@n8n/n8n-nodes-langchain 1.85.3 → 1.87.0

package/dist/nodes/embeddings/EmbeddingsGoogleVertex/EmbeddingsGoogleVertex.node.js

@@ -0,0 +1,166 @@
+"use strict";
+var __defProp = Object.defineProperty;
+var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
+var __getOwnPropNames = Object.getOwnPropertyNames;
+var __hasOwnProp = Object.prototype.hasOwnProperty;
+var __export = (target, all) => {
+  for (var name in all)
+    __defProp(target, name, { get: all[name], enumerable: true });
+};
+var __copyProps = (to, from, except, desc) => {
+  if (from && typeof from === "object" || typeof from === "function") {
+    for (let key of __getOwnPropNames(from))
+      if (!__hasOwnProp.call(to, key) && key !== except)
+        __defProp(to, key, { get: () => from[key], enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable });
+  }
+  return to;
+};
+var __toCommonJS = (mod) => __copyProps(__defProp({}, "__esModule", { value: true }), mod);
+var EmbeddingsGoogleVertex_node_exports = {};
+__export(EmbeddingsGoogleVertex_node_exports, {
+  EmbeddingsGoogleVertex: () => EmbeddingsGoogleVertex
+});
+module.exports = __toCommonJS(EmbeddingsGoogleVertex_node_exports);
+var import_resource_manager = require("@google-cloud/resource-manager");
+var import_google_vertexai = require("@langchain/google-vertexai");
+var import_utilities = require("n8n-nodes-base/dist/utils/utilities");
+var import_n8n_workflow = require("n8n-workflow");
+var import_logWrapper = require("../../../utils/logWrapper");
+var import_sharedFields = require("../../../utils/sharedFields");
+class EmbeddingsGoogleVertex {
+  constructor() {
+    this.methods = {
+      listSearch: {
+        async gcpProjectsList() {
+          const results = [];
+          const credentials = await this.getCredentials("googleApi");
+          const privateKey = (0, import_utilities.formatPrivateKey)(credentials.privateKey);
+          const email = credentials.email.trim();
+          const client = new import_resource_manager.ProjectsClient({
+            credentials: {
+              client_email: email,
+              private_key: privateKey
+            }
+          });
+          const [projects] = await client.searchProjects();
+          for (const project of projects) {
+            if (project.projectId) {
+              results.push({
+                name: project.displayName ?? project.projectId,
+                value: project.projectId
+              });
+            }
+          }
+          return { results };
+        }
+      }
+    };
+    this.description = {
+      displayName: "Embeddings Google Vertex",
+      name: "embeddingsGoogleVertex",
+      icon: "file:google.svg",
+      group: ["transform"],
+      version: 1,
+      description: "Use Google Vertex Embeddings",
+      defaults: {
+        name: "Embeddings Google Vertex"
+      },
+      requestDefaults: {
+        ignoreHttpStatusErrors: true,
+        baseURL: "={{ $credentials.host }}"
+      },
+      credentials: [
+        {
+          name: "googleApi",
+          required: true
+        }
+      ],
+      codex: {
+        categories: ["AI"],
+        subcategories: {
+          AI: ["Embeddings"]
+        },
+        resources: {
+          primaryDocumentation: [
+            {
+              url: "https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.embeddingsgooglevertex/"
+            }
+          ]
+        }
+      },
+      // eslint-disable-next-line n8n-nodes-base/node-class-description-inputs-wrong-regular-node
+      inputs: [],
+      // eslint-disable-next-line n8n-nodes-base/node-class-description-outputs-wrong
+      outputs: [import_n8n_workflow.NodeConnectionTypes.AiEmbedding],
+      outputNames: ["Embeddings"],
+      properties: [
+        (0, import_sharedFields.getConnectionHintNoticeField)([import_n8n_workflow.NodeConnectionTypes.AiVectorStore]),
