add couchbase vectore store support (#2303)

* add couchbase vectore store support

* Updated on review comments

packages/components/nodes/vectorstores/Couchbase/Couchbase.ts

@@ -0,0 +1,229 @@
+import { flatten } from 'lodash'
+import { Embeddings } from '@langchain/core/embeddings'
+import { Document } from '@langchain/core/documents'
+import { CouchbaseVectorStore, CouchbaseVectorStoreArgs } from '@langchain/community/vectorstores/couchbase'
+import { Cluster } from 'couchbase'
+import { ICommonObject, INode, INodeData, INodeOutputsValue, INodeParams, IndexingResult } from '../../../src/Interface'
+import { getBaseClasses, getCredentialData, getCredentialParam } from '../../../src/utils'
+import { resolveVectorStoreOrRetriever } from '../VectorStoreUtils'
+
+class Couchbase_VectorStores implements INode {
+    label: string
+    name: string
+    version: number
+    description: string
+    type: string
+    icon: string
+    category: string
+    badge: string
+    baseClasses: string[]
+    inputs: INodeParams[]
+    credential: INodeParams
+    outputs: INodeOutputsValue[]
+
+    constructor() {
+        this.label = 'Couchbase'
+        this.name = 'couchbase'
+        this.version = 1.0
+        this.type = 'Couchbase'
+        this.icon = 'couchbase.svg'
+        this.category = 'Vector Stores'
+        this.description = `Upsert embedded data and load existing index using Couchbase, a award-winning distributed NoSQL database`
+        this.baseClasses = [this.type, 'VectorStoreRetriever', 'BaseRetriever']
+        this.credential = {
+            label: 'Connect Credential',
+            name: 'credential',
+            type: 'credential',
+            credentialNames: ['couchbaseApi']
+        }
+        this.inputs = [
+            {
+                label: 'Document',
+                name: 'document',
+                type: 'Document',
+                list: true,
+                optional: true
+            },
+            {
+                label: 'Embeddings',
+                name: 'embeddings',
+                type: 'Embeddings'
+            },
+            {
+                label: 'Bucket Name',
+                name: 'bucketName',
+                placeholder: '<DB_BUCKET_NAME>',
+                type: 'string'
+            },
+            {
+                label: 'Scope Name',
+                name: 'scopeName',
+                placeholder: '<SCOPE_NAME>',
+                type: 'string'
+            },
+            {
+                label: 'Collection Name',
+                name: 'collectionName',
+                placeholder: '<COLLECTION_NAME>',
+                type: 'string'
+            },
+            {
+                label: 'Index Name',
+                name: 'indexName',
+                placeholder: '<VECTOR_INDEX_NAME>',
+                type: 'string'
+            },
+            {
+                label: 'Content Field',
+                name: 'textKey',
+                description: 'Name of the field (column) that contains the actual content',
+                type: 'string',
+                default: 'text',
+                additionalParams: true,
+                optional: true
+            },
+            {
+                label: 'Embedded Field',
+                name: 'embeddingKey',
+                description: 'Name of the field (column) that contains the Embedding',
+                type: 'string',
+                default: 'embedding',
+                additionalParams: true,
+                optional: true
+            },
+            {
+                label: 'Couchbase Metadata Filter',
+                name: 'couchbaseMetadataFilter',
+                type: 'json',
+                optional: true,
+                additionalParams: true
+            },
+            {
+                label: 'Top K',
+                name: 'topK',
+                description: 'Number of top results to fetch. Default to 4',
+                placeholder: '4',
+                type: 'number',
+                additionalParams: true,
+                optional: true
+            }
+        ]
+        this.outputs = [
+            {
+                label: 'Couchbase Retriever',
+                name: 'retriever',
+                baseClasses: this.baseClasses
+            },
+            {
+                label: 'Couchbase Vector Store',
+                name: 'vectorStore',
+                baseClasses: [this.type, ...getBaseClasses(CouchbaseVectorStore)]
+            }
+        ]
+    }
+
+    //@ts-ignore
+    vectorStoreMethods = {
+        async upsert(nodeData: INodeData, options: ICommonObject): Promise<Partial<IndexingResult>> {
+            const credentialData = await getCredentialData(nodeData.credential ?? '', options)
+            const bucketName = nodeData.inputs?.bucketName as string
+            const scopeName = nodeData.inputs?.scopeName as string
+            const collectionName = nodeData.inputs?.collectionName as string
+            const indexName = nodeData.inputs?.indexName as string
+            let textKey = nodeData.inputs?.textKey as string
