本篇博客將探討如何將阿里云的 AI 服務(wù)與 Elasticsearch 集成。您將學(xué)習(xí)如何在 Elasticsearch 中設(shè)置和使用阿里巴巴的文本生成(chat completion)、重排序(rerank)、稀疏向量(sparse vector)和稠密向量(dense vector)服務(wù)。將這些多種類型的模型集成到推理任務(wù)中將增強包括 RAG 在內(nèi)的許多應(yīng)用場景的搜索相關(guān)性。阿里云團隊為 Elasticsearch 開放推理 API 貢獻代碼來支持這些任務(wù)類型，并且通過示例了解如何在 Elasticsearch 環(huán)境中配置和使用這些服務(wù)。注意阿里云使用?service_id?這樣的術(shù)語 而不是?model_id。

01使用阿里云 AI 搜索開放平臺中的基礎(chǔ)模型

本演練假設(shè)您已經(jīng)擁有阿里云的帳戶來使用阿里云 AI 搜索開放平臺。接下來，您需要創(chuàng)建一個工作空間和 API key 以用于創(chuàng)建推理模型。

02在 Elasticsearch 中創(chuàng)建推理 API 端點

在 Elasticsearch 中，通過“alibabacloud-ai-search”服務(wù)來創(chuàng)建端點，并提供服務(wù)設(shè)置，包括工作空間、主機地址、服務(wù) ID 和用于訪問阿里云 AI 搜索平臺的 api key。在 Elasticsearch 的示例中，使用“ops-text-embedding-001”作為 service id 創(chuàng)建一個文本向量端點。

PUT _inference/text_embedding/ali_ai_embeddings

{

    "service": "alibabacloud-ai-search",

    "service_settings": {

        "api_key": "<api_key>",

        "service_id": "ops-text-embedding-001",

        "host": "xxxxx.platform-cn-shanghai.opensearch.aliyuncs.com",

        "workspace": "default"

    }

}

您將收到來自 Elasticsearch 的響應(yīng)，其中包含已成功創(chuàng)建的端點：

{

  "inference_id": "ali_ai_embeddings",

  "task_type": "text_embedding",

  "service": "alibabacloud-ai-search",

  "service_settings": {

    "similarity": "dot_product",

    "dimensions": 1536,

    "service_id": "ops-text-embedding-001",

    "host": "xxxxx.platform-cn-shanghai.opensearch.aliyuncs.com",

    "workspace": "default",

    "rate_limit": {

      "requests_per_minute": 10000

    }

  },

  "task_settings": {}

}

請注意，模型創(chuàng)建不需要其他額外的設(shè)置。Elasticsearch 將自動連接阿里云 AI 搜索開放平臺來測試您的憑據(jù)和 service id，并為您填寫維度數(shù)和相似度度量。接下來，測試端點以確保一切設(shè)置正確。為此將調(diào)用執(zhí)行推理 API：

POST _inference/text_embedding/ali_ai_embeddings

{

  "input": "What is Elastic?"

}

API 調(diào)用將返回輸入文本生成的向量，如下所示：

{

    "text_embedding": [

        {

            "embedding": [

                0.048400473,

                0.051464397,

                … (additional values) …

                0.033325635,

                -0.008986305

            ]

        }

    ]

}

您現(xiàn)在已準備好開始探索。嘗試完這些示例后，請看一下 Elasticsearch 中針對語義搜索應(yīng)用場景的一些令人興奮的創(chuàng)新：

首先，需要我們深入研究示例！

1. 會話生成

阿里云提供了多種會話生成模型，service ID 列于其模型?API文檔?中。

步驟1：配置會話生成服務(wù)

設(shè)置用于會話生成的推理服務(wù)：

PUT _inference/completion/ali-chat

{

 "service": "alibabacloud-ai-search",

 "service_settings": {

     "host" : "xxxxx.platform-cn-shanghai.opensearch.aliyuncs.com",

     "api_key": "xxxxxxxxxxxxxxxxxx",

     "service_id": "ops-qwen-turbo",

     "workspace" : "default"

 }

}

返回

 "inference_id": "ali-chat",

 "task_type": "completion",

 "service": "alibabacloud-ai-search",

 "service_settings": {

   "service_id": "ops-qwen-turbo",

   "host": "xxxxx.platform-cn-shanghai.opensearch.aliyuncs.com",

   "workspace": "default",

   "rate_limit": {

     "requests_per_minute": 1000

   }

 },

 "task_settings": {}

}

步驟2：發(fā)出會話生成的請求

使用配置的端點，發(fā)送 POST 請求以生成會話：

POST _inference/completion/ali-chat

{

 "input":["Where is the capital of Henan?"]