+        {
+          displayName: 'Each model is using different dimensional density for embeddings. Please make sure to use the same dimensionality for your vector store. The default model is using 768-dimensional embeddings. You can find available models <a href="https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/text-embeddings-api">here</a>.',
+          name: "notice",
+          type: "notice",
+          default: ""
+        },
+        {
+          displayName: "Project ID",
+          name: "projectId",
+          type: "resourceLocator",
+          default: { mode: "list", value: "" },
+          required: true,
+          description: "Select or enter your Google Cloud project ID",
+          modes: [
+            {
+              displayName: "From List",
+              name: "list",
+              type: "list",
+              typeOptions: {
+                searchListMethod: "gcpProjectsList"
+              }
+            },
+            {
+              displayName: "ID",
+              name: "id",
+              type: "string"
+            }
+          ]
+        },
+        {
+          displayName: "Model Name",
+          name: "modelName",
+          type: "string",
+          description: 'The model which will generate the embeddings. <a href="https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/text-embeddings-api">Learn more</a>.',
+          default: "text-embedding-005"
+        }
+      ]
+    };
+  }
+  async supplyData(itemIndex) {
+    const credentials = await this.getCredentials("googleApi");
+    const privateKey = (0, import_utilities.formatPrivateKey)(credentials.privateKey);
+    const email = credentials.email.trim();
+    const region = credentials.region;
+    const modelName = this.getNodeParameter("modelName", itemIndex);
+    const projectId = this.getNodeParameter("projectId", itemIndex, "", {
+      extractValue: true
+    });
+    const embeddings = new import_google_vertexai.VertexAIEmbeddings({
+      authOptions: {
+        projectId,
+        credentials: {
+          client_email: email,
+          private_key: privateKey
+        }
+      },
+      location: region,
+      model: modelName
+    });
+    return {
+      response: (0, import_logWrapper.logWrapper)(embeddings, this)
+    };
+  }
+}
+// Annotate the CommonJS export names for ESM import in node:
+0 && (module.exports = {
+  EmbeddingsGoogleVertex
+});
+//# sourceMappingURL=EmbeddingsGoogleVertex.node.js.map

package/dist/nodes/embeddings/EmbeddingsGoogleVertex/EmbeddingsGoogleVertex.node.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../../../../nodes/embeddings/EmbeddingsGoogleVertex/EmbeddingsGoogleVertex.node.ts"],"sourcesContent":["/* eslint-disable n8n-nodes-base/node-dirname-against-convention */\nimport { ProjectsClient } from '@google-cloud/resource-manager';\nimport { VertexAIEmbeddings } from '@langchain/google-vertexai';\nimport { formatPrivateKey } from 'n8n-nodes-base/dist/utils/utilities';\nimport { NodeConnectionTypes } from 'n8n-workflow';\nimport type {\n\tILoadOptionsFunctions,\n\tINodeType,\n\tINodeTypeDescription,\n\tISupplyDataFunctions,\n\tSupplyData,\n} from 'n8n-workflow';\n\nimport { logWrapper } from '@utils/logWrapper';\nimport { getConnectionHintNoticeField } from '@utils/sharedFields';\n\nexport class EmbeddingsGoogleVertex implements INodeType {\n\tmethods = {\n\t\tlistSearch: {\n\t\t\tasync gcpProjectsList(this: ILoadOptionsFunctions) {\n\t\t\t\tconst results: Array<{ name: string; value: string }> = [];\n\n\t\t\t\tconst credentials = await this.getCredentials('googleApi');\n\t\t\t\tconst privateKey = formatPrivateKey(credentials.privateKey as string);\n\t\t\t\tconst email = (credentials.email as string).trim();\n\n\t\t\t\tconst client = new ProjectsClient({\n\t\t\t\t\tcredentials: {\n\t\t\t\t\t\tclient_email: email,\n\t\t\t\t\t\tprivate_key: privateKey,\n\t\t\t\t\t},\n\t\t\t\t});\n\n\t\t\t\tconst [projects] = await client.searchProjects();\n\n\t\t\t\tfor (const project of projects) {\n\t\t\t\t\tif (project.projectId) {\n\t\t\t\t\t\tresults.push({\n\t\t\t\t\t\t\tname: project.displayName ?? project.projectId,\n\t\t\t\t\t\t\tvalue: project.projectId,\n\t\t\t\t\t\t});\n\t\t\t\t\t}\n\t\t\t\t}\n\n\t\t\t\treturn { results };\n\t\t\t},\n\t\t},\n\t};\n\n\tdescription: INodeTypeDescription = {\n\t\tdisplayName: 'Embeddings Google Vertex',\n\t\tname: 'embeddingsGoogleVertex',\n\t\ticon: 'file:google.svg',\n\t\tgroup: ['transform'],\n\t\tversion: 1,\n\t\tdescription: 'Use Google Vertex Embeddings',\n\t\tdefaults: {\n\t\t\tname: 'Embeddings Google Vertex',\n\t\t},\n\t\trequestDefaults: {\n\t\t\tignoreHttpStatusErrors: true,\n\t\t\tbaseURL: '={{ $credentials.host }}',\n\t\t},\n\t\tcredentials: [\n\t\t\t{\n\t\t\t\tname: 'googleApi',\n\t\t\t\trequired: true,\n\t\t\t},\n\t\t],\n\t\tcodex: {\n\t\t\tcategories: ['AI'],\n\t\t\tsubcategories: {\n\t\t\t\tAI: ['Embeddings'],\n\t\t\t},\n\t\t\tresources: {\n\t\t\t\tprimaryDocumentation: [\n\t\t\t\t\t{\n\t\t\t\t\t\turl: 'https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.embeddingsgooglevertex/',\n\t\t\t\t\t},\n\t\t\t\t],\n\t\t\t},\n\t\t},\n\t\t// eslint-disable-next-line n8n-nodes-base/node-class-description-inputs-wrong-regular-node\n\t\tinputs: [],\n\t\t// eslint-disable-next-line n8n-nodes-base/node-class-description-outputs-wrong\n\t\toutputs: [NodeConnectionTypes.AiEmbedding],\n\t\toutputNames: ['Embeddings'],\n\n\t\tproperties: [\n\t\t\tgetConnectionHintNoticeField([NodeConnectionTypes.AiVectorStore]),\n\t\t\t{\n\t\t\t\tdisplayName:\n\t\t\t\t\t'Each model is using different dimensional density for embeddings. Please make sure to use the same dimensionality for your vector store. The default model is using 768-dimensional embeddings. You can find available models <a href=\"https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/text-embeddings-api\">here</a>.',\n\t\t\t\tname: 'notice',\n\t\t\t\ttype: 'notice',\n\t\t\t\tdefault: '',\n\t\t\t},\n\t\t\t{\n\t\t\t\tdisplayName: 'Project ID',\n\t\t\t\tname: 'projectId',\n\t\t\t\ttype: 'resourceLocator',\n\t\t\t\tdefault: { mode: 'list', value: '' },\n\t\t\t\trequired: true,\n\t\t\t\tdescription: 'Select or enter your Google Cloud project ID',\n\t\t\t\tmodes: [\n\t\t\t\t\t{\n\t\t\t\t\t\tdisplayName: 'From List',\n\t\t\t\t\t\tname: 'list',\n\t\t\t\t\t\ttype: 'list',\n\t\t\t\t\t\ttypeOptions: {\n\t\t\t\t\t\t\tsearchListMethod: 'gcpProjectsList',\n\t\t\t\t\t\t},\n\t\t\t\t\t},\n\t\t\t\t\t{\n\t\t\t\t\t\tdisplayName: 'ID',\n\t\t\t\t\t\tname: 'id',\n\t\t\t\t\t\ttype: 'string',\n\t\t\t\t\t},\n\t\t\t\t],\n\t\t\t},\n\t\t\t{\n\t\t\t\tdisplayName: 'Model Name',\n\t\t\t\tname: 'modelName',\n\t\t\t\ttype: 'string',\n\t\t\t\tdescription:\n\t\t\t\t\t'The model which will generate the embeddings. <a href=\"https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/text-embeddings-api\">Learn more</a>.',\n\t\t\t\tdefault: 'text-embedding-005',\n\t\t\t},\n\t\t],\n\t};\n\n\tasync supplyData(this: ISupplyDataFunctions, itemIndex: number): Promise<SupplyData> {\n\t\tconst credentials = await this.getCredentials('googleApi');\n\t\tconst privateKey = formatPrivateKey(credentials.privateKey as string);\n\t\tconst email = (credentials.email as string).trim();\n\t\tconst region = credentials.region as string;\n\n\t\tconst modelName = this.getNodeParameter('modelName', itemIndex) as string;\n\n\t\tconst projectId = this.getNodeParameter('projectId', itemIndex, '', {\n\t\t\textractValue: true,\n\t\t}) as string;\n\n\t\tconst embeddings = new VertexAIEmbeddings({\n\t\t\tauthOptions: {\n\t\t\t\tprojectId,\n\t\t\t\tcredentials: {\n\t\t\t\t\tclient_email: email,\n\t\t\t\t\tprivate_key: privateKey,\n\t\t\t\t},\n\t\t\t},\n\t\t\tlocation: region,\n\t\t\tmodel: modelName,\n\t\t});\n\n\t\treturn {\n\t\t\tresponse: logWrapper(embeddings, this),\n\t\t};\n\t}\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;AAAA;AAAA;AAAA;AAAA;AAAA;AACA,8BAA+B;AAC/B,6BAAmC;AACnC,uBAAiC;AACjC,0BAAoC;AASpC,wBAA2B;AAC3B,0BAA6C;AAEtC,MAAM,uBAA4C;AAAA,EAAlD;AACN,mBAAU;AAAA,MACT,YAAY;AAAA,QACX,MAAM,kBAA6C;AAClD,gBAAM,UAAkD,CAAC;AAEzD,gBAAM,cAAc,MAAM,KAAK,eAAe,WAAW;AACzD,gBAAM,iBAAa,mCAAiB,YAAY,UAAoB;AACpE,gBAAM,QAAS,YAAY,MAAiB,KAAK;AAEjD,gBAAM,SAAS,IAAI,uCAAe;AAAA,YACjC,aAAa;AAAA,cACZ,cAAc;AAAA,cACd,aAAa;AAAA,YACd;AAAA,UACD,CAAC;AAED,gBAAM,CAAC,QAAQ,IAAI,MAAM,OAAO,eAAe;AAE/C,qBAAW,WAAW,UAAU;AAC/B,gBAAI,QAAQ,WAAW;AACtB,sBAAQ,KAAK;AAAA,gBACZ,MAAM,QAAQ,eAAe,QAAQ;AAAA,gBACrC,OAAO,QAAQ;AAAA,cAChB,CAAC;AAAA,YACF;AAAA,UACD;AAEA,iBAAO,EAAE,QAAQ;AAAA,QAClB;AAAA,MACD;AAAA,IACD;AAEA,uBAAoC;AAAA,MACnC,aAAa;AAAA,MACb,MAAM;AAAA,MACN,MAAM;AAAA,MACN,OAAO,CAAC,WAAW;AAAA,MACnB,SAAS;AAAA,MACT,aAAa;AAAA,MACb,UAAU;AAAA,QACT,MAAM;AAAA,MACP;AAAA,MACA,iBAAiB;AAAA,QAChB,wBAAwB;AAAA,QACxB,SAAS;AAAA,MACV;AAAA,MACA,aAAa;AAAA,QACZ;AAAA,UACC,MAAM;AAAA,UACN,UAAU;AAAA,QACX;AAAA,MACD;AAAA,MACA,OAAO;AAAA,QACN,YAAY,CAAC,IAAI;AAAA,QACjB,eAAe;AAAA,UACd,IAAI,CAAC,YAAY;AAAA,QAClB;AAAA,QACA,WAAW;AAAA,UACV,sBAAsB;AAAA,YACrB;AAAA,cACC,KAAK;AAAA,YACN;AAAA,UACD;AAAA,QACD;AAAA,MACD;AAAA;AAAA,MAEA,QAAQ,CAAC;AAAA;AAAA,MAET,SAAS,CAAC,wCAAoB,WAAW;AAAA,MACzC,aAAa,CAAC,YAAY;AAAA,MAE1B,YAAY;AAAA,YACX,kDAA6B,CAAC,wCAAoB,aAAa,CAAC;AAAA,QAChE;AAAA,UACC,aACC;AAAA,UACD,MAAM;AAAA,UACN,MAAM;AAAA,UACN,SAAS;AAAA,QACV;AAAA,QACA;AAAA,UACC,aAAa;AAAA,UACb,MAAM;AAAA,UACN,MAAM;AAAA,UACN,SAAS,EAAE,MAAM,QAAQ,OAAO,GAAG;AAAA,UACnC,UAAU;AAAA,UACV,aAAa;AAAA,UACb,OAAO;AAAA,YACN;AAAA,cACC,aAAa;AAAA,cACb,MAAM;AAAA,cACN,MAAM;AAAA,cACN,aAAa;AAAA,gBACZ,kBAAkB;AAAA,cACnB;AAAA,YACD;AAAA,YACA;AAAA,cACC,aAAa;AAAA,cACb,MAAM;AAAA,cACN,MAAM;AAAA,YACP;AAAA,UACD;AAAA,QACD;AAAA,QACA;AAAA,UACC,aAAa;AAAA,UACb,MAAM;AAAA,UACN,MAAM;AAAA,UACN,aACC;AAAA,UACD,SAAS;AAAA,QACV;AAAA,MACD;AAAA,IACD;AAAA;AAAA,EAEA,MAAM,WAAuC,WAAwC;AACpF,UAAM,cAAc,MAAM,KAAK,eAAe,WAAW;AACzD,UAAM,iBAAa,mCAAiB,YAAY,UAAoB;AACpE,UAAM,QAAS,YAAY,MAAiB,KAAK;AACjD,UAAM,SAAS,YAAY;AAE3B,UAAM,YAAY,KAAK,iBAAiB,aAAa,SAAS;AAE9D,UAAM,YAAY,KAAK,iBAAiB,aAAa,WAAW,IAAI;AAAA,MACnE,cAAc;AAAA,IACf,CAAC;AAED,UAAM,aAAa,IAAI,0CAAmB;AAAA,MACzC,aAAa;AAAA,QACZ;AAAA,QACA,aAAa;AAAA,UACZ,cAAc;AAAA,UACd,aAAa;AAAA,QACd;AAAA,MACD;AAAA,MACA,UAAU;AAAA,MACV,OAAO;AAAA,IACR,CAAC;AAED,WAAO;AAAA,MACN,cAAU,8BAAW,YAAY,IAAI;AAAA,IACtC;AAAA,EACD;AACD;","names":[]}

package/dist/nodes/embeddings/EmbeddingsGoogleVertex/google.svg

@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" viewBox="0 0 48 48"><defs><path id="a" d="M44.5 20H24v8.5h11.8C34.7 33.9 30.1 37 24 37c-7.2 0-13-5.8-13-13s5.8-13 13-13c3.1 0 5.9 1.1 8.1 2.9l6.4-6.4C34.6 4.1 29.6 2 24 2 11.8 2 2 11.8 2 24s9.8 22 22 22c11 0 21-8 21-22 0-1.3-.2-2.7-.5-4"/></defs><clipPath id="b"><use xlink:href="#a" overflow="visible"/></clipPath><path fill="#FBBC05" d="M0 37V11l17 13z" clip-path="url(#b)"/><path fill="#EA4335" d="m0 11 17 13 7-6.1L48 14V0H0z" clip-path="url(#b)"/><path fill="#34A853" d="m0 37 30-23 7.9 1L48 0v48H0z" clip-path="url(#b)"/><path fill="#4285F4" d="M48 48 17 24l-4-3 35-10z" clip-path="url(#b)"/></svg>

package/dist/nodes/embeddings/EmbeddingsHuggingFaceInference/EmbeddingsHuggingFaceInference.node.js

@@ -1,93 +1,122 @@
 "use strict";
-Object.defineProperty(exports, "__esModule", { value: true });
-exports.EmbeddingsHuggingFaceInference = void 0;
-const hf_1 = require("@langchain/community/embeddings/hf");
-const n8n_workflow_1 = require("n8n-workflow");
-const logWrapper_1 = require("../../../utils/logWrapper");
-const sharedFields_1 = require("../../../utils/sharedFields");