+            let embeddingKey = nodeData.inputs?.embeddingKey as string
+            const embeddings = nodeData.inputs?.embeddings as Embeddings
+
+            let connectionString = getCredentialParam('connectionString', credentialData, nodeData)
+            let databaseUsername = getCredentialParam('username', credentialData, nodeData)
+            let databasePassword = getCredentialParam('password', credentialData, nodeData)
+
+            const docs = nodeData.inputs?.document as Document[]
+
+            const flattenDocs = docs && docs.length ? flatten(docs) : []
+            const finalDocs = []
+            for (let i = 0; i < flattenDocs.length; i += 1) {
+                if (flattenDocs[i] && flattenDocs[i].pageContent) {
+                    const document = new Document(flattenDocs[i])
+                    finalDocs.push(document)
+                }
+            }
+
+            const couchbaseClient = await Cluster.connect(connectionString, {
+                username: databaseUsername,
+                password: databasePassword,
+                configProfile: 'wanDevelopment'
+            })
+
+            const couchbaseConfig: CouchbaseVectorStoreArgs = {
+                cluster: couchbaseClient,
+                bucketName: bucketName,
+                scopeName: scopeName,
+                collectionName: collectionName,
+                indexName: indexName,
+                textKey: textKey,
+                embeddingKey: embeddingKey
+            }
+
+            try {
+                if (!textKey || textKey === '') couchbaseConfig.textKey = 'text'
+                if (!embeddingKey || embeddingKey === '') couchbaseConfig.embeddingKey = 'embedding'
+
+                await CouchbaseVectorStore.fromDocuments(finalDocs, embeddings, couchbaseConfig)
+                return { numAdded: finalDocs.length, addedDocs: finalDocs }
+            } catch (e) {
+                throw new Error(e)
+            }
+        }
+    }
+
+    async init(nodeData: INodeData, _: string, options: ICommonObject): Promise<any> {
+        const credentialData = await getCredentialData(nodeData.credential ?? '', options)
+        const bucketName = nodeData.inputs?.bucketName as string
+        const scopeName = nodeData.inputs?.scopeName as string
+        const collectionName = nodeData.inputs?.collectionName as string
+        const indexName = nodeData.inputs?.indexName as string
+        let textKey = nodeData.inputs?.textKey as string
+        let embeddingKey = nodeData.inputs?.embeddingKey as string
+        const embeddings = nodeData.inputs?.embeddings as Embeddings
+        const couchbaseMetadataFilter = nodeData.inputs?.couchbaseMetadataFilter
+
+        let connectionString = getCredentialParam('connectionString', credentialData, nodeData)
+        let databaseUsername = getCredentialParam('username', credentialData, nodeData)
+        let databasePassword = getCredentialParam('password', credentialData, nodeData)
+        let metadatafilter
+
+        const couchbaseClient = await Cluster.connect(connectionString, {
+            username: databaseUsername,
+            password: databasePassword,
+            configProfile: 'wanDevelopment'
+        })
+
+        const couchbaseConfig: CouchbaseVectorStoreArgs = {
+            cluster: couchbaseClient,
+            bucketName: bucketName,
+            scopeName: scopeName,
+            collectionName: collectionName,
+            indexName: indexName,
+            textKey: textKey,
+            embeddingKey: embeddingKey
+        }
+
+        try {
+            if (!textKey || textKey === '') couchbaseConfig.textKey = 'text'
+            if (!embeddingKey || embeddingKey === '') couchbaseConfig.embeddingKey = 'embedding'
+
+            if (couchbaseMetadataFilter) {
+                metadatafilter = typeof couchbaseMetadataFilter === 'object' ? couchbaseMetadataFilter : JSON.parse(couchbaseMetadataFilter)
+            }
+
+            const vectorStore = await CouchbaseVectorStore.initialize(embeddings, couchbaseConfig)
+
+            return resolveVectorStoreOrRetriever(nodeData, vectorStore, metadatafilter)
+        } catch (e) {
+            throw new Error(e)
+        }
+    }
+}
+
+module.exports = { nodeClass: Couchbase_VectorStores }

packages/components/nodes/vectorstores/Couchbase/couchbase.svg

@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="2500" height="2500" preserveAspectRatio="xMidYMid" viewBox="0 0 256 256" id="couchbase"><path fill="#ED2226" d="M128 0C57.426 0 0 57.233 0 128c0 70.574 57.233 128 128 128 70.574 0 128-57.233 128-128S198.574 0 128 0zm86.429 150.429c0 7.734-4.447 14.502-13.148 16.048-15.082 2.707-46.792 4.254-73.281 4.254-26.49 0-58.2-1.547-73.281-4.254-8.7-1.546-13.148-8.314-13.148-16.048v-49.885c0-7.734 5.994-14.888 13.148-16.049 4.447-.773 14.888-1.546 23.01-1.546 3.093 0 5.606 2.32 5.606 5.994v34.997l44.858-.967 44.858.967V88.943c0-3.674 2.514-5.994 5.608-5.994 8.12 0 18.562.773 23.009 1.546 7.347 1.16 13.148 8.315 13.148 16.049-.387 16.435-.387 33.257-.387 49.885z"></path></svg>