feat: Add AI tool building capabilities (#7336)

Github issue / Community forum post (link here to close automatically):
https://community.n8n.io/t/langchain-memory-chat/23733

---------

Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
Co-authored-by: Oleg Ivaniv <me@olegivaniv.com>
Co-authored-by: Val <68596159+valya@users.noreply.github.com>
Co-authored-by: Alex Grozav <alex@grozav.com>
Co-authored-by: कारतोफ्फेलस्क्रिप्ट™ <aditya@netroy.in>
Co-authored-by: Deborah <deborah@starfallprojects.co.uk>
Co-authored-by: Jesper Bylund <mail@jesperbylund.com>
Co-authored-by: Jon <jonathan.bennetts@gmail.com>
Co-authored-by: Michael Kret <88898367+michael-radency@users.noreply.github.com>
Co-authored-by: Giulio Andreini <andreini@netseven.it>
Co-authored-by: Mason Geloso <Mason.geloso@gmail.com>
Co-authored-by: Mason Geloso <hone@Masons-Mac-mini.local>
Co-authored-by: Mutasem Aldmour <mutasem@n8n.io>

packages/@n8n/nodes-langchain/nodes/llms/LMOpenHuggingFaceInference/LmOpenHuggingFaceInference.node.ts

@@ -0,0 +1,150 @@
+/* eslint-disable n8n-nodes-base/node-dirname-against-convention */
+import {
+	NodeConnectionType,
+	type IExecuteFunctions,
+	type INodeType,
+	type INodeTypeDescription,
+	type SupplyData,
+} from 'n8n-workflow';
+
+import { HuggingFaceInference } from 'langchain/llms/hf';
+import { logWrapper } from '../../../utils/logWrapper';
+import { getConnectionHintNoticeField } from '../../../utils/sharedFields';
+
+export class LmOpenHuggingFaceInference implements INodeType {
+	description: INodeTypeDescription = {
+		displayName: 'Hugging Face Inference Model',
+		// eslint-disable-next-line n8n-nodes-base/node-class-description-name-miscased
+		name: 'lmOpenHuggingFaceInference',
+		icon: 'file:huggingface.svg',
+		group: ['transform'],
+		version: 1,
+		description: 'Language Model HuggingFaceInference',
+		defaults: {
+			name: 'Hugging Face Inference Model',
+		},
+		codex: {
+			categories: ['AI'],
+			subcategories: {
+				AI: ['Language Models'],
+			},
+			resources: {
+				primaryDocumentation: [
+					{
+						url: 'https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmopenhuggingfaceinference/',
+					},
+				],
+			},
+		},
+		// 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: [NodeConnectionType.AiLanguageModel],
+		outputNames: ['Model'],
+		credentials: [
+			{
+				name: 'huggingFaceApi',
+				required: true,
+			},
+		],
+		properties: [
+			getConnectionHintNoticeField([NodeConnectionType.AiChain, NodeConnectionType.AiAgent]),
+			{
+				displayName: 'Model',
+				name: 'model',
+				type: 'string',
+				default: 'gpt2',
+			},
+			{
+				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',
+					},
+					{
+						displayName: 'Frequency Penalty',
+						name: 'frequencyPenalty',
+						default: 0,
+						typeOptions: { maxValue: 2, minValue: -2, numberPrecision: 1 },
+						description:
+							"Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim",
+						type: 'number',
+					},
+					{
+						displayName: 'Maximum Number of Tokens',
+						name: 'maxTokens',
+						default: 128,
+						description:
+							'The maximum number of tokens to generate in the completion. Most models have a context length of 2048 tokens (except for the newest models, which support 32,768).',
+						type: 'number',
+						typeOptions: {
+							maxValue: 32768,
+						},
+					},
+					{
+						displayName: 'Presence Penalty',
+						name: 'presencePenalty',
+						default: 0,
+						typeOptions: { maxValue: 2, minValue: -2, numberPrecision: 1 },
+						description:
+							"Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics",
+						type: 'number',
+					},
+					{
+						displayName: 'Sampling Temperature',
+						name: 'temperature',
+						default: 1,
+						typeOptions: { maxValue: 1, minValue: 0, numberPrecision: 1 },
+						description:
+							'Controls randomness: Lowering results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive.',
+						type: 'number',
+					},
+					{
+						displayName: 'Top K',
+						name: 'topK',
+						default: 1,
+						typeOptions: { maxValue: 1, minValue: 0, numberPrecision: 1 },
+						description:
+							'Controls the top tokens to consider within the sample operation to create new text',
+						type: 'number',
+					},
+					{
+						displayName: 'Top P',
+						name: 'topP',
+						default: 1,
+						typeOptions: { maxValue: 1, minValue: 0, numberPrecision: 1 },
+						description:
+							'Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered. We generally recommend altering this or temperature but not both.',
+						type: 'number',
+					},
+				],
+			},
+		],
+	};
+
+	async supplyData(this: IExecuteFunctions, itemIndex: number): Promise<SupplyData> {
+		const credentials = await this.getCredentials('huggingFaceApi');
+
+		const modelName = this.getNodeParameter('model', itemIndex) as string;
+		const options = this.getNodeParameter('options', itemIndex, {}) as object;
+
+		const model = new HuggingFaceInference({
+			model: modelName,
+			apiKey: credentials.apiKey as string,
+			...options,
+		});
+
+		return {
+			response: logWrapper(model, this),
+		};
+	}
+}