+var __defProp = Object.defineProperty;
+var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
+var __getOwnPropNames = Object.getOwnPropertyNames;
+var __hasOwnProp = Object.prototype.hasOwnProperty;
+var __export = (target, all) => {
+  for (var name in all)
+    __defProp(target, name, { get: all[name], enumerable: true });
+};
+var __copyProps = (to, from, except, desc) => {
+  if (from && typeof from === "object" || typeof from === "function") {
+    for (let key of __getOwnPropNames(from))
+      if (!__hasOwnProp.call(to, key) && key !== except)
+        __defProp(to, key, { get: () => from[key], enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable });
+  }
+  return to;
+};
+var __toCommonJS = (mod) => __copyProps(__defProp({}, "__esModule", { value: true }), mod);
+var EmbeddingsHuggingFaceInference_node_exports = {};
+__export(EmbeddingsHuggingFaceInference_node_exports, {
+  EmbeddingsHuggingFaceInference: () => EmbeddingsHuggingFaceInference
+});
+module.exports = __toCommonJS(EmbeddingsHuggingFaceInference_node_exports);
+var import_hf = require("@langchain/community/embeddings/hf");
+var import_n8n_workflow = require("n8n-workflow");
+var import_logWrapper = require("../../../utils/logWrapper");
+var import_sharedFields = require("../../../utils/sharedFields");
 class EmbeddingsHuggingFaceInference {
-    constructor() {
-        this.description = {
-            displayName: 'Embeddings Hugging Face Inference',
-            name: 'embeddingsHuggingFaceInference',
-            icon: 'file:huggingface.svg',
-            group: ['transform'],
-            version: 1,
-            description: 'Use HuggingFace Inference Embeddings',
-            defaults: {
-                name: 'Embeddings HuggingFace Inference',
-            },
-            credentials: [
-                {
-                    name: 'huggingFaceApi',
-                    required: true,
-                },
-            ],
-            codex: {
-                categories: ['AI'],
-                subcategories: {
-                    AI: ['Embeddings'],
-                },
-                resources: {
-                    primaryDocumentation: [
-                        {
-                            url: 'https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.embeddingshuggingfaceinference/',
-                        },
-                    ],
-                },
-            },
-            inputs: [],
-            outputs: [n8n_workflow_1.NodeConnectionTypes.AiEmbedding],
-            outputNames: ['Embeddings'],
-            properties: [
-                (0, sharedFields_1.getConnectionHintNoticeField)([n8n_workflow_1.NodeConnectionTypes.AiVectorStore]),
-                {
-                    displayName: 'Each model is using different dimensional density for embeddings. Please make sure to use the same dimensionality for your vector store. The default model is using 768-dimensional embeddings.',
-                    name: 'notice',
-                    type: 'notice',
-                    default: '',
-                },
-                {
-                    displayName: 'Model Name',
-                    name: 'modelName',
-                    type: 'string',
-                    default: 'sentence-transformers/distilbert-base-nli-mean-tokens',
-                    description: 'The model name to use from HuggingFace library',
-                },
-                {
-                    displayName: 'Options',
-                    name: 'options',
-                    placeholder: 'Add Option',
-                    description: 'Additional options to add',
-                    type: 'collection',
-                    default: {},
-                    options: [
-                        {
-                            displayName: 'Custom Inference Endpoint',
