多模態產生 - Vector Retrieval Service for Milvus

AI_MULTI_MODAL_GENERATE 函數用於將文本、圖片、視頻或音頻轉換為文本結果，可用於商品素材描述、視頻摘要、視覺問答和語音轉寫等情境。

命令格式

REST 介面

POST /v2/vectordb/ai/multi_modal_generate
{
  "model_name": "<model_name>",
  "texts": ["<text_or_media_url>"],
  "params": {"media_type": "text | image | video | audio", "prompt": "<instruction>"}
}

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("generated", DataType.VARCHAR, max_length=1024)
schema.add_field("dummy_vector", DataType.FLOAT_VECTOR, dim=2)
schema.add_function(
    Function(
        name="generate_text",
        function_type=texttransform_function_type(),
        input_field_names=["content"],
        output_field_names=["generated"],
        params={
            "provider": "aliyun_milvus",
            "model_name": "<模型名>",
            "task": "ai_multi_modal_generate",
            "media_type": "text",
            "prompt": "Answer concisely: ${content}",
            "temperature": "0",
        },
    )
)

參數說明

參數	說明
`model_name`	必填。文本、圖片和視頻可使用 `qwen3.7-plus`（推薦）、`qwen3.6-plus`、`qwen3.6-flash`、`qwen3.5-flash` 或 `kimi-k2.6`；音頻使用 `qwen3-asr-flash`。
`texts`	REST 必填。`text` 傳原文，其他模態傳模型服務可訪問的 URL；圖片也可用 Base64 引用。結果與輸入順序一致。
`media_type`	必填。取值為 `text`、`image`、`video` 或 `audio`。
`prompt`	圖片和視頻必填，文本可選，音頻不支援。Schema 中可用 `${field_name}`。
`language` / `enable_itn`	僅音頻可選，分別指定識別語言（如 `zh`、`en`）和是否啟用逆文本正常化。
`timeout_sec` / `max_concurrency`	可選。控制單次調用逾時和批量並發數。
`output_mapping`	僅 Collection 的 text/image/video 情境可選；將模型輸出 JSON 的簡單路徑映射到多個 `VARCHAR`、`TEXT` 或 `JSON` 欄位。未設定時只能有一個文本輸出欄位。
`provider` / `task`	僅 Collection Function 必填，固定為 `aliyun_milvus` 與 `ai_multi_modal_generate`。

傳回值說明

成功時，data.output.outputs 是與 texts 一一對應的文本數組；data.usage 可能包含 input_tokens、output_tokens、image_tokens、video_tokens、audio_tokens、total_tokens 和音視頻時間長度 seconds。

樣本一：商品標題產生一句賣點（文本）

根據已有商品標題產生一句簡潔賣點。

REST 介面

#!/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=$(cat <<JSON
{
  "model_name": "qwen3.7-plus",
  "texts": ["Explain in one sentence how Milvus is used in a RAG application."],
  "params": {"media_type": "text", "prompt": "Answer concisely.", "temperature": 0}
}
JSON
)
RESPONSE_BODY="$(post_json "/v2/vectordb/ai/multi_modal_generate" "$BODY")"
if command -v jq >/dev/null 2>&1; then
  echo "$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
    # 阿里雲 Milvus 將 TEXTTRANSFORM 作為託管擴充(函數類型值 9)提供;
    # 部分 pymilvus 版本尚未內建該枚舉成員,而 Function(...) 通過 FunctionType(...) 校正。
    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_multi_modal_generate_text",
    input_fields=[("content", DataType.VARCHAR, 4096)],
    output_field=("generated", DataType.VARCHAR, 1024),
    function_name="generate_text",
    function_params={"provider": "aliyun_milvus", "model_name": "qwen3.7-plus", "task": "ai_multi_modal_generate", "media_type": "text", "prompt": "Answer concisely: ${content}", "temperature": "0"},
    rows=[{"content": "Explain how Milvus is used in a RAG application.", "dummy_vector": [0.1, 0.2]}],
)

