Sultan
/
Flowise
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge pull request #774 from vectara/sentence-config 

Add sentence config option to Vectara
This commit is contained in:
Henry Heng 2023-08-17 10:20:09 +01:00 committed by GitHub
parent e998b6a984 9ab23889b6
commit 5a8db9a534
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 248 additions and 196 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
packages/components/nodes/vectorstores/Vectara_Existing/Vectara_Existing.ts
View File

@ -1,6 +1,6 @@
import { ICommonObject, INode, INodeData, INodeOutputsValue, INodeParams } from '../../../src/Interface'
import { getBaseClasses, getCredentialData, getCredentialParam } from '../../../src/utils'
import { VectaraStore, VectaraLibArgs, VectaraFilter } from 'langchain/vectorstores/vectara'
import { VectaraStore, VectaraLibArgs, VectaraFilter, VectaraContextConfig } from 'langchain/vectorstores/vectara'
class VectaraExisting_VectorStores implements INode {
label: string
@ -40,9 +40,27 @@ class VectaraExisting_VectorStores implements INode {
additionalParams: true,
optional: true
},
{
label: 'Sentences Before',
name: 'sentencesBefore',
description: 'Number of sentences to fetch before the matched sentence. Defaults to 2.',
type: 'number',
additionalParams: true,
optional: true
},
{
label: 'Sentences After',
name: 'sentencesAfter',
description: 'Number of sentences to fetch after the matched sentence. Defaults to 2.',
type: 'number',
additionalParams: true,
optional: true
},
{
label: 'Lambda',
name: 'lambda',
description:
'Improves retrieval accuracy by adjusting the balance (from 0 to 1) between neural search and keyword-based search factors.',
type: 'number',
additionalParams: true,
optional: true
@ -77,6 +95,8 @@ class VectaraExisting_VectorStores implements INode {
const corpusId = getCredentialParam('corpusID', credentialData, nodeData)
const vectaraMetadataFilter = nodeData.inputs?.filter as string
const sentencesBefore = nodeData.inputs?.sentencesBefore as number
const sentencesAfter = nodeData.inputs?.sentencesAfter as number
const lambda = nodeData.inputs?.lambda as number
const output = nodeData.outputs?.output as string
const topK = nodeData.inputs?.topK as string
@ -92,6 +112,11 @@ class VectaraExisting_VectorStores implements INode {
if (vectaraMetadataFilter) vectaraFilter.filter = vectaraMetadataFilter
if (lambda) vectaraFilter.lambda = lambda
const vectaraContextConfig: VectaraContextConfig = {}
if (sentencesBefore) vectaraContextConfig.sentencesBefore = sentencesBefore
if (sentencesAfter) vectaraContextConfig.sentencesAfter = sentencesAfter
vectaraFilter.contextConfig = vectaraContextConfig
const vectorStore = new VectaraStore(vectaraArgs)
if (output === 'retriever') {

27
packages/components/nodes/vectorstores/Vectara_Upsert/Vectara_Upsert.ts
View File

@ -1,7 +1,7 @@
import { ICommonObject, INode, INodeData, INodeOutputsValue, INodeParams } from '../../../src/Interface'
import { Embeddings } from 'langchain/embeddings/base'
import { getBaseClasses, getCredentialData, getCredentialParam } from '../../../src/utils'
import { VectaraStore, VectaraLibArgs, VectaraFilter } from 'langchain/vectorstores/vectara'
import { VectaraStore, VectaraLibArgs, VectaraFilter, VectaraContextConfig } from 'langchain/vectorstores/vectara'
