Voyage AI - Credentials, Embeddings and Rerank (#2015)

* Voyage AI - Credentials and Embeddings

* reranker and fixes for embeddings

packages/components/credentials/VoyageAIApi.credential.ts

@@ -0,0 +1,32 @@
+import { INodeParams, INodeCredential } from '../src/Interface'
+
+class VoyageAIApi implements INodeCredential {
+    label: string
+    name: string
+    version: number
+    description: string
+    inputs: INodeParams[]
+
+    constructor() {
+        this.label = 'Voyage AI API'
+        this.name = 'voyageAIApi'
+        this.version = 1.0
+        this.description =
+            'Refer to <a target="_blank" href="https://docs.voyageai.com/install/#authentication-with-api-keys">official guide</a> on how to get an API Key'
+        this.inputs = [
+            {
+                label: 'Voyage AI Endpoint',
+                name: 'endpoint',
+                type: 'string',
+                default: 'https://api.voyageai.com/v1/embeddings'
+            },
+            {
+                label: 'Voyage AI API Key',
+                name: 'apiKey',
+                type: 'password'
+            }
+        ]
+    }
+}
+
+module.exports = { credClass: VoyageAIApi }

packages/components/nodes/embeddings/VoyageAIEmbedding/VoyageAIEmbedding.ts

@@ -0,0 +1,84 @@
+import { ICommonObject, INode, INodeData, INodeParams } from '../../../src/Interface'
+import { getBaseClasses, getCredentialData, getCredentialParam } from '../../../src/utils'
+import { VoyageEmbeddings, VoyageEmbeddingsParams } from 'langchain/embeddings/voyage'
+
+class VoyageAIEmbedding_Embeddings implements INode {
+    label: string
+    name: string
+    version: number
+    type: string
+    icon: string
+    category: string
+    description: string
+    baseClasses: string[]
+    credential: INodeParams
+    inputs: INodeParams[]
+
+    constructor() {
+        this.label = 'VoyageAI Embeddings'
+        this.name = 'voyageAIEmbeddings'
+        this.version = 1.0
+        this.type = 'VoyageAIEmbeddings'
+        this.icon = 'voyageai.png'
+        this.category = 'Embeddings'
+        this.description = 'Voyage AI API to generate embeddings for a given text'
+        this.baseClasses = [this.type, ...getBaseClasses(VoyageEmbeddings)]
+        this.credential = {
+            label: 'Connect Credential',
+            name: 'credential',
+            type: 'credential',
+            credentialNames: ['voyageAIApi']
+        }
+        this.inputs = [
+            {
+                label: 'Model Name',
+                name: 'modelName',
+                type: 'options',
+                options: [
+                    {
+                        label: 'voyage-2',
+                        name: 'voyage-2',
+                        description: 'Base generalist embedding model optimized for both latency and quality'
+                    },
+                    {
+                        label: 'voyage-code-2',
+                        name: 'voyage-code-2',
+                        description: 'Optimized for code retrieval'
+                    },
+                    {
+                        label: 'voyage-large-2',
+                        name: 'voyage-large-2',
+                        description: 'Powerful generalist embedding model'
+                    },
+                    {
+                        label: 'voyage-lite-02-instruct',
+                        name: 'voyage-lite-02-instruct',
+                        description: 'Instruction-tuned for classification, clustering, and sentence textual similarity tasks'
+                    }
+                ],
+                default: 'voyage-2',
+                optional: true
+            }
+        ]
+    }
+
+    async init(nodeData: INodeData, _: string, options: ICommonObject): Promise<any> {
+        const modelName = nodeData.inputs?.modelName as string
+
+        const credentialData = await getCredentialData(nodeData.credential ?? '', options)
+        const voyageAiApiKey = getCredentialParam('apiKey', credentialData, nodeData)
+        const voyageAiEndpoint = getCredentialParam('endpoint', credentialData, nodeData)
+
+        const obj: Partial<VoyageEmbeddingsParams> & { apiKey?: string } = {
+            apiKey: voyageAiApiKey
+        }
+
+        if (modelName) obj.modelName = modelName
+
+        const model = new VoyageEmbeddings(obj)
+        if (voyageAiEndpoint) model.apiUrl = voyageAiEndpoint
+        return model
+    }
+}
+
+module.exports = { nodeClass: VoyageAIEmbedding_Embeddings }

packages/components/nodes/retrievers/VoyageAIRetriever/VoyageAIRerank.ts

@@ -0,0 +1,52 @@
+import axios from 'axios'
+import { Callbacks } from '@langchain/core/callbacks/manager'
+import { Document } from '@langchain/core/documents'
+import { BaseDocumentCompressor } from 'langchain/retrievers/document_compressors'
+
+export class VoyageAIRerank extends BaseDocumentCompressor {
+    private voyageAIAPIKey: any
+    private readonly VOYAGEAI_RERANK_API_URL = 'https://api.voyageai.com/v1/rerank'
+    private model: string = 'rerank-lite-1'
+    private readonly k: number
+
+    constructor(voyageAIAPIKey: string, model: string, k: number) {
+        super()
+        this.voyageAIAPIKey = voyageAIAPIKey
+        this.model = model
+        this.k = k
+    }
+    async compressDocuments(
+        documents: Document<Record<string, any>>[],
+        query: string,
+        _?: Callbacks | undefined
+    ): Promise<Document<Record<string, any>>[]> {
+        // avoid empty api call
+        if (documents.length === 0) {
+            return []
+        }
+        const config = {
+            headers: {
+                Authorization: `Bearer ${this.voyageAIAPIKey}`,
+                'Content-Type': 'application/json',
+                Accept: 'application/json'
+            }
+        }
+        const data = {
+            model: this.model,
+            query: query,
+            documents: documents.map((doc) => doc.pageContent)
+        }
+        try {
+            let returnedDocs = await axios.post(this.VOYAGEAI_RERANK_API_URL, data, config)
+            const finalResults: Document<Record<string, any>>[] = []
+            returnedDocs.data.results.forEach((result: any) => {
+                const doc = documents[result.index]
+                doc.metadata.relevance_score = result.relevance_score
+                finalResults.push(doc)
+            })
+            return finalResults.splice(0, this.k)
+        } catch (error) {
+            return documents
+        }
+    }
+}

