@sateeshreddy/n8n-nodes-nvidia-nim 1.0.3 → 1.0.6

package/README.md

@@ -4,9 +4,9 @@
 
 # n8n-nodes-nvidia-nim
 
-**Connect any free NVIDIA NIM language model to your n8n workflows — in one node.**
+**Connect NVIDIA NIM language models and embedding models to your n8n workflows — in one package.**
 
-[![npm version](https://img.shields.io/npm/v/n8n-nodes-nvidia-nim?color=76b900&label=npm&style=flat-square)](https://www.npmjs.com/package/n8n-nodes-nvidia-nim)
+[![npm version](https://img.shields.io/npm/v/@sateeshreddy/n8n-nodes-nvidia-nim?color=76b900&label=npm&style=flat-square)](https://www.npmjs.com/package/@sateeshreddy/n8n-nodes-nvidia-nim)
 [![n8n community node](https://img.shields.io/badge/n8n-community%20node-EA4B71?style=flat-square&logo=n8n)](https://n8n.io)
 [![License: MIT](https://img.shields.io/badge/license-MIT-blue?style=flat-square)](LICENSE)
 
@@ -16,20 +16,30 @@
 
 ## Overview
 
-`n8n-nodes-nvidia-nim` is an n8n community node that gives you access to **NVIDIA NIM's free hosted language models** directly inside your workflows.  
-It plugs into n8n's **AI Agent** as a drop-in language model — just like the built-in OpenAI or Anthropic nodes.
+`@sateeshreddy/n8n-nodes-nvidia-nim` is an n8n community node package that gives you access to **NVIDIA NIM's free hosted models** directly inside your workflows.
+
+This package includes **two nodes**:
+
+| Node | Purpose |
+|---|---|
+| **NVIDIA NIM** | Language model — connects to AI Agent, LLM Chain, etc. |
+| **NVIDIA NIM Embeddings** | Embeddings model — connects to Qdrant, Pinecone, PGVector, Supabase, Weaviate, etc. |
 
 ### Why use this?
 
 - ✅ Free tier models via [build.nvidia.com](https://build.nvidia.com)
-- ✅ Works as a proper **AI sub-node** (connect to any AI Agent)  
-- ✅ Supports 17+ models including Llama 4, Mistral, Qwen3, Gemma, and more
+- ✅ **Language model node** — plugs into AI Agent, Basic LLM Chain, Summarization Chain
+- ✅ **Embeddings node** — plugs into any n8n vector store (Qdrant, Pinecone, PGVector, Supabase, Weaviate, Chroma)
+- ✅ Supports 17+ chat models including Llama 4, Mistral, Qwen3, Gemma, and more
+- ✅ Supports 5 embedding models including free hosted endpoints
 - ✅ Drop-in OpenAI-compatible API — no extra setup
 
 ---
 
 ## Supported Models
 
+### Chat / Language Models
+
 | Model | Value |
 |---|---|
 | Llama 4 Maverick 17B 128E Instruct *(default)* | `meta/llama-4-maverick-17b-128e-instruct` |
@@ -50,6 +60,16 @@ It plugs into n8n's **AI Agent** as a drop-in language model — just like the b
 | Nemotron Mini 4B Instruct | `nvidia/nemotron-mini-4b-instruct` |
 | Solar 10.7B Instruct | `upstage/solar-10.7b-instruct` |
 
+### Embedding Models
+
+| Model | Value | Note |
+|---|---|---|
+| NV Embed v1 *(default)* | `nvidia/nv-embed-v1` | Free hosted endpoint |
+| NV EmbedQA E5 v5 | `nvidia/nv-embedqa-e5-v5` | Best for RAG / QA pipelines |
+| Llama Nemotron Embed 1B v2 | `nvidia/llama-nemotron-embed-1b-v2` | Multilingual, 26 languages |
+| Llama Nemotron Embed VL 1B v2 | `nvidia/llama-nemotron-embed-vl-1b-v2` | Multimodal (text + image docs) |
+| BGE-M3 | `BAAI/bge-m3` | Dense + multi-vector + sparse retrieval |
+
 ---
 