import { Document } from 'langchain/document'
import { flatten } from 'lodash'
@ -49,9 +49,27 @@ class VectaraUpsert_VectorStores implements INode {
additionalParams: true,
optional: true
},
{
label: 'Sentences Before',
name: 'sentencesBefore',
description: 'Number of sentences to fetch before the matched sentence. Defaults to 2.',
type: 'number',
additionalParams: true,
optional: true
},
{
label: 'Sentences After',
name: 'sentencesAfter',
description: 'Number of sentences to fetch after the matched sentence. Defaults to 2.',
type: 'number',
additionalParams: true,
optional: true
},
{
label: 'Lambda',
name: 'lambda',
description:
'Improves retrieval accuracy by adjusting the balance (from 0 to 1) between neural search and keyword-based search factors.',
type: 'number',
additionalParams: true,
optional: true
@ -88,6 +106,8 @@ class VectaraUpsert_VectorStores implements INode {
const docs = nodeData.inputs?.document as Document[]
const embeddings = {} as Embeddings
const vectaraMetadataFilter = nodeData.inputs?.filter as string
const sentencesBefore = nodeData.inputs?.sentencesBefore as number
const sentencesAfter = nodeData.inputs?.sentencesAfter as number
const lambda = nodeData.inputs?.lambda as number
const output = nodeData.outputs?.output as string
const topK = nodeData.inputs?.topK as string
@ -103,6 +123,11 @@ class VectaraUpsert_VectorStores implements INode {
if (vectaraMetadataFilter) vectaraFilter.filter = vectaraMetadataFilter
if (lambda) vectaraFilter.lambda = lambda
const vectaraContextConfig: VectaraContextConfig = {}
if (sentencesBefore) vectaraContextConfig.sentencesBefore = sentencesBefore
if (sentencesAfter) vectaraContextConfig.sentencesAfter = sentencesAfter
vectaraFilter.contextConfig = vectaraContextConfig
const flattenDocs = docs && docs.length ? flatten(docs) : []
const finalDocs = []
for (let i = 0; i < flattenDocs.length; i += 1) {

2
packages/components/package.json
View File

@ -40,7 +40,7 @@
"google-auth-library": "^9.0.0",
"graphql": "^16.6.0",
"html-to-text": "^9.0.5",
"langchain": "^0.0.122",
"langchain": "^0.0.126",
"linkifyjs": "^4.1.1",
"mammoth": "^1.5.1",
"moment": "^2.29.3",

388
packages/server/marketplaces/chatflows/Vectara LLM Chain Upload.json
View File

@ -1,186 +1,11 @@
{
"description": "A simple LLM chain that uses Vectara to enable conversations with uploaded documents",
"nodes": [
{
"width": 300,
"height": 408,
"id": "vectaraUpsert_0",
"position": { "x": 438, "y": 214 },
"type": "customNode",
"data": {
"id": "vectaraUpsert_0",
"label": "Vectara Upsert Document",
"version": 1,
"name": "vectaraUpsert",
"type": "Vectara",
"baseClasses": ["Vectara", "VectorStoreRetriever", "BaseRetriever"],
"category": "Vector Stores",
"description": "Upsert documents to Vectara",
"inputParams": [
{
"label": "Connect Credential",
"name": "credential",
"type": "credential",
"credentialNames": ["vectaraApi"],
"id": "vectaraUpsert_0-input-credential-credential"
},
{
"label": "Filter",
"name": "filter",
"type": "json",
"additionalParams": true,
"optional": true,
"id": "vectaraUpsert_0-input-filter-json"
},
{
"label": "Lambda",
"name": "lambda",
"type": "number",
"additionalParams": true,
"optional": true,
"id": "vectaraUpsert_0-input-lambda-number"
},
{
"label": "Top K",
"name": "topK",
"description": "Number of top results to fetch. Defaults to 4",