-                            name: 'endpointUrl',
-                            default: '',
-                            description: 'Custom endpoint URL',
-                            type: 'string',
-                        },
-                    ],
-                },
-            ],
-        };
-    }
-    async supplyData(itemIndex) {
-        this.logger.debug('Supply data for embeddings HF Inference');
-        const model = this.getNodeParameter('modelName', itemIndex, 'sentence-transformers/distilbert-base-nli-mean-tokens');
-        const credentials = await this.getCredentials('huggingFaceApi');
-        const options = this.getNodeParameter('options', itemIndex, {});
-        const embeddings = new hf_1.HuggingFaceInferenceEmbeddings({
-            apiKey: credentials.apiKey,
-            model,
-            ...options,
-        });
-        return {
-            response: (0, logWrapper_1.logWrapper)(embeddings, this),
-        };
-    }
+  constructor() {
+    this.description = {
+      displayName: "Embeddings Hugging Face Inference",
+      name: "embeddingsHuggingFaceInference",
+      icon: "file:huggingface.svg",
+      group: ["transform"],
+      version: 1,
+      description: "Use HuggingFace Inference Embeddings",
+      defaults: {
+        name: "Embeddings HuggingFace Inference"
+      },
+      credentials: [
+        {
+          name: "huggingFaceApi",
+          required: true
+        }
+      ],
+      codex: {
+        categories: ["AI"],
+        subcategories: {
+          AI: ["Embeddings"]
+        },
+        resources: {
+          primaryDocumentation: [
+            {
+              url: "https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.embeddingshuggingfaceinference/"
+            }
+          ]
+        }
+      },
+      // eslint-disable-next-line n8n-nodes-base/node-class-description-inputs-wrong-regular-node
+      inputs: [],
+      // eslint-disable-next-line n8n-nodes-base/node-class-description-outputs-wrong
+      outputs: [import_n8n_workflow.NodeConnectionTypes.AiEmbedding],
+      outputNames: ["Embeddings"],
+      properties: [
+        (0, import_sharedFields.getConnectionHintNoticeField)([import_n8n_workflow.NodeConnectionTypes.AiVectorStore]),
+        {
+          displayName: "Each model is using different dimensional density for embeddings. Please make sure to use the same dimensionality for your vector store. The default model is using 768-dimensional embeddings.",
+          name: "notice",
+          type: "notice",
+          default: ""
+        },
+        {
+          displayName: "Model Name",
+          name: "modelName",
+          type: "string",
+          default: "sentence-transformers/distilbert-base-nli-mean-tokens",
+          description: "The model name to use from HuggingFace library"
+        },
+        {
+          displayName: "Options",
+          name: "options",
+          placeholder: "Add Option",
+          description: "Additional options to add",
+          type: "collection",
+          default: {},
+          options: [
+            {
+              displayName: "Custom Inference Endpoint",
+              name: "endpointUrl",
+              default: "",
+              description: "Custom endpoint URL",
+              type: "string"
+            }
+          ]
+        }
+      ]
+    };
+  }
+  async supplyData(itemIndex) {
+    this.logger.debug("Supply data for embeddings HF Inference");
+    const model = this.getNodeParameter(
+      "modelName",
+      itemIndex,
+      "sentence-transformers/distilbert-base-nli-mean-tokens"
+    );
+    const credentials = await this.getCredentials("huggingFaceApi");
+    const options = this.getNodeParameter("options", itemIndex, {});
+    const embeddings = new import_hf.HuggingFaceInferenceEmbeddings({