}

返回

{

 "completion": [

   {

     "result": "The capital of Henan is Zhengzhou."

   }

 ]

}

獨一無二的，在阿里云的 Elastic 推理 API 集成中，聊天歷史記錄可以包含在輸入中，在此示例中，包含了之前返回的內(nèi)容并添加了：“那里有什么有趣的事情嗎？”

POST _inference/completion/ali-chat

{

 "input":["Where is the capital of Henan?", "The capital of Henan is Zhengzhou.", "What fun things are there?" ]

}

響應(yīng)明確包含了歷史記錄

{

 "completion": [

   {

     "result": "I'm sorry, I do not have enough information to provide a specific list of fun things to do in Zhengzhou, Henan. I can only tell you that Zhengzhou is the capital of Henan province. To find out about fun activities, attractions, or events in Zhengzhou, I would suggest researching local tourism websites, asking locals, or checking out travel guides for the area."

   }

 ]

}

在未來的更新中，Elastic 計劃允許用戶明確地包含聊天歷史記錄，以提高易用性。

2. 重排序

繼續(xù)下一個任務(wù)類型，重排序。重排序可以利用阿里云強大的模型對搜索結(jié)果進行重新排序，以提高相關(guān)性。如果您想了解有關(guān)此概念的更多信息，請查看 Elastic 上的此博客?Search Labs。

步驟1：配置重排序服務(wù)

配置重排序推理服務(wù)：

PUT _inference/rerank/ali-rank

{

 "service": "alibabacloud-ai-search",

 "service_settings": {

   "api_key": "xxxxxxxxxxxxxxxxxx",

   "service_id": "ops-bge-reranker-larger",

   "host" : "xxxxx.platform-cn-shanghai.opensearch.aliyuncs.com",

   "workspace" : "default"   

 }

}
{

 "inference_id": "ali-rank",

 "task_type": "rerank",

 "service": "alibabacloud-ai-search",

 "service_settings": {

   "service_id": "ops-bge-reranker-larger",

   "host": "xxxxx.platform-cn-shanghai.opensearch.aliyuncs.com",

   "workspace": "default",

   "rate_limit": {

     "requests_per_minute": 1000

   }

 },

 "task_settings": {}

}

步驟2：發(fā)出重排序請求

發(fā)送 POST 請求以重新排列您的搜索查詢結(jié)果：rerank 接口不需要很多配置（task_settings），它返回語義相關(guān)性分數(shù)，越相關(guān)的越靠前，并返回其對應(yīng)文本在輸入數(shù)組中的序號 。

POST _inference/rerank/ali-rank

{

 "query": "What is the capital of the USA?",

 "input": [

   "Carson City is the capital city of the American state of Nevada. At the 2010 United States Census, Carson City had a population of 55,274.",



   "Capital punishment (the death penalty) has existed in the United States since before the United States was a country. As of 2017, capital punishment is legal in 30 of the 50 states.",



   "The Commonwealth of the Northern Mariana Islands is a group of islands in the Pacific Ocean that are a political division controlled by the United States. Its capital is Saipan.",



   "Washington, D.C. (also known as simply Washington or D.C., and officially as the District of Columbia) is the capital of the United States. It is a federal district.",



   "Charlotte Amalie is the capital and largest city of the United States Virgin Islands. It has about 20,000 people. The city is on the island of Saint Thomas.",



   "North Dakota is a state in the United States. 672,591 people lived in North Dakota in the year 2010. The capital and seat of government is Bismarck."