"placeholder": "4",
"type": "number",
"additionalParams": true,
"optional": true,
"id": "vectaraUpsert_0-input-topK-number"
}
],
"inputAnchors": [
{
"label": "Document",
"name": "document",
"type": "Document",
"list": true,
"id": "vectaraUpsert_0-input-document-Document"
}
],
"inputs": {
"document": ["{{pdfFile_0.data.instance}}"],
"filter": "",
"lambda": "",
"topK": ""
},
"outputAnchors": [
{
"name": "output",
"label": "Output",
"type": "options",
"options": [
{
"id": "vectaraUpsert_0-output-retriever-Vectara|VectorStoreRetriever|BaseRetriever",
"name": "retriever",
"label": "Vectara Retriever",
"type": "Vectara | VectorStoreRetriever | BaseRetriever"
},
{
"id": "vectaraUpsert_0-output-vectorStore-Vectara|VectorStore",
"name": "vectorStore",
"label": "Vectara Vector Store",
"type": "Vectara | VectorStore"
}
],
"default": "retriever"
}
],
"outputs": { "output": "retriever" },
"selected": false
},
"selected": false,
"dragging": false,
"positionAbsolute": { "x": 438, "y": 214 }
},
{
"width": 300,
"height": 509,
"id": "pdfFile_0",
"position": { "x": 68.3013317598369, "y": 199.60454731299677 },
"type": "customNode",
"data": {
"id": "pdfFile_0",
"label": "Pdf File",
"version": 1,
"name": "pdfFile",
"type": "Document",
"baseClasses": ["Document"],
"category": "Document Loaders",
"description": "Load data from PDF files",
"inputParams": [
{
"label": "Pdf File",
"name": "pdfFile",
"type": "file",
"fileType": ".pdf",
"id": "pdfFile_0-input-pdfFile-file"
},
{
"label": "Usage",
"name": "usage",
"type": "options",
"options": [
{ "label": "One document per page", "name": "perPage" },
{ "label": "One document per file", "name": "perFile" }
],
"default": "perPage",
"id": "pdfFile_0-input-usage-options"
},
{
"label": "Use Legacy Build",
"name": "legacyBuild",
"type": "boolean",
"optional": true,
"additionalParams": true,
"id": "pdfFile_0-input-legacyBuild-boolean"
},
{
"label": "Metadata",
"name": "metadata",
"type": "json",
"optional": true,
"additionalParams": true,
"id": "pdfFile_0-input-metadata-json"
}
],
"inputAnchors": [
{
"label": "Text Splitter",
"name": "textSplitter",
"type": "TextSplitter",
"optional": true,
"id": "pdfFile_0-input-textSplitter-TextSplitter"
}
],
"inputs": {
"textSplitter": "",
"usage": "perPage",
"legacyBuild": "",
"metadata": ""
},
"outputAnchors": [
{
"id": "pdfFile_0-output-pdfFile-Document",
"name": "pdfFile",
"label": "Document",
"type": "Document"
}
],
"outputs": {},
"selected": false
},
"selected": false,
"positionAbsolute": { "x": 68.3013317598369, "y": 199.60454731299677 },
"dragging": false
},
{
"width": 300,
"height": 525,
"id": "chatOpenAI_0",
"position": { "x": 804.3889791707068, "y": 195.11620799951592 },
"position": { "x": 514.1088940275924, "y": 199.574479681537 },
"type": "customNode",
"data": {
"id": "chatOpenAI_0",
@ -211,10 +36,7 @@
{ "label": "gpt-3.5-turbo", "name": "gpt-3.5-turbo" },
{ "label": "gpt-3.5-turbo-0613", "name": "gpt-3.5-turbo-0613" },
{ "label": "gpt-3.5-turbo-16k", "name": "gpt-3.5-turbo-16k" },
{
"label": "gpt-3.5-turbo-16k-0613",
"name": "gpt-3.5-turbo-16k-0613"
}
{ "label": "gpt-3.5-turbo-16k-0613", "name": "gpt-3.5-turbo-16k-0613" }
],
"default": "gpt-3.5-turbo",
"optional": true,
@ -286,7 +108,7 @@
"inputAnchors": [],
"inputs": {
"modelName": "gpt-3.5-turbo",
"temperature": "0.2",
"temperature": "0.5",