 ## Installation
@@ -59,17 +79,14 @@ It plugs into n8n's **AI Agent** as a drop-in language model — just like the b
 1. Open your n8n instance
 2. Go to **Settings → Community Nodes**
 3. Click **Install**
-4. Enter `n8n-nodes-nvidia-nim` and confirm
+4. Enter `@sateeshreddy/n8n-nodes-nvidia-nim` and confirm
 
 ### Manual Installation
 
-```bash
-# Navigate to your n8n custom nodes directory
-cd ~/.n8n/custom/
+Navigate to your n8n custom nodes directory and install:
 
-# Install the package
-npm install n8n-nodes-nvidia-nim
-```
+    cd ~/.n8n/custom/
+    npm install @sateeshreddy/n8n-nodes-nvidia-nim
 
 Then restart n8n.
 
@@ -88,146 +105,59 @@ Then restart n8n.
 
 ## Usage
 
-### 1. Add Credentials
+### Setting Up Credentials
 
-In n8n, go to **Credentials → New → NVIDIA NIM API** and paste your API key.
+In n8n, go to **Credentials → New → NVIDIA NIM API** and paste your API key. Both the chat node and the embeddings node share the same credential.
 
-### 2. Add the Node to a Workflow
+---
 
-1. Add an **AI Agent** node to your workflow
-2. In the Agent's **Model** slot, click the `+` button
-3. Search for **NVIDIA NIM** and select it
-4. Configure the model, temperature, and max tokens
-5. Run your workflow
+### NVIDIA NIM (Chat / Language Model)
 
-The node acts as a language model supplier — it connects to AI Agents, chains, and any other LangChain-compatible n8n node.
+Use this node anywhere n8n expects a **language model**.
 
----
+1. Add an **AI Agent** (or Basic LLM Chain) node to your workflow
+2. In the **Model** slot, click `+`
+3. Search for **NVIDIA NIM** and select it
+4. Choose your model, set temperature and max tokens
+5. Run your workflow
 
-## Configuration Options
+**Configuration Options:**
 
 | Parameter | Type | Default | Description |
 |---|---|---|---|
-| **Model** | Dropdown | `llama-4-maverick-17b-128e-instruct` | The NIM model to use |
-| **Temperature** | Number (0–2) | `0.7` | Controls output randomness. Lower = more deterministic |
-| **Max Tokens** | Number (1–4096) | `1000` | Maximum tokens in the response |
+| Model | Dropdown | `llama-4-maverick-17b-128e-instruct` | The NIM chat model to use |
+| Temperature | Number (0–2) | `0.7` | Controls output randomness. Lower = more deterministic |
+| Max Tokens | Number (1–4096) | `1000` | Maximum tokens in the response |
 
 ---
 
-## Known Issue — Routing Light Not Animating
-
-> ⚠️ **This section documents a bug found in earlier versions of this node and how it was fixed.**  
-> If you installed version `1.0.0` or earlier, please update to the latest version.
-
-### What was happening
-
-When users ran a workflow containing this node, the **routing light** (the animated glow/pulse around a node that shows it is actively executing) never appeared — even though the node was working correctly behind the scenes.
-
-Every other node in the workflow showed the animation, but the NVIDIA NIM node stayed visually "dark" throughout execution.
-
-### Root Cause
-
-This node uses n8n's `supplyData()` method instead of `execute()` — which is the correct pattern for **AI sub-nodes** (language model supply nodes that connect to AI Agents). However, `supplyData` has a different execution lifecycle than `execute`, and n8n tracks visual status through that lifecycle.
-
-Three things were missing:
-
-**1. No `closeFunction` returned**
-
-`supplyData` must return a `closeFunction` alongside the model response. n8n uses this callback as the signal that the node has finished its work — which is what triggers the routing light to complete its animation and mark the node as done.
+### NVIDIA NIM Embeddings
 
-```ts
-// ❌ Before — n8n never knew the node finished
-return {
-  response: chatModel,
-};
+Use this node anywhere n8n expects an **embeddings model** — vector stores like Qdrant, Pinecone, PGVector, Supabase, Weaviate, and Chroma.
 
