "model_name": "qwen3.7-max",
  "texts": [
    "In March 2024, Zhang San joined Alibaba in Hangzhou to work on Milvus."
  ],
  "params": {
    "entity_types": ["PERSON", "ORGANIZATION", "LOCATION", "DATE", "PRODUCT"],
    "temperature": 0
  }
}
JSON
)
RESPONSE_BODY="$(post_json "/v2/vectordb/ai/entity_extract" "$BODY")"
if command -v jq >/dev/null 2>&1; then
  echo "$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_entity_extract_text",
    input_fields=[("content", DataType.VARCHAR, 4096)],
    output_field=("entities", DataType.JSON, None),
    function_name="extract_entities",
    function_params={"provider": "aliyun_milvus", "model_name": "qwen3.7-max", "task": "ai_entity_extract", "entity_types": "PERSON,ORGANIZATION,LOCATION,DATE,PRODUCT", "temperature": "0"},
    rows=[{"content": "In March 2024, Zhang San joined Alibaba in Hangzhou to work on Milvus.", "dummy_vector": [0.1, 0.2]}],
)

预期结果：entities 中每项含非空 text 且 type 属于请求集合。实测返回 {"entities":[{"text":"March 2024","type":"DATE"},{"text":"Zhang San","type":"PERSON"},{"text":"Alibaba","type":"ORGANIZATION"},{"text":"Hangzhou","type":"LOCATION"},{"text":"Milvus","type":"PRODUCT"}]}，实际边界以模型和实体规则为准。

示例二：审核服饰宣传图中的命名实体（图片）

素材库收到一张人物穿黑白条纹上衣、手持黑色包的图片。这些只是可见对象，不等于可确认的人名、品牌、商品名或地点；因此示例明确禁止猜测，并接受空 entities 作为真实结果。

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=$(cat <<JSON
{"model_name":"qwen3.7-plus","texts":["https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260415/hynnff/wan-video-edit-clothes.webp"],"params":{"media_type":"image","entity_types":["PERSON","PRODUCT","LOCATION"],"temperature":0}}
JSON
)
RESPONSE_BODY="$(post_json "/v2/vectordb/ai/entity_extract" "$BODY")"
if command -v jq >/dev/null 2>&1; then
  echo "$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_entity_extract_image",
    input_fields=[("image_url", DataType.VARCHAR, 4096)],
    output_field=("entities", DataType.JSON, None),
    function_name="extract_image_entities",
    function_params={"provider": "aliyun_milvus", "model_name": "qwen3.7-plus", "task": "ai_entity_extract", "media_type": "image", "entity_types": "PERSON,PRODUCT,LOCATION", "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：输出是合法实体对象，且每项类型属于请求集合。如图片没有足够证据确认命名实体，{"entities":[ ]} 是预期范围内的真实结果，不应为了“有数据”而猜测。

示例三：审核拟人马角色视频中的命名实体（视频）

视频素材近景呈现一个穿西装的拟人马角色。角色外观不能证明真实人物身份、作品名、品牌或地点；因此该素材也采用“有明确证据才抽取”的规则，空实体数组属于正常结果。

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=$(cat <<JSON
{"model_name":"qwen3.7-plus","texts":["https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260409/dozxak/Wan_Video_Edit_33_1.mp4"],"params":{"media_type":"video","entity_types":["PERSON","PRODUCT","LOCATION"],"temperature":0}}
JSON
)
RESPONSE_BODY="$(post_json "/v2/vectordb/ai/entity_extract" "$BODY")"
if command -v jq >/dev/null 2>&1; then
  echo "$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_entity_extract_video",
    input_fields=[("video_url", DataType.VARCHAR, 4096)],
    output_field=("entities", DataType.JSON, None),
    function_name="extract_video_entities",
    function_params={"provider": "aliyun_milvus", "model_name": "qwen3.7-plus", "task": "ai_entity_extract", "media_type": "video", "entity_types": "PERSON,PRODUCT,LOCATION", "temperature": "0"},
    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：输出结构正确，实体类型均属于请求集合，或返回空 entities。实测视频返回 {"entities":[]}（无可确认命名实体，合法）。如需角色类型、服装或运动描述，应使用内容摘要/分类能力，不应将普通视觉属性冒充为命名实体。