packages/components/nodes/retrievers/VoyageAIRetriever/VoyageAIRerankRetriever.ts

@@ -0,0 +1,129 @@
+import { BaseRetriever } from '@langchain/core/retrievers'
+import { VectorStoreRetriever } from '@langchain/core/vectorstores'
+import { ContextualCompressionRetriever } from 'langchain/retrievers/contextual_compression'
+import { VoyageAIRerank } from './VoyageAIRerank'
+import { getCredentialData, getCredentialParam, handleEscapeCharacters } from '../../../src'
+import { ICommonObject, INode, INodeData, INodeOutputsValue, INodeParams } from '../../../src/Interface'
+
+class VoyageAIRerankRetriever_Retrievers implements INode {
+    label: string
+    name: string
+    version: number
+    description: string
+    type: string
+    icon: string
+    category: string
+    baseClasses: string[]
+    inputs: INodeParams[]
+    credential: INodeParams
+    badge: string
+    outputs: INodeOutputsValue[]
+
+    constructor() {
+        this.label = 'Voyage AI Rerank Retriever'
+        this.name = 'voyageAIRerankRetriever'
+        this.version = 1.0
+        this.type = 'VoyageAIRerankRetriever'
+        this.icon = 'voyageai.png'
+        this.category = 'Retrievers'
+        this.badge = 'NEW'
+        this.description = 'Voyage AI Rerank indexes the documents from most to least semantically relevant to the query.'
+        this.baseClasses = [this.type, 'BaseRetriever']
+        this.credential = {
+            label: 'Connect Credential',
+            name: 'credential',
+            type: 'credential',
+            credentialNames: ['voyageAIApi']
+        }
+        this.inputs = [
+            {
+                label: 'Vector Store Retriever',
+                name: 'baseRetriever',
+                type: 'VectorStoreRetriever'
+            },
+            {
+                label: 'Model Name',
+                name: 'model',
+                type: 'options',
+                options: [
+                    {
+                        label: 'rerank-lite-1',
+                        name: 'rerank-lite-1'
+                    }
+                ],
+                default: 'rerank-lite-1',
+                optional: true
+            },
+            {
+                label: 'Query',
+                name: 'query',
+                type: 'string',
+                description: 'Query to retrieve documents from retriever. If not specified, user question will be used',
+                optional: true,
+                acceptVariable: true
+            },
+            {
+                label: 'Top K',
+                name: 'topK',
+                description: 'Number of top results to fetch. Default to the TopK of the Base Retriever',
+                placeholder: '4',
+                type: 'number',
+                additionalParams: true,
+                optional: true
+            }
+        ]
+        this.outputs = [
+            {
+                label: 'Voyage AI Rerank Retriever',
+                name: 'retriever',
+                baseClasses: this.baseClasses
+            },
+            {
+                label: 'Document',
+                name: 'document',
+                description: 'Array of document objects containing metadata and pageContent',
+                baseClasses: ['Document', 'json']
+            },
+            {
+                label: 'Text',
+                name: 'text',
+                description: 'Concatenated string from pageContent of documents',
+                baseClasses: ['string', 'json']
+            }
+        ]
+    }
+
+    async init(nodeData: INodeData, input: string, options: ICommonObject): Promise<any> {
+        const baseRetriever = nodeData.inputs?.baseRetriever as BaseRetriever
+        const model = nodeData.inputs?.model as string
+        const query = nodeData.inputs?.query as string
+        const credentialData = await getCredentialData(nodeData.credential ?? '', options)
+        const voyageAiApiKey = getCredentialParam('apiKey', credentialData, nodeData)
+        const topK = nodeData.inputs?.topK as string
+        const k = topK ? parseFloat(topK) : (baseRetriever as VectorStoreRetriever).k ?? 4
+        const output = nodeData.outputs?.output as string
+
+        const voyageAICompressor = new VoyageAIRerank(voyageAiApiKey, model, k)
+
+        const retriever = new ContextualCompressionRetriever({
+            baseCompressor: voyageAICompressor,
+            baseRetriever: baseRetriever
+        })
+
+        if (output === 'retriever') return retriever
+        else if (output === 'document') return await retriever.getRelevantDocuments(query ? query : input)
+        else if (output === 'text') {
+            let finaltext = ''
+
+            const docs = await retriever.getRelevantDocuments(query ? query : input)
+
+            for (const doc of docs) finaltext += `${doc.pageContent}\n`
+
+            return handleEscapeCharacters(finaltext, false)
+        }
+
+        return retriever
+    }
+}
+
+module.exports = { nodeClass: VoyageAIRerankRetriever_Retrievers }