-// ✅ After — n8n now correctly tracks completion
-return {
-  response: chatModel,
-  closeFunction: async () => {},
-};
-```
-
-**2. Errors were not re-thrown as `NodeOperationError`**
-
-When the node threw an error (bad API key, network failure, etc.), n8n had no way to update the node's visual state to "failed". The routing light would simply never appear.
-
-```ts
-// ❌ Before — silent failure, n8n UI stays blank
-} catch (error) {
-  console.error(error);
-}
-
-// ✅ After — n8n marks the node as failed with an error badge
-} catch (error) {
-  throw new NodeOperationError(this.getNode(), error as Error);
-}
-```
-
-**3. Missing `outputConnectionTypes` in node descriptor**
-
-Without declaring `outputConnectionTypes`, n8n's UI couldn't properly register the node as a typed AI supply node, which prevented the execution tracker from attaching to it.
-
-```json
-// ✅ Added to NvidiaNim.node.json
-"outputConnectionTypes": {
-  "ai_languageModel": [{ "type": "ai_languageModel" }]
-}
-```
-
-### The Fix (v1.1.0+)
-
-All three issues were resolved in `v1.1.0`. The node now correctly shows the routing light animation during execution, displays an error badge on failure, and cleans up properly after each run.
-
----
-
-## Development
-
-```bash
-# Install dependencies
-npm install
-
-# TypeScript watch mode (auto-recompile on save)
-npm run dev
-
-# Build distributable files
-npm run build
-
-# Lint code
-npm run lint
-
-# Auto-fix lint issues
-npm run lintfix
+1. Add a **Qdrant Vector Store** (or any other vector store) node
+2. In the **Embeddings** slot, click `+`
+3. Search for **NVIDIA NIM Embeddings** and select it
+4. Choose your embedding model
+5. Run your workflow
 
-# Format with Prettier
-npm run format
-```
+**Configuration Options:**
 
-### Project Structure
+| Parameter | Type | Default | Description |
+|---|---|---|---|
+| Model | Dropdown | `nvidia/nv-embed-v1` | The NIM embedding model to use |
 
-```
-n8n-nodes-nvidia-nim/
-├── credentials/
-│   └── NvidiaNimApi.credentials.ts   # API key credential definition
-├── nodes/
-│   └── NvidiaNim/
-│       ├── NvidiaNim.node.ts          # Node logic (supplyData)
-│       ├── NvidiaNim.node.json        # Node descriptor & UI properties
-│       └── nvidia-nim.png             # Node icon
-├── dist/                              # Compiled output (generated)
-├── package.json
-└── README.md
-```
+**Compatible vector stores:** Qdrant · Pinecone · PGVector · Supabase · Weaviate · Chroma
 
 ---
 
 ## Contributing
 
-Pull requests are welcome! If you'd like to add a new model, fix a bug, or improve documentation:
+Pull requests are welcome! To add a new model, fix a bug, or improve documentation:
 
 1. Fork the repo
-2. Create a feature branch: `git checkout -b feat/your-feature`
-3. Commit your changes: `git commit -m 'feat: add your feature'`
+2. Create a feature branch
+3. Commit your changes
 4. Push and open a PR
 
 ---

package/dist/nodes/NvidiaNim/NvidiaNimEmbeddings.node.d.ts

@@ -0,0 +1,6 @@
+import { INodeType, INodeTypeDescription, ISupplyDataFunctions, SupplyData } from 'n8n-workflow';
+export declare class NvidiaNimEmbeddings implements INodeType {
+    description: INodeTypeDescription;
+    supplyData(this: ISupplyDataFunctions, itemIndex: number): Promise<SupplyData>;
+}
+//# sourceMappingURL=NvidiaNimEmbeddings.node.d.ts.map

package/dist/nodes/NvidiaNim/NvidiaNimEmbeddings.node.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"NvidiaNimEmbeddings.node.d.ts","sourceRoot":"","sources":["../../../nodes/NvidiaNim/NvidiaNimEmbeddings.node.ts"],"names":[],"mappings":"AAAA,OAAO,EACN,SAAS,EACT,oBAAoB,EACpB,oBAAoB,EACpB,UAAU,EAEV,MAAM,cAAc,CAAC;AA2CtB,qBAAa,mBAAoB,YAAW,SAAS;IACpD,WAAW,EAAE,oBAAoB,CA4CI;IAE/B,UAAU,CAAC,IAAI,EAAE,oBAAoB,EAAE,SAAS,EAAE,MAAM,GAAG,OAAO,CAAC,UAAU,CAAC;CAgBpF"}

