Feature: Add Jina AI Rerank Retriever (#3898)

packages/components/nodes/retrievers/JinaRerankRetriever/JinaAI.svg

@@ -0,0 +1,5 @@
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 94 40">
+  <path fill="#EB6161" d="M6.12 39.92c3.38 0 6.12-2.74 6.12-6.12s-2.74-6.12-6.12-6.12S0 30.42 0 33.8s2.74 6.12 6.12 6.12z"/>
+  <path fill="#009191" fill-rule="evenodd" d="M25.4 14.52c.8 0 1.44.64 1.44 1.44l-.08 11.72c0 6.68-5.36 12.12-12.04 12.24h-.2v-12.2h.04L14.6 16c0-.8.64-1.44 1.44-1.44h9.36v-.04zm18.8 0c.8 0 1.44.64 1.44 1.44v16.4c0 .8-.64 1.44-1.44 1.44h-9.36c-.8 0-1.44-.64-1.44-1.44v-16.4c0-.8.64-1.44 1.44-1.44h9.36zm14.72-.04h.2c6 .08 10.88 4.92 11.04 10.92v6.92c0 .8-.64 1.44-1.44 1.44H53.6c-.8 0-1.44-.64-1.44-1.44v-16.4c0-.8.64-1.44 1.44-1.44h5.32zM83.68 33.6c-5.04-.32-9.08-4.52-9.08-9.64 0-5.32 4.32-9.64 9.64-9.64 5.12 0 9.32 4 9.64 9.08v8.76c0 .8-.64 1.44-1.44 1.44h-8.76z" clip-rule="evenodd"/>
+  <path fill="#FBCB67" d="M39.499 12.24c3.38 0 6.12-2.74 6.12-6.12S42.879 0 39.499 0s-6.12 2.74-6.12 6.12 2.74 6.12 6.12 6.12z"/>
+</svg>

packages/components/nodes/retrievers/JinaRerankRetriever/JinaRerank.ts

@@ -0,0 +1,51 @@
+import { Callbacks } from '@langchain/core/callbacks/manager'
+import { Document } from '@langchain/core/documents'
+import axios from 'axios'
+import { BaseDocumentCompressor } from 'langchain/retrievers/document_compressors'
+
+export class JinaRerank extends BaseDocumentCompressor {
+    private jinaAPIKey: string
+    private readonly JINA_RERANK_API_URL = 'https://api.jina.ai/v1/rerank'
+    private model: string = 'jina-reranker-v2-base-multilingual'
+    private readonly topN: number
+
+    constructor(jinaAPIKey: string, model: string, topN: number) {
+        super()
+        this.jinaAPIKey = jinaAPIKey
+        this.model = model
+        this.topN = topN
+    }
+    async compressDocuments(
+        documents: Document<Record<string, any>>[],
+        query: string,
+        _?: Callbacks | undefined
+    ): Promise<Document<Record<string, any>>[]> {
+        if (documents.length === 0) {
+            return []
+        }
+        const config = {
+            headers: {
+                Authorization: `Bearer ${this.jinaAPIKey}`,
+                'Content-Type': 'application/json'
+            }
+        }
+        const data = {
+            model: this.model,
+            query: query,
+            documents: documents.map((doc) => doc.pageContent),
+            top_n: this.topN
+        }
+        try {
+            let returnedDocs = await axios.post(this.JINA_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
+        } catch (error) {
+            return documents
+        }
+    }
+}

packages/components/nodes/retrievers/JinaRerankRetriever/JinaRerankRetriever.ts

@@ -0,0 +1,129 @@
+import { BaseRetriever } from '@langchain/core/retrievers'
+import { ContextualCompressionRetriever } from 'langchain/retrievers/contextual_compression'
+import { getCredentialData, getCredentialParam, handleEscapeCharacters } from '../../../src'
+import { ICommonObject, INode, INodeData, INodeOutputsValue, INodeParams } from '../../../src/Interface'
+import { JinaRerank } from './JinaRerank'
+
+class JinaRerankRetriever_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 = 'Jina AI Rerank Retriever'
+        this.name = 'JinaRerankRetriever'
+        this.version = 1.0
+        this.type = 'JinaRerankRetriever'
+        this.icon = 'JinaAI.svg'
+        this.category = 'Retrievers'
+        this.description = 'Jina 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: ['jinaAIApi']
+        }
+        this.inputs = [
+            {
+                label: 'Vector Store Retriever',
+                name: 'baseRetriever',
+                type: 'VectorStoreRetriever'
+            },
+            {
+                label: 'Model Name',
+                name: 'model',
+                type: 'options',
+                options: [
+                    {
+                        label: 'jina-reranker-v2-base-multilingual',
+                        name: 'jina-reranker-v2-base-multilingual'
+                    },
+                    {
+                        label: 'jina-colbert-v2',
+                        name: 'jina-colbert-v2'
+                    }
+                ],
+                default: 'jina-reranker-v2-base-multilingual',
+                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 N',
+                name: 'topN',
+                description: 'Number of top results to fetch. Default to 4',
+                placeholder: '4',
+                default: 4,
+                type: 'number',
+                additionalParams: true,
+                optional: true
+            }
+        ]
+        this.outputs = [
+            {
+                label: 'Jina 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 jinaApiKey = getCredentialParam('jinaAIAPIKey', credentialData, nodeData)
+        const topN = nodeData.inputs?.topN ? parseFloat(nodeData.inputs?.topN as string) : 4
+        const output = nodeData.outputs?.output as string
+
+        const jinaCompressor = new JinaRerank(jinaApiKey, model, topN)
+
+        const retriever = new ContextualCompressionRetriever({
+            baseCompressor: jinaCompressor,
+            baseRetriever: baseRetriever
+        })
+
+        if (output === 'retriever') return retriever
+        else if (output === 'document') return await retriever.invoke(query ? query : input)
+        else if (output === 'text') {
+            const docs = await retriever.invoke(query ? query : input)
+            let finaltext = ''
+            for (const doc of docs) finaltext += `${doc.pageContent}\n`
+
+            return handleEscapeCharacters(finaltext, false)
+        }
+
+        return retriever
+    }
+}
+
+module.exports = { nodeClass: JinaRerankRetriever_Retrievers }