From fb02632f4b682b8b0ee2d1ec1a79330118318eaa Mon Sep 17 00:00:00 2001
From: vinodkiran <vinodkiran@usa.net>
Date: Fri, 22 Dec 2023 12:12:16 +0530
Subject: [PATCH] Compression Retriever - Embeddings Filter

---
 .../EmbeddingsFilterRetriever.ts              | 97 +++++++++++++++++++
 .../compressionRetriever.svg                  |  7 ++
 2 files changed, 104 insertions(+)
 create mode 100644 packages/components/nodes/retrievers/EmbeddingsFilterRetriever/EmbeddingsFilterRetriever.ts
 create mode 100644 packages/components/nodes/retrievers/EmbeddingsFilterRetriever/compressionRetriever.svg

diff --git a/packages/components/nodes/retrievers/EmbeddingsFilterRetriever/EmbeddingsFilterRetriever.ts b/packages/components/nodes/retrievers/EmbeddingsFilterRetriever/EmbeddingsFilterRetriever.ts
new file mode 100644
index 00000000..d373704c
--- /dev/null
+++ b/packages/components/nodes/retrievers/EmbeddingsFilterRetriever/EmbeddingsFilterRetriever.ts
@@ -0,0 +1,97 @@
+import { INode, INodeData, INodeOutputsValue, INodeParams } from '../../../src/Interface'
+import { BaseRetriever } from 'langchain/schema/retriever'
+import { Embeddings } from 'langchain/embeddings/base'
+import { ContextualCompressionRetriever } from 'langchain/retrievers/contextual_compression'
+import { EmbeddingsFilter } from 'langchain/retrievers/document_compressors/embeddings_filter'
+
+class EmbeddingsFilterRetriever_Retrievers implements INode {
+    label: string
+    name: string
+    version: number
+    description: string
+    type: string
+    icon: string
+    category: string
+    baseClasses: string[]
+    inputs: INodeParams[]
+    outputs: INodeOutputsValue[]
+    badge: string
+
+    constructor() {
+        this.label = 'Embeddings Filter Retriever'
+        this.name = 'embeddingsFilterRetriever'
+        this.version = 1.0
+        this.type = 'EmbeddingsFilterRetriever'
+        this.icon = 'compressionRetriever.svg'
+        this.category = 'Retrievers'
+        this.badge = 'NEW'
+        this.description = 'A document compressor that uses embeddings to drop documents unrelated to the query'
+        this.baseClasses = [this.type, 'BaseRetriever']
+        this.inputs = [
+            {
+                label: 'Base Retriever',
+                name: 'baseRetriever',
+                type: 'VectorStoreRetriever'
+            },
+            {
+                label: 'Embeddings',
+                name: 'embeddings',
+                type: 'Embeddings',
+                optional: false
+            },
+            {
+                label: 'Similarity Threshold',
+                name: 'similarityThreshold',
+                description:
+                    'Threshold for determining when two documents are similar enough to be considered redundant. Must be specified if `k` is not set',
+                type: 'number',
+                default: 0.8,
+                step: 0.1,
+                optional: true
+            },
+            {
+                label: 'K',
+                name: 'k',
+                description:
+                    'The number of relevant documents to return. Can be explicitly set to undefined, in which case similarity_threshold must be specified. Defaults to 20',
+                type: 'number',
+                default: 20,
+                step: 1,
+                optional: true,
+                additionalParams: true
+            }
+        ]
+    }
+
+    async init(nodeData: INodeData): Promise<any> {
+        const baseRetriever = nodeData.inputs?.baseRetriever as BaseRetriever
+        const embeddings = nodeData.inputs?.embeddings as Embeddings
+        const similarityThreshold = nodeData.inputs?.similarityThreshold as string
+        const k = nodeData.inputs?.k as string
+
+        if (k === undefined && similarityThreshold === undefined) {
+            throw new Error(`Must specify one of "k" or "similarity_threshold".`)
+        }
+
+        let similarityThresholdNumber = 0.8
+        if (similarityThreshold) {
+            similarityThresholdNumber = parseFloat(similarityThreshold)
+        }
+        let kNumber = 0.8
+        if (k) {
+            kNumber = parseFloat(k)
+        }
+        const baseCompressor = new EmbeddingsFilter({
+            embeddings: embeddings,
+            similarityThreshold: similarityThresholdNumber,
+            k: kNumber
+        })
+
+        return new ContextualCompressionRetriever({
+            baseCompressor,
+            baseRetriever: baseRetriever
+        })
+    }
+}
+
+module.exports = { nodeClass: EmbeddingsFilterRetriever_Retrievers }
diff --git a/packages/components/nodes/retrievers/EmbeddingsFilterRetriever/compressionRetriever.svg b/packages/components/nodes/retrievers/EmbeddingsFilterRetriever/compressionRetriever.svg
new file mode 100644
index 00000000..23c52d25
--- /dev/null
+++ b/packages/components/nodes/retrievers/EmbeddingsFilterRetriever/compressionRetriever.svg
@@ -0,0 +1,7 @@
+<svg xmlns="http://www.w3.org/2000/svg" class="icon icon-tabler icon-tabler-chart-bar" width="24" height="24" viewBox="0 0 24 24" stroke-width="2" stroke="currentColor" fill="none" stroke-linecap="round" stroke-linejoin="round">
+   <path stroke="none" d="M0 0h24v24H0z" fill="none"/>
+   <path d="M3 12m0 1a1 1 0 0 1 1 -1h4a1 1 0 0 1 1 1v6a1 1 0 0 1 -1 1h-4a1 1 0 0 1 -1 -1z" />
+   <path d="M9 8m0 1a1 1 0 0 1 1 -1h4a1 1 0 0 1 1 1v10a1 1 0 0 1 -1 1h-4a1 1 0 0 1 -1 -1z" />
+   <path d="M15 4m0 1a1 1 0 0 1 1 -1h4a1 1 0 0 1 1 1v14a1 1 0 0 1 -1 1h-4a1 1 0 0 1 -1 -1z" />
+   <path d="M4 20l14 0" />
+</svg>
\ No newline at end of file