package/dist/nodes/NvidiaNim/NvidiaNimEmbeddings.node.js

@@ -0,0 +1,109 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.NvidiaNimEmbeddings = void 0;
+const n8n_workflow_1 = require("n8n-workflow");
+const embeddings_1 = require("@langchain/core/embeddings");
+class NvidiaNimEmbeddingsClass extends embeddings_1.Embeddings {
+    constructor(apiKey, model) {
+        super({});
+        this.apiKey = apiKey;
+        this.model = model;
+    }
+    async embedDocuments(texts) {
+        try {
+            const response = await fetch('https://integrate.api.nvidia.com/v1/embeddings', {
+                method: 'POST',
+                headers: {
+                    'Content-Type': 'application/json',
+                    Authorization: `Bearer ${this.apiKey}`,
+                    Accept: 'application/json',
+                },
+                body: JSON.stringify({
+                    input: texts,
+                    model: this.model,
+                    input_type: 'query',
+                }),
+            });
+            if (!response.ok) {
+                const errorText = await response.text();
+                throw new Error(`NVIDIA NIM API Error: ${response.status} ${errorText}`);
+            }
+            const data = await response.json();
+            const sortedData = data.data.sort((a, b) => a.index - b.index);
+            return sortedData.map((item) => item.embedding);
+        }
+        catch (error) {
+            throw new Error(`Failed to generate embeddings: ${error.message}`);
+        }
+    }
+    async embedQuery(text) {
+        const docs = await this.embedDocuments([text]);
+        return docs[0];
+    }
+}
+class NvidiaNimEmbeddings {
+    constructor() {
+        this.description = {
+            displayName: 'NVIDIA NIM Embeddings',
+            name: 'nvidiaNimEmbeddings',
+            icon: 'file:nvidia-nim.png',
+            group: ['transform'],
+            version: 1,
+            description: 'Call any embeddings model from NVIDIA NIM',
+            defaults: {
+                name: 'NVIDIA NIM Embeddings',
+            },
+            inputs: [],
+            outputs: ['ai_embedding'],
+            outputNames: ['Embeddings'],
+            outputConnectionTypes: {
+                ai_embedding: [{ type: 'ai_embedding' }],
+            },
+            codex: {
+                categories: ['AI'],
+                subcategories: {
+                    AI: ['Embeddings'],
+                },
+                resources: {},
+            },
+            credentials: [
+                {
+                    name: 'nvidiaNimApi',
+                    required: true,
+                },
+            ],
+            properties: [
+                {
+                    displayName: 'Model',
+                    name: 'model',
+                    type: 'options',
+                    options: [
+                        { name: 'NV Embed v1 (Free Endpoint)', value: 'nvidia/nv-embed-v1' },
+                        { name: 'NV EmbedQA E5 v5', value: 'nvidia/nv-embedqa-e5-v5' },
+                        { name: 'Llama Nemotron Embed 1B v2', value: 'nvidia/llama-nemotron-embed-1b-v2' },
+                        { name: 'Llama Nemotron Embed VL 1B v2 (Multimodal)', value: 'nvidia/llama-nemotron-embed-vl-1b-v2' },
+                        { name: 'BGE-M3 (Dense + Sparse)', value: 'BAAI/bge-m3' },
+                    ],
+                    default: 'nvidia/nv-embed-v1',
+                },
+            ],
+        };
+    }
+    async supplyData(itemIndex) {
+        try {
+            const credentials = await this.getCredentials('nvidiaNimApi');
+            const apiKey = credentials.apiKey;
+            const model = this.getNodeParameter('model', itemIndex, '');
+            const embeddings = new NvidiaNimEmbeddingsClass(apiKey, model);
+            return {
+                response: embeddings,
+                closeFunction: async () => { },
+            };
+        }
+        catch (error) {
+            throw new n8n_workflow_1.NodeOperationError(this.getNode(), error);
+        }
+    }
+}
+exports.NvidiaNimEmbeddings = NvidiaNimEmbeddings;
+//# sourceMappingURL=NvidiaNimEmbeddings.node.js.map