+      apiKey: credentials.apiKey,
+      model,
+      ...options
+    });
+    return {
+      response: (0, import_logWrapper.logWrapper)(embeddings, this)
+    };
+  }
 }
-exports.EmbeddingsHuggingFaceInference = EmbeddingsHuggingFaceInference;
+// Annotate the CommonJS export names for ESM import in node:
+0 && (module.exports = {
+  EmbeddingsHuggingFaceInference
+});
 //# sourceMappingURL=EmbeddingsHuggingFaceInference.node.js.map

package/dist/nodes/embeddings/EmbeddingsHuggingFaceInference/EmbeddingsHuggingFaceInference.node.js.map

@@ -1 +1 @@
-{"version":3,"file":"EmbeddingsHuggingFaceInference.node.js","sourceRoot":"","sources":["../../../../nodes/embeddings/EmbeddingsHuggingFaceInference/EmbeddingsHuggingFaceInference.node.ts"],"names":[],"mappings":";;;AACA,2DAAoF;AACpF,+CAMsB;AAEtB,kDAA+C;AAC/C,sDAAmE;AAEnE,MAAa,8BAA8B;IAA3C;QACC,gBAAW,GAAyB;YACnC,WAAW,EAAE,mCAAmC;YAChD,IAAI,EAAE,gCAAgC;YACtC,IAAI,EAAE,sBAAsB;YAC5B,KAAK,EAAE,CAAC,WAAW,CAAC;YACpB,OAAO,EAAE,CAAC;YACV,WAAW,EAAE,sCAAsC;YACnD,QAAQ,EAAE;gBACT,IAAI,EAAE,kCAAkC;aACxC;YACD,WAAW,EAAE;gBACZ;oBACC,IAAI,EAAE,gBAAgB;oBACtB,QAAQ,EAAE,IAAI;iBACd;aACD;YACD,KAAK,EAAE;gBACN,UAAU,EAAE,CAAC,IAAI,CAAC;gBAClB,aAAa,EAAE;oBACd,EAAE,EAAE,CAAC,YAAY,CAAC;iBAClB;gBACD,SAAS,EAAE;oBACV,oBAAoB,EAAE;wBACrB;4BACC,GAAG,EAAE,sHAAsH;yBAC3H;qBACD;iBACD;aACD;YAED,MAAM,EAAE,EAAE;YAEV,OAAO,EAAE,CAAC,kCAAmB,CAAC,WAAW,CAAC;YAC1C,WAAW,EAAE,CAAC,YAAY,CAAC;YAC3B,UAAU,EAAE;gBACX,IAAA,2CAA4B,EAAC,CAAC,kCAAmB,CAAC,aAAa,CAAC,CAAC;gBACjE;oBACC,WAAW,EACV,iMAAiM;oBAClM,IAAI,EAAE,QAAQ;oBACd,IAAI,EAAE,QAAQ;oBACd,OAAO,EAAE,EAAE;iBACX;gBACD;oBACC,WAAW,EAAE,YAAY;oBACzB,IAAI,EAAE,WAAW;oBACjB,IAAI,EAAE,QAAQ;oBACd,OAAO,EAAE,uDAAuD;oBAChE,WAAW,EAAE,gDAAgD;iBAC7D;gBACD;oBACC,WAAW,EAAE,SAAS;oBACtB,IAAI,EAAE,SAAS;oBACf,WAAW,EAAE,YAAY;oBACzB,WAAW,EAAE,2BAA2B;oBACxC,IAAI,EAAE,YAAY;oBAClB,OAAO,EAAE,EAAE;oBACX,OAAO,EAAE;wBACR;4BACC,WAAW,EAAE,2BAA2B;4BACxC,IAAI,EAAE,aAAa;4BACnB,OAAO,EAAE,EAAE;4BACX,WAAW,EAAE,qBAAqB;4BAClC,IAAI,EAAE,QAAQ;yBACd;qBACD;iBACD;aACD;SACD,CAAC;IAsBH,CAAC;IApBA,KAAK,CAAC,UAAU,CAA6B,SAAiB;QAC7D,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,yCAAyC,CAAC,CAAC;QAC7D,MAAM,KAAK,GAAG,IAAI,CAAC,gBAAgB,CAClC,WAAW,EACX,SAAS,EACT,uDAAuD,CAC7C,CAAC;QACZ,MAAM,WAAW,GAAG,MAAM,IAAI,CAAC,cAAc,CAAC,gBAAgB,CAAC,CAAC;QAChE,MAAM,OAAO,GAAG,IAAI,CAAC,gBAAgB,CAAC,SAAS,EAAE,SAAS,EAAE,EAAE,CAAW,CAAC;QAE1E,MAAM,UAAU,GAAG,IAAI,mCAA8B,CAAC;YACrD,MAAM,EAAE,WAAW,CAAC,MAAgB;YACpC,KAAK;YACL,GAAG,OAAO;SACV,CAAC,CAAC;QAEH,OAAO;YACN,QAAQ,EAAE,IAAA,uBAAU,EAAC,UAAU,EAAE,IAAI,CAAC;SACtC,CAAC;IACH,CAAC;CACD;AA3FD,wEA2FC"}
+{"version":3,"sources":["../../../../nodes/embeddings/EmbeddingsHuggingFaceInference/EmbeddingsHuggingFaceInference.node.ts"],"sourcesContent":["/* eslint-disable n8n-nodes-base/node-dirname-against-convention */\nimport { HuggingFaceInferenceEmbeddings } from '@langchain/community/embeddings/hf';\nimport {\n\tNodeConnectionTypes,\n\ttype INodeType,\n\ttype INodeTypeDescription,\n\ttype ISupplyDataFunctions,\n\ttype SupplyData,\n} from 'n8n-workflow';\n\nimport { logWrapper } from '@utils/logWrapper';\nimport { getConnectionHintNoticeField } from '@utils/sharedFields';\n\nexport class EmbeddingsHuggingFaceInference implements INodeType {\n\tdescription: INodeTypeDescription = {\n\t\tdisplayName: 'Embeddings Hugging Face Inference',\n\t\tname: 'embeddingsHuggingFaceInference',\n\t\ticon: 'file:huggingface.svg',\n\t\tgroup: ['transform'],\n\t\tversion: 1,\n\t\tdescription: 'Use HuggingFace Inference Embeddings',\n\t\tdefaults: {\n\t\t\tname: 'Embeddings HuggingFace Inference',\n\t\t},\n\t\tcredentials: [\n\t\t\t{\n\t\t\t\tname: 'huggingFaceApi',\n\t\t\t\trequired: true,\n\t\t\t},\n\t\t],\n\t\tcodex: {\n\t\t\tcategories: ['AI'],\n\t\t\tsubcategories: {\n\t\t\t\tAI: ['Embeddings'],\n\t\t\t},\n\t\t\tresources: {\n\t\t\t\tprimaryDocumentation: [\n\t\t\t\t\t{\n\t\t\t\t\t\turl: 'https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.embeddingshuggingfaceinference/',\n\t\t\t\t\t},\n\t\t\t\t],\n\t\t\t},\n\t\t},\n\t\t// eslint-disable-next-line n8n-nodes-base/node-class-description-inputs-wrong-regular-node\n\t\tinputs: [],\n\t\t// eslint-disable-next-line n8n-nodes-base/node-class-description-outputs-wrong\n\t\toutputs: [NodeConnectionTypes.AiEmbedding],\n\t\toutputNames: ['Embeddings'],\n\t\tproperties: [\n\t\t\tgetConnectionHintNoticeField([NodeConnectionTypes.AiVectorStore]),\n\t\t\t{\n\t\t\t\tdisplayName:\n\t\t\t\t\t'Each model is using different dimensional density for embeddings. Please make sure to use the same dimensionality for your vector store. The default model is using 768-dimensional embeddings.',\n\t\t\t\tname: 'notice',\n\t\t\t\ttype: 'notice',\n\t\t\t\tdefault: '',\n\t\t\t},\n\t\t\t{\n\t\t\t\tdisplayName: 'Model Name',\n\t\t\t\tname: 'modelName',\n\t\t\t\ttype: 'string',\n\t\t\t\tdefault: 'sentence-transformers/distilbert-base-nli-mean-tokens',\n\t\t\t\tdescription: 'The model name to use from HuggingFace library',\n\t\t\t},\n\t\t\t{\n\t\t\t\tdisplayName: 'Options',\n\t\t\t\tname: 'options',\n\t\t\t\tplaceholder: 'Add Option',\n\t\t\t\tdescription: 'Additional options to add',\n\t\t\t\ttype: 'collection',\n\t\t\t\tdefault: {},\n\t\t\t\toptions: [\n\t\t\t\t\t{\n\t\t\t\t\t\tdisplayName: 'Custom Inference Endpoint',\n\t\t\t\t\t\tname: 'endpointUrl',\n\t\t\t\t\t\tdefault: '',\n\t\t\t\t\t\tdescription: 'Custom endpoint URL',\n\t\t\t\t\t\ttype: 'string',\n\t\t\t\t\t},\n\t\t\t\t],\n\t\t\t},\n\t\t],\n\t};\n\n\tasync supplyData(this: ISupplyDataFunctions, itemIndex: number): Promise<SupplyData> {\n\t\tthis.logger.debug('Supply data for embeddings HF Inference');\n\t\tconst model = this.getNodeParameter(\n\t\t\t'modelName',\n\t\t\titemIndex,\n\t\t\t'sentence-transformers/distilbert-base-nli-mean-tokens',\n\t\t) as string;\n\t\tconst credentials = await this.getCredentials('huggingFaceApi');\n\t\tconst options = this.getNodeParameter('options', itemIndex, {}) as object;\n\n\t\tconst embeddings = new HuggingFaceInferenceEmbeddings({\n\t\t\tapiKey: credentials.apiKey as string,\n\t\t\tmodel,\n\t\t\t...options,\n\t\t});\n\n\t\treturn {\n\t\t\tresponse: logWrapper(embeddings, this),\n\t\t};\n\t}\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;AAAA;AAAA;AAAA;AAAA;AAAA;AACA,gBAA+C;AAC/C,0BAMO;AAEP,wBAA2B;AAC3B,0BAA6C;AAEtC,MAAM,+BAAoD;AAAA,EAA1D;AACN,uBAAoC;AAAA,MACnC,aAAa;AAAA,MACb,MAAM;AAAA,MACN,MAAM;AAAA,MACN,OAAO,CAAC,WAAW;AAAA,MACnB,SAAS;AAAA,MACT,aAAa;AAAA,MACb,UAAU;AAAA,QACT,MAAM;AAAA,MACP;AAAA,MACA,aAAa;AAAA,QACZ;AAAA,UACC,MAAM;AAAA,UACN,UAAU;AAAA,QACX;AAAA,MACD;AAAA,MACA,OAAO;AAAA,QACN,YAAY,CAAC,IAAI;AAAA,QACjB,eAAe;AAAA,UACd,IAAI,CAAC,YAAY;AAAA,QAClB;AAAA,QACA,WAAW;AAAA,UACV,sBAAsB;AAAA,YACrB;AAAA,cACC,KAAK;AAAA,YACN;AAAA,UACD;AAAA,QACD;AAAA,MACD;AAAA;AAAA,MAEA,QAAQ,CAAC;AAAA;AAAA,MAET,SAAS,CAAC,wCAAoB,WAAW;AAAA,MACzC,aAAa,CAAC,YAAY;AAAA,MAC1B,YAAY;AAAA,YACX,kDAA6B,CAAC,wCAAoB,aAAa,CAAC;AAAA,QAChE;AAAA,UACC,aACC;AAAA,UACD,MAAM;AAAA,UACN,MAAM;AAAA,UACN,SAAS;AAAA,QACV;AAAA,QACA;AAAA,UACC,aAAa;AAAA,UACb,MAAM;AAAA,UACN,MAAM;AAAA,UACN,SAAS;AAAA,UACT,aAAa;AAAA,QACd;AAAA,QACA;AAAA,UACC,aAAa;AAAA,UACb,MAAM;AAAA,UACN,aAAa;AAAA,UACb,aAAa;AAAA,UACb,MAAM;AAAA,UACN,SAAS,CAAC;AAAA,UACV,SAAS;AAAA,YACR;AAAA,cACC,aAAa;AAAA,cACb,MAAM;AAAA,cACN,SAAS;AAAA,cACT,aAAa;AAAA,cACb,MAAM;AAAA,YACP;AAAA,UACD;AAAA,QACD;AAAA,MACD;AAAA,IACD;AAAA;AAAA,EAEA,MAAM,WAAuC,WAAwC;AACpF,SAAK,OAAO,MAAM,yCAAyC;AAC3D,UAAM,QAAQ,KAAK;AAAA,MAClB;AAAA,MACA;AAAA,MACA;AAAA,IACD;AACA,UAAM,cAAc,MAAM,KAAK,eAAe,gBAAgB;AAC9D,UAAM,UAAU,KAAK,iBAAiB,WAAW,WAAW,CAAC,CAAC;AAE9D,UAAM,aAAa,IAAI,yCAA+B;AAAA,MACrD,QAAQ,YAAY;AAAA,MACpB;AAAA,MACA,GAAG;AAAA,IACJ,CAAC;AAED,WAAO;AAAA,MACN,cAAU,8BAAW,YAAY,IAAI;AAAA,IACtC;AAAA,EACD;AACD;","names":[]}