預期結果：generated 得到一句（或一段）關於 Milvus 在 RAG 中作用的說明，位於 data.output.outputs[0]。

樣本二：商品圖片自動產生檢索描述（圖片）

將服裝素材入庫前產生一條用於圖文檢索的客觀描述，Curl 樣本需要 jq。

REST 介面

#!/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=$(cat <<JSON
{
  "model_name": "qwen3.7-plus",
  "texts": ["https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260415/hynnff/wan-video-edit-clothes.webp"],
  "params": {"media_type": "image", "prompt": "Describe the image in one concise sentence.", "temperature": 0}
}
JSON
)
RESPONSE_BODY="$(post_json "/v2/vectordb/ai/multi_modal_generate" "$BODY")"
if command -v jq >/dev/null 2>&1; then
  echo "$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
    # 阿里雲 Milvus 將 TEXTTRANSFORM 作為託管擴充(函數類型值 9)提供;
    # 部分 pymilvus 版本尚未內建該枚舉成員,而 Function(...) 通過 FunctionType(...) 校正。
    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_multi_modal_generate_image",
    input_fields=[("image_url", DataType.VARCHAR, 4096)],
    output_field=("description", DataType.VARCHAR, 2048),
    function_name="describe_image",
    function_params={"provider": "aliyun_milvus", "model_name": "qwen3.7-plus", "task": "ai_multi_modal_generate", "media_type": "image", "prompt": "Describe the image in one concise sentence.", "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]}],
)

預期結果：description 得到一句圖片客觀描述，可寫入商品檢索欄位。

樣本三：品牌角色概念片產生檢索摘要（視頻）

為概念片產生檢索摘要，方便按角色、動作和畫面氛圍檢索素材。只校正文本非空，不假設固定措辭。

REST 介面

#!/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=$(cat <<JSON
{
  "model_name": "qwen3.7-plus",
  "texts": ["https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260409/dozxak/Wan_Video_Edit_33_1.mp4"],
  "params": {"media_type": "video", "prompt": "Describe the video in one concise sentence.", "temperature": 0}
}
JSON
)
RESPONSE_BODY="$(post_json "/v2/vectordb/ai/multi_modal_generate" "$BODY")"
if command -v jq >/dev/null 2>&1; then
  echo "$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
    # 阿里雲 Milvus 將 TEXTTRANSFORM 作為託管擴充(函數類型值 9)提供;
    # 部分 pymilvus 版本尚未內建該枚舉成員,而 Function(...) 通過 FunctionType(...) 校正。
    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_multi_modal_generate_video",
    input_fields=[("video_url", DataType.VARCHAR, 4096)],
    output_field=("description", DataType.VARCHAR, 2048),
    function_name="describe_video",
    function_params={"provider": "aliyun_milvus", "model_name": "qwen3.7-plus", "task": "ai_multi_modal_generate", "media_type": "video", "prompt": "Describe the video in one concise sentence.", "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]}],
)

預期結果：description 得到一句視頻內容摘要，可用於創意素材檢索欄位。

樣本四：客服熱線歡迎語轉寫並歸檔（音頻）

將熱線歡迎語轉寫為可檢索文本便于歸檔；音頻請求無需傳 prompt，Curl 樣本需要 jq。範例音頻為公開歡迎語，轉寫語言以實際音頻為準。

REST 介面

#!/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=$(cat <<JSON
{
  "model_name": "qwen3-asr-flash",
  "texts": ["https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"],
  "params": {"media_type": "audio", "language": "en", "enable_itn": true}
}
JSON
)
RESPONSE_BODY="$(post_json "/v2/vectordb/ai/multi_modal_generate" "$BODY")"
if command -v jq >/dev/null 2>&1; then
  echo "$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
    # 阿里雲 Milvus 將 TEXTTRANSFORM 作為託管擴充(函數類型值 9)提供;
    # 部分 pymilvus 版本尚未內建該枚舉成員,而 Function(...) 通過 FunctionType(...) 校正。
    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_multi_modal_generate_audio",
    input_fields=[("audio_url", DataType.VARCHAR, 4096)],
    output_field=("transcript", DataType.VARCHAR, 4096),
    function_name="transcribe_audio",
    function_params={"provider": "aliyun_milvus", "model_name": "qwen3-asr-flash", "task": "ai_multi_modal_generate", "media_type": "audio", "language": "en", "enable_itn": "true"},
    rows=[{"audio_url": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3", "dummy_vector": [0.1, 0.2]}],
)

預期結果：transcript 得到非空轉寫文本（範例音頻轉寫為 歡迎使用阿里雲。）。轉寫文本可寫入檔案，但不應用範例程式碼自動作出合規結論。

媒體安全與留存

使用自有圖片、視頻或音頻前，請確認已獲得內容和肖像、聲音等相關授權。建議使用有時效的最小許可權 URL，並按業務的保留原則刪除轉寫和派生文本中的個人資訊。