package/dist/nodes/NvidiaNim/NvidiaNimEmbeddings.node.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"NvidiaNimEmbeddings.node.js","sourceRoot":"","sources":["../../../nodes/NvidiaNim/NvidiaNimEmbeddings.node.ts"],"names":[],"mappings":";;;AAAA,+CAMsB;AACtB,2DAAwD;AAExD,MAAM,wBAAyB,SAAQ,uBAAU;IAChD,YAAoB,MAAc,EAAU,KAAa;QACxD,KAAK,CAAC,EAAE,CAAC,CAAC;QADS,WAAM,GAAN,MAAM,CAAQ;QAAU,UAAK,GAAL,KAAK,CAAQ;IAEzD,CAAC;IAED,KAAK,CAAC,cAAc,CAAC,KAAe;QACnC,IAAI,CAAC;YACJ,MAAM,QAAQ,GAAG,MAAM,KAAK,CAAC,gDAAgD,EAAE;gBAC9E,MAAM,EAAE,MAAM;gBACd,OAAO,EAAE;oBACR,cAAc,EAAE,kBAAkB;oBAClC,aAAa,EAAE,UAAU,IAAI,CAAC,MAAM,EAAE;oBACtC,MAAM,EAAE,kBAAkB;iBAC1B;gBACD,IAAI,EAAE,IAAI,CAAC,SAAS,CAAC;oBACpB,KAAK,EAAE,KAAK;oBACZ,KAAK,EAAE,IAAI,CAAC,KAAK;oBACjB,UAAU,EAAE,OAAO;iBACnB,CAAC;aACF,CAAC,CAAC;YAEH,IAAI,CAAC,QAAQ,CAAC,EAAE,EAAE,CAAC;gBAClB,MAAM,SAAS,GAAG,MAAM,QAAQ,CAAC,IAAI,EAAE,CAAC;gBACxC,MAAM,IAAI,KAAK,CAAC,yBAAyB,QAAQ,CAAC,MAAM,IAAI,SAAS,EAAE,CAAC,CAAC;YAC1E,CAAC;YAED,MAAM,IAAI,GAAG,MAAM,QAAQ,CAAC,IAAI,EAAE,CAAC;YACnC,MAAM,UAAU,GAAG,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAM,EAAE,CAAM,EAAE,EAAE,CAAC,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC,KAAK,CAAC,CAAC;YACzE,OAAO,UAAU,CAAC,GAAG,CAAC,CAAC,IAAS,EAAE,EAAE,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;QACtD,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YAChB,MAAM,IAAI,KAAK,CAAC,kCAAmC,KAAe,CAAC,OAAO,EAAE,CAAC,CAAC;QAC/E,CAAC;IACF,CAAC;IAED,KAAK,CAAC,UAAU,CAAC,IAAY;QAC5B,MAAM,IAAI,GAAG,MAAM,IAAI,CAAC,cAAc,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC;QAC/C,OAAO,IAAI,CAAC,CAAC,CAAC,CAAC