 ]

}
{

 "rerank": [

   {

     "index": 3,

     "relevance_score": 0.9998832

   },

   {

     "index": 4,

     "relevance_score": 0.008847355

   },

   {

     "index": 5,

     "relevance_score": 0.0026626128

   },

   {

     "index": 0,

     "relevance_score": 0.00068250194

   },

   {

     "index": 2,

     "relevance_score": 0.00019716943

   },

   {

     "index": 1,

     "relevance_score": 0.00011591934

   }

 ]

}

3. 稀疏向量

阿里云特別為生成稀疏向量提供了一個模型 ，使用?ops-text-sparse-embedding-001?這個 service id。

步驟1：配置稀疏向量生成服務(wù)

PUT _inference/sparse_embedding/ali-sparse-embedding

{

 "service": "alibabacloud-ai-search",

 "service_settings": {

   "api_key": "xxxxxxxxxxxxxxxxxx",

   "service_id": "ops-text-sparse-embedding-001",

   "host" : "xxxxx.platform-cn-shanghai.opensearch.aliyuncs.com",

   "workspace" : "default"

 }

}
{

 "inference_id": "ali-sparse-embedding",

 "task_type": "sparse_embedding",

 "service": "alibabacloud-ai-search",

 "service_settings": {

   "service_id": "ops-text-sparse-embedding-001",

   "host": "xxxxx.platform-cn-shanghai.opensearch.aliyuncs.com",

   "workspace": "default",

   "rate_limit": {

     "requests_per_minute": 1000

   }

 },

 "task_settings": {}

}

步驟2：發(fā)出稀疏向量生成查詢

Sparse 的 task_settings 為：

POST _inference/sparse_embedding/ali-sparse-embedding

{

 "input": "Hello world",

 "task_settings": {

   "input_type": "search",

   "return_token": true

 }

}
{

 "sparse_embedding": [

   {

     "is_truncated": false,

     "embedding": {

       "hello": 0.27783203,

       "world": 0.28222656

     }

   }

 ]

}

設(shè)置 return_token == false 返回如下

{

 "sparse_embedding": [

   {

     "is_truncated": false,

     "embedding": {

       "8999": 0.28222656,

       "35378": 0.27783203

     }

   }

 ]

}

4. 文本向量

阿里云還為不同的任務(wù)類型提供多種文本向量模型 。

步驟1：配置文本向量服務(wù)

文本向量只有一個 task_setting：

PUT _inference/text_embedding/ali-embeddings

{

 "service": "alibabacloud-ai-search",

 "service_settings": {

   "api_key": "xxxxxxxxxxxxxxxxxx",

   "service_id": "ops-text-embedding-001",

   "host" : "xxxxx.platform-cn-shanghai.opensearch.aliyuncs.com",

   "workspace" : "default"

 }

}
{

 "inference_id": "ali-embeddings",

 "task_type": "text_embedding",

 "service": "alibabacloud-ai-search",

 "service_settings": {

   "service_id": "ops-text-embedding-001",

   "host": "xxxxx.platform-cn-shanghai.opensearch.aliyuncs.com",

   "workspace": "default",

   "rate_limit": {

     "requests_per_minute": 1000

   },

   "similarity": "dot_product",

   "dimensions": 1536

 },

 "task_settings": {}

}

步驟2：發(fā)出文本向量請求

發(fā)送 POST 請求以生成文本向量：

POST _inference/text_embedding/ali-embeddings

{

 "input": "Hello world"

}
{

 "text_embedding": [

   {

     "embedding": [

       -0.017036675,

       0.07038724,

       0.044685286,

       0.0064531807,

       0.013290042,

       0.011183944,

       -0.0020014185,

       -0.009508779,

03使用 Elastic 和阿里云進行 AI 搜索

無論您是使用 Elasticsearch 實現(xiàn)混合搜索、語義重排序，還是通過摘要增強 RAG 應(yīng)用場景，與阿里云 AI 服務(wù)的連接都為 Elasticsearch 開發(fā)人員打開了一個充滿可能性的新世界。再次感謝阿里云團隊的貢獻！

本文章轉(zhuǎn)載微信公眾號@阿里云大數(shù)據(jù)AI平臺

上一篇：

結(jié)合大語言模型與 Zabbix API 實現(xiàn) Zabbix 模板自動化翻譯

下一篇：

工具與測評 | 用Cursor構(gòu)建基于AI的搜索引擎實戰(zhàn)教學(xué)
#你可能也喜歡這些API文章!

我們有何不同？

API服務(wù)商零注冊

多API并行試用

數(shù)據(jù)驅(qū)動選型，提升決策效率

查看全部API→
??

熱門場景實測，選對API

#AI文本生成大模型API

對比大模型API的內(nèi)容創(chuàng)意新穎性、情感共鳴力、商業(yè)轉(zhuǎn)化潛力

25個渠道
一鍵對比試用API 限時免費

#AI深度推理大模型API

對比大模型API的邏輯推理準確性、分析深度、可視化建議合理性

10個渠道
一鍵對比試用API 限時免費