"maxTokens": "",
"topP": "",
"frequencyPenalty": "",
@ -306,14 +128,14 @@
"selected": false
},
"selected": false,
"positionAbsolute": { "x": 804.3889791707068, "y": 195.11620799951592 },
"positionAbsolute": { "x": 514.1088940275924, "y": 199.574479681537 },
"dragging": false
},
{
"width": 300,
"height": 481,
"id": "conversationalRetrievalQAChain_0",
"position": { "x": 1160.4877473512795, "y": 259.2799138505109 },
"position": { "x": 900.4793407261002, "y": 205.9476004518217 },
"type": "customNode",
"data": {
"id": "conversationalRetrievalQAChain_0",
@ -410,11 +232,200 @@
"selected": false
},
"selected": false,
"positionAbsolute": { "x": 1160.4877473512795, "y": 259.2799138505109 },
"positionAbsolute": { "x": 900.4793407261002, "y": 205.9476004518217 },
"dragging": false
},
{
"width": 300,
"height": 509,
"id": "pdfFile_0",
"position": { "x": -210.44158723479913, "y": 236.6627524951051 },
"type": "customNode",
"data": {
"id": "pdfFile_0",
"label": "Pdf File",
"version": 1,
"name": "pdfFile",
"type": "Document",
"baseClasses": ["Document"],
"category": "Document Loaders",
"description": "Load data from PDF files",
"inputParams": [
{ "label": "Pdf File", "name": "pdfFile", "type": "file", "fileType": ".pdf", "id": "pdfFile_0-input-pdfFile-file" },
{
"label": "Usage",
"name": "usage",
"type": "options",
"options": [
{ "label": "One document per page", "name": "perPage" },
{ "label": "One document per file", "name": "perFile" }
],
"default": "perPage",
"id": "pdfFile_0-input-usage-options"
},
{
"label": "Use Legacy Build",
"name": "legacyBuild",
"type": "boolean",
"optional": true,
"additionalParams": true,
"id": "pdfFile_0-input-legacyBuild-boolean"
},
{
"label": "Metadata",
"name": "metadata",
"type": "json",
"optional": true,
"additionalParams": true,
"id": "pdfFile_0-input-metadata-json"
}
],
"inputAnchors": [
{
"label": "Text Splitter",
"name": "textSplitter",
"type": "TextSplitter",
"optional": true,
"id": "pdfFile_0-input-textSplitter-TextSplitter"
}
],
"inputs": { "textSplitter": "", "usage": "perPage", "legacyBuild": "", "metadata": "" },
"outputAnchors": [
{ "id": "pdfFile_0-output-pdfFile-Document", "name": "pdfFile", "label": "Document", "type": "Document" }
],
"outputs": {},
"selected": false
},
"selected": false,
"positionAbsolute": { "x": -210.44158723479913, "y": 236.6627524951051 },
"dragging": false
},
{
"width": 300,
"height": 408,
"id": "vectaraUpsert_0",
"position": { "x": 172.06946164914868, "y": 373.11406233089934 },
"type": "customNode",
"data": {
"id": "vectaraUpsert_0",
"label": "Vectara Upsert Document",
"version": 1,
"name": "vectaraUpsert",
"type": "Vectara",
"baseClasses": ["Vectara", "VectorStoreRetriever", "BaseRetriever"],
"category": "Vector Stores",
"description": "Upsert documents to Vectara",
"inputParams": [
{
"label": "Connect Credential",
"name": "credential",
"type": "credential",
"credentialNames": ["vectaraApi"],
"id": "vectaraUpsert_0-input-credential-credential"
},
{
"label": "Vectara Metadata Filter",
"name": "filter",
"description": "Filter to apply to Vectara metadata. Refer to the <a target=\"_blank\" href=\"https://docs.flowiseai.com/vector-stores/vectara\">documentation</a> on how to use Vectara filters with Flowise.",
"type": "string",
"additionalParams": true,
"optional": true,
"id": "vectaraUpsert_0-input-filter-string"