;IAChB,CAAC;CACD;AAED,MAAa,mBAAmB;IAAhC;QACC,gBAAW,GAAyB;YACnC,WAAW,EAAE,uBAAuB;YACpC,IAAI,EAAE,qBAAqB;YAC3B,IAAI,EAAE,qBAAqB;YAC3B,KAAK,EAAE,CAAC,WAAW,CAAC;YACpB,OAAO,EAAE,CAAC;YACV,WAAW,EAAE,2CAA2C;YACxD,QAAQ,EAAE;gBACT,IAAI,EAAE,uBAAuB;aAC7B;YACD,MAAM,EAAE,EAAE;YACV,OAAO,EAAE,CAAC,cAAc,CAAC;YACzB,WAAW,EAAE,CAAC,YAAY,CAAC;YAC3B,qBAAqB,EAAE;gBACtB,YAAY,EAAE,CAAC,EAAE,IAAI,EAAE,cAAc,EAAE,CAAC;aACxC;YACD,KAAK,EAAE;gBACN,UAAU,EAAE,CAAC,IAAI,CAAC;gBAClB,aAAa,EAAE;oBACd,EAAE,EAAE,CAAC,YAAY,CAAC;iBAClB;gBACD,SAAS,EAAE,EAAE;aACb;YACD,WAAW,EAAE;gBACZ;oBACC,IAAI,EAAE,cAAc;oBACpB,QAAQ,EAAE,IAAI;iBACd;aACD;YACD,UAAU,EAAE;gBACX;oBACC,WAAW,EAAE,OAAO;oBACpB,IAAI,EAAE,OAAO;oBACb,IAAI,EAAE,SAAS;oBACf,OAAO,EAAE;wBACR,EAAE,IAAI,EAAE,6BAA6B,EAAE,KAAK,EAAE,oBAAoB,EAAE;wBACpE,EAAE,IAAI,EAAE,kBAAkB,EAAE,KAAK,EAAE,yBAAyB,EAAE;wBAC9D,EAAE,IAAI,EAAE,4BAA4B,EAAE,KAAK,EAAE,mCAAmC,EAAE;wBAClF,EAAE,IAAI,EAAE,4CAA4C,EAAE,KAAK,EAAE,sCAAsC,EAAE;wBACrG,EAAE,IAAI,EAAE,yBAAyB,EAAE,KAAK,EAAE,aAAa,EAAE;qBACzD;oBACD,OAAO,EAAE,oBAAoB;iBAC7B;aACD;SACkC,CAAC;IAkBtC,CAAC;IAhBA,KAAK,CAAC,UAAU,CAA6B,SAAiB;QAC7D,IAAI,CAAC;YACJ,MAAM,WAAW,GAAG,MAAM,IAAI,CAAC,cAAc,CAAC,cAAc,CAAC,CAAC;YAC9D,MAAM,MAAM,GAAG,WAAW,CAAC,MAAgB,CAAC;YAC5C,MAAM,KAAK,GAAG,IAAI,CAAC,gBAAgB,CAAC,OAAO,EAAE,SAAS,EAAE,EAAE,CAAW,CAAC;YAEtE,MAAM,UAAU,GAAG,IAAI,wBAAwB,CAAC,MAAM,EAAE,KAAK,CAAC,CAAC;YAE/D,OAAO;gBACN,QAAQ,EAAE,UAAU;gBACpB,aAAa,EAAE,KAAK,IAAI,EAAE,GAAE,CAAC;aAC7B,CAAC;QACH,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YAChB,MAAM,IAAI,iCAAkB,CAAC,IAAI,CAAC,OAAO,EAAE,EAAE,KAAc,CAAC,CAAC;QAC9D,CAAC;IACF,CAAC;CACD;AA/DD,kDA+DC"}

