feat: optimize elasticsearch ai-search plugin and update related docs" (#2100)

plugins/wasm-go/extensions/ai-search/README.md

@@ -75,18 +75,22 @@ description: higress 支持通过集成搜索引擎（Google/Bing/Arxiv/Elastics
 
 ## Elasticsearch 特定配置
 
-| 名称 | 数据类型 | 填写要求 | 默认值 | 描述                    |
-|------|----------|----------|--------|-----------------------|
-| index | string | 必填 | - | 要搜索的Elasticsearch索引名称 |
-| contentField | string | 必填 | - | 要查询的内容字段名称            |
-| semanticTextField | string | 必填 | - | 要查询的 embedding 字段名称   | 
-| linkField | string | 必填 | - | 结果链接字段名称              |
-| titleField | string | 必填 | - | 结果标题字段名称              |
-| username | string | 选填 | - | Elasticsearch 用户名          |
-| password | string | 选填 | - | Elasticsearch 密码          |
+| 名称 | 数据类型 | 填写要求 | 默认值 | 描述                                 |
+|------|----------|------|--------|------------------------------------|
+| index | string | 必填   | - | 要搜索的 Elasticsearch 索引名称            |
+| contentField | string | 必填   | - | 要查询的内容字段名称                         |
+| semanticTextField | string | 必填   | - | 要查询的 embedding 字段名称                | 
+| linkField | string | 选填   | - | 结果链接字段名称，当配置 `needReference` 时需要填写 |
+| titleField | string | 选填   | - | 结果标题字段名称，当配置 `needReference` 时需要填写 |
+| username | string | 选填   | - | Elasticsearch 用户名                  |
+| password | string | 选填   | - | Elasticsearch 密码                   |
 
 混合搜索中使用的 [Reciprocal Rank Fusion (RRF)](https://www.elastic.co/guide/en/elasticsearch/reference/8.17/rrf.html) 查询要求 Elasticsearch 的版本在 8.8 及以上。
 
+目前文档向量化依赖于 Elasticsearch 的 Embedding 模型，该功能需要 Elasticsearch 企业版 License，或可使用 30 天的 Trial License。安装 Elasticsearch 内置 Embedding 模型的步骤可参考[该文档](https://www.elastic.co/docs/explore-analyze/machine-learning/nlp/ml-nlp-elser#alternative-download-deploy)；若需安装第三方 Embedding 模型，可参考[该文档](https://www.elastic.co/docs/explore-analyze/machine-learning/nlp/ml-nlp-text-emb-vector-search-example)。
+
+有关 ai-search 插件集成 Elasticsearch 的完整教程，请参考：[使用 LangChain + Higress + Elasticsearch 构建 RAG 应用](https://cr7258.github.io/blogs/original/2025/15-rag-higress-es-langchain)。
+
 ## Quark 特定配置
 
 | 名称 | 数据类型 | 填写要求 | 默认值 | 描述 |
@@ -204,13 +208,9 @@ searchFrom:
 searchFrom:
 - type: elasticsearch
   serviceName: "es-svc.static"
-  # 固定地址服务的端口默认是80
-  servicePort: 80
   index: "knowledge_base"
   contentField: "content"
   semanticTextField: "semantic_text"
-  linkField: "url" 
-  titleField: "title"
   # username: "elastic"
   # password: "password"
 ```

plugins/wasm-go/extensions/ai-search/README_EN.md

@@ -80,13 +80,17 @@ It is strongly recommended to enable this feature when using Arxiv or Elasticsea
 | index | string | Required    | - | Elasticsearch index name to search |
 | contentField | string | Required    | - | Content field name to query        |
 | semanticTextField | string | Required    | - | Embedding field name to query      |
-| linkField | string | Required    | - | Result link field name             |
-| titleField | string | Required    | - | Result title field name            |
+| linkField | string | Optional    | - | Result link field name, needed when `needReference` is configured |
+| titleField | string | Optional    | - | Result title field name, needed when `needReference` is configured          |
 | username | string | Optional          | - | Elasticsearch username             |
 | password | string | Optional    | - | Elasticsearch password             |
 
 The [Reciprocal Rank Fusion (RRF)](https://www.elastic.co/guide/en/elasticsearch/reference/8.17/rrf.html) query used in hybrid search requires Elasticsearch version 8.8 or higher.
 
+Currently, document vectorization relies on Elasticsearch's embedding model, which requires an Elasticsearch Enterprise license or a 30-day Trial license. To install the built-in embedding model in Elasticsearch, please refer to [this documentation](https://www.elastic.co/docs/explore-analyze/machine-learning/nlp/ml-nlp-elser#alternative-download-deploy). If you want to install a third-party embedding model, please refer to [this guide](https://www.elastic.co/docs/explore-analyze/machine-learning/nlp/ml-nlp-text-emb-vector-search-example).
+
+For a complete tutorial on integrating the ai-search plugin with Elasticsearch, please refer to: [Building a RAG Application with LangChain + Higress + Elasticsearch](https://cr7258.github.io/blogs/original/2025/15-rag-higress-es-langchain).
+
 ## Quark Specific Configuration
 
 | Name | Data Type | Requirement | Default Value | Description |
@@ -203,13 +207,9 @@ Note that excessive concurrency may lead to rate limiting, adjust according to a
 searchFrom:
 - type: elasticsearch
   serviceName: "es-svc.static"
-  # static ip service use 80 as default port
-  servicePort: 80
   index: "knowledge_base"
   contentField: "content"
   semanticTextField: "semantic_text"
-  linkField: "url" 
-  titleField: "title"
   # username: "elastic"
   # password: "password"
 ```