},
{
"label": "Sentences Before",
"name": "sentencesBefore",
"description": "Number of sentences to fetch before the matched sentence. Defaults to 2.",
"type": "number",
"additionalParams": true,
"optional": true,
"id": "vectaraUpsert_0-input-sentencesBefore-number"
},
{
"label": "Sentences After",
"name": "sentencesAfter",
"description": "Number of sentences to fetch after the matched sentence. Defaults to 2.",
"type": "number",
"additionalParams": true,
"optional": true,
"id": "vectaraUpsert_0-input-sentencesAfter-number"
},
{
"label": "Lambda",
"name": "lambda",
"description": "Improves retrieval accuracy by adjusting the balance (from 0 to 1) between neural search and keyword-based search factors.",
"type": "number",
"additionalParams": true,
"optional": true,
"id": "vectaraUpsert_0-input-lambda-number"
},
{
"label": "Top K",
"name": "topK",
"description": "Number of top results to fetch. Defaults to 4",
"placeholder": "4",
"type": "number",
"additionalParams": true,
"optional": true,
"id": "vectaraUpsert_0-input-topK-number"
}
],
"inputAnchors": [
{
"label": "Document",
"name": "document",
"type": "Document",
"list": true,
"id": "vectaraUpsert_0-input-document-Document"
}
],
"inputs": {
"document": ["{{pdfFile_0.data.instance}}"],
"filter": "",
"sentencesBefore": "",
"sentencesAfter": "",
"lambda": "",
"topK": ""
},
"outputAnchors": [
{
"name": "output",
"label": "Output",
"type": "options",
"options": [
{
"id": "vectaraUpsert_0-output-retriever-Vectara|VectorStoreRetriever|BaseRetriever",
"name": "retriever",
"label": "Vectara Retriever",
"type": "Vectara | VectorStoreRetriever | BaseRetriever"
},
{
"id": "vectaraUpsert_0-output-vectorStore-Vectara|VectorStore",
"name": "vectorStore",
"label": "Vectara Vector Store",
"type": "Vectara | VectorStore"
}
],
"default": "retriever"
}
],
"outputs": { "output": "retriever" },
"selected": false
},
"positionAbsolute": { "x": 172.06946164914868, "y": 373.11406233089934 },
"selected": false
}
],
"edges": [
{
"source": "chatOpenAI_0",
"sourceHandle": "chatOpenAI_0-output-chatOpenAI-ChatOpenAI|BaseChatModel|BaseLanguageModel",
"target": "conversationalRetrievalQAChain_0",
"targetHandle": "conversationalRetrievalQAChain_0-input-model-BaseLanguageModel",
"type": "buttonedge",
"id": "chatOpenAI_0-chatOpenAI_0-output-chatOpenAI-ChatOpenAI|BaseChatModel|BaseLanguageModel-conversationalRetrievalQAChain_0-conversationalRetrievalQAChain_0-input-model-BaseLanguageModel",
"data": { "label": "" }
},
{
"source": "pdfFile_0",
"sourceHandle": "pdfFile_0-output-pdfFile-Document",
@ -432,15 +443,6 @@
"type": "buttonedge",
"id": "vectaraUpsert_0-vectaraUpsert_0-output-retriever-Vectara|VectorStoreRetriever|BaseRetriever-conversationalRetrievalQAChain_0-conversationalRetrievalQAChain_0-input-vectorStoreRetriever-BaseRetriever",
"data": { "label": "" }
},
{
"source": "chatOpenAI_0",
"sourceHandle": "chatOpenAI_0-output-chatOpenAI-ChatOpenAI|BaseChatModel|BaseLanguageModel",
"target": "conversationalRetrievalQAChain_0",
"targetHandle": "conversationalRetrievalQAChain_0-input-model-BaseLanguageModel",
"type": "buttonedge",
"id": "chatOpenAI_0-chatOpenAI_0-output-chatOpenAI-ChatOpenAI|BaseChatModel|BaseLanguageModel-conversationalRetrievalQAChain_0-conversationalRetrievalQAChain_0-input-model-BaseLanguageModel",
"data": { "label": "" }
}
]
}