package/nodes/NvidiaNim/NvidiaNimEmbeddings.node.ts

@@ -0,0 +1,113 @@
+import {
+	INodeType,
+	INodeTypeDescription,
+	ISupplyDataFunctions,
+	SupplyData,
+	NodeOperationError,
+} from 'n8n-workflow';
+import { Embeddings } from '@langchain/core/embeddings';
+
+class NvidiaNimEmbeddingsClass extends Embeddings {
+	constructor(private apiKey: string, private model: string) {
+		super({});
+	}
+
+	async embedDocuments(texts: string[]): Promise<number[][]> {
+		try {
+			const response = await fetch('https://integrate.api.nvidia.com/v1/embeddings', {
+				method: 'POST',
+				headers: {
+					'Content-Type': 'application/json',
+					Authorization: `Bearer ${this.apiKey}`,
+					Accept: 'application/json',
+				},
+				body: JSON.stringify({
+					input: texts,
+					model: this.model,
+					input_type: 'query',
+				}),
+			});
+
+			if (!response.ok) {
+				const errorText = await response.text();
+				throw new Error(`NVIDIA NIM API Error: ${response.status} ${errorText}`);
+			}
+
+			const data = await response.json();
+			const sortedData = data.data.sort((a: any, b: any) => a.index - b.index);
+			return sortedData.map((item: any) => item.embedding);
+		} catch (error) {
+			throw new Error(`Failed to generate embeddings: ${(error as Error).message}`);
+		}
+	}
+
+	async embedQuery(text: string): Promise<number[]> {
+		const docs = await this.embedDocuments([text]);
+		return docs[0];
+	}
+}
+
+export class NvidiaNimEmbeddings implements INodeType {
+	description: INodeTypeDescription = {
+		displayName: 'NVIDIA NIM Embeddings',
+		name: 'nvidiaNimEmbeddings',
+		icon: 'file:nvidia-nim.png',
+		group: ['transform'],
+		version: 1,
+		description: 'Call any embeddings model from NVIDIA NIM',
+		defaults: {
+			name: 'NVIDIA NIM Embeddings',
+		},
+		inputs: [],
+		outputs: ['ai_embedding'],
+		outputNames: ['Embeddings'],
+		outputConnectionTypes: {
+			ai_embedding: [{ type: 'ai_embedding' }],
+		},
+		codex: {
+			categories: ['AI'],
+			subcategories: {
+				AI: ['Embeddings'],
+			},
+			resources: {},
+		},
+		credentials: [
+			{
+				name: 'nvidiaNimApi',
+				required: true,
+			},
+		],
+		properties: [
+			{
+				displayName: 'Model',
+				name: 'model',
+				type: 'options',
+				options: [
+					{ name: 'NV Embed v1 (Free Endpoint)', value: 'nvidia/nv-embed-v1' },
+					{ name: 'NV EmbedQA E5 v5', value: 'nvidia/nv-embedqa-e5-v5' },
+					{ name: 'Llama Nemotron Embed 1B v2', value: 'nvidia/llama-nemotron-embed-1b-v2' },
+					{ name: 'Llama Nemotron Embed VL 1B v2 (Multimodal)', value: 'nvidia/llama-nemotron-embed-vl-1b-v2' },
+					{ name: 'BGE-M3 (Dense + Sparse)', value: 'BAAI/bge-m3' },
+				],
+				default: 'nvidia/nv-embed-v1',
+			},
+		],
+	} as unknown as INodeTypeDescription;
+
+	async supplyData(this: ISupplyDataFunctions, itemIndex: number): Promise<SupplyData> {
+		try {
+			const credentials = await this.getCredentials('nvidiaNimApi');
+			const apiKey = credentials.apiKey as string;
+			const model = this.getNodeParameter('model', itemIndex, '') as string;
+
+			const embeddings = new NvidiaNimEmbeddingsClass(apiKey, model);
+
+			return {
+				response: embeddings,
+				closeFunction: async () => {},
+			};
+		} catch (error) {
+			throw new NodeOperationError(this.getNode(), error as Error);
+		}
+	}
+}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sateeshreddy/n8n-nodes-nvidia-nim",
-  "version": "1.0.3",
+  "version": "1.0.6",
   "description": "n8n community node for NVIDIA NIM",
   "main": "dist/nodes/NvidiaNim/NvidiaNim.node.js",
   "scripts": {
@@ -24,6 +24,9 @@
     "@langchain/openai": "^1.4.5",
     "n8n-workflow": "^1.0.0"
   },
+  "overrides": {
+    "form-data": "^4.0.1"
+  },
   "devDependencies": {
     "@types/node": "^16.0.0",
     "@typescript-eslint/eslint-plugin": "^5.0.0",
@@ -37,7 +40,8 @@
   "n8n": {
     "n8nNodesApiVersion": 1,
     "nodes": [
-      "dist/nodes/NvidiaNim/NvidiaNim.node.js"
+      "dist/nodes/NvidiaNim/NvidiaNim.node.js",
+      "dist/nodes/NvidiaNim/NvidiaNimEmbeddings.node.js"
     ],
     "credentials": [
       "dist/credentials/NvidiaNimApi.credentials.js"

package/tsconfig.json

@@ -2,7 +2,10 @@
   "compilerOptions": {
     "target": "es2020",
     "module": "commonjs",
-     "lib": ["es2020", "dom"],
+    "lib": [
+      "es2020",
+      "dom"
+    ],
     "outDir": "./dist",
     "rootDir": "./",
     "strict": true,