plugins/wasm-go/extensions/ai-search/engine/elasticsearch/elasticsearch.go

@@ -27,7 +27,7 @@ type ElasticsearchSearch struct {
 	password           string
 }
 
-func NewElasticsearchSearch(config *gjson.Result) (*ElasticsearchSearch, error) {
+func NewElasticsearchSearch(config *gjson.Result, needReference bool) (*ElasticsearchSearch, error) {
 	engine := &ElasticsearchSearch{}
 	serviceName := config.Get("serviceName").String()
 	if serviceName == "" {
@@ -35,7 +35,13 @@ func NewElasticsearchSearch(config *gjson.Result) (*ElasticsearchSearch, error)
 	}
 	servicePort := config.Get("servicePort").Int()
 	if servicePort == 0 {
-		return nil, errors.New("servicePort not found")
+		if strings.HasSuffix(serviceName, ".static") {
+			servicePort = 80
+		} else if strings.HasSuffix(serviceName, ".dns") {
+			servicePort = 443
+		} else {
+			return nil, errors.New("servicePort not found")
+		}
 	}
 	engine.client = wrapper.NewClusterClient(wrapper.FQDNCluster{
 		FQDN: serviceName,
@@ -54,14 +60,18 @@ func NewElasticsearchSearch(config *gjson.Result) (*ElasticsearchSearch, error)
 	if engine.semanticTextField == "" {
 		return nil, errors.New("semanticTextField not found")
 	}
-	engine.linkField = config.Get("linkField").String()
-	if engine.linkField == "" {
-		return nil, errors.New("linkField not found")
-	}
-	engine.titleField = config.Get("titleField").String()
-	if engine.titleField == "" {
-		return nil, errors.New("titleField not found")
+
+	if needReference {
+		engine.linkField = config.Get("linkField").String()
+		if engine.linkField == "" {
+			return nil, errors.New("linkField not found")
+		}
+		engine.titleField = config.Get("titleField").String()
+		if engine.titleField == "" {
+			return nil, errors.New("titleField not found")
+		}
 	}
+
 	engine.timeoutMillisecond = uint32(config.Get("timeoutMillisecond").Uint())
 	if engine.timeoutMillisecond == 0 {
 		engine.timeoutMillisecond = 5000
@@ -93,6 +103,9 @@ func (e ElasticsearchSearch) generateAuthorizationHeader() string {
 func (e ElasticsearchSearch) generateQueryBody(ctx engine.SearchContext) string {
 	queryText := strings.Join(ctx.Querys, " ")
 	return fmt.Sprintf(`{
+        "_source":{
+            "excludes": "%s"
+        },
 		"retriever": {
 			"rrf": {
 				"retrievers": [
@@ -118,7 +131,7 @@ func (e ElasticsearchSearch) generateQueryBody(ctx engine.SearchContext) string
 				]
 			}
 		}
-	}`, e.contentField, queryText, e.semanticTextField, queryText)
+	}`, e.semanticTextField, e.contentField, queryText, e.semanticTextField, queryText)
 }
 
 func (e ElasticsearchSearch) CallArgs(ctx engine.SearchContext) engine.CallArgs {
@@ -145,9 +158,7 @@ func (e ElasticsearchSearch) ParseResult(ctx engine.SearchContext, response []by
 			Link:    source.Get(e.linkField).String(),
 			Content: source.Get(e.contentField).String(),
 		}
-		if result.Valid() {
-			results = append(results, result)
-		}
+		results = append(results, result)
 	}
 	return results
 }

plugins/wasm-go/extensions/ai-search/main.go

@@ -185,7 +185,7 @@ func parseConfig(json gjson.Result, config *Config, log wrapper.Log) error {
 			arxivExists = true
 			onlyQuark = false
 		case "elasticsearch":
-			searchEngine, err := elasticsearch.NewElasticsearchSearch(&e)
+			searchEngine, err := elasticsearch.NewElasticsearchSearch(&e, config.needReference)
 			if err != nil {
 				return fmt.Errorf("elasticsearch search engine init failed:%s", err)
 			}