Skip to content

feat: aiDAPTIV™ RAG shared-prefix KV-cache reuse #250

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
TingyinKuo-Phison wants to merge 3 commits into
base: 3.1.2-beta-test6
Choose a base branch
from
Open

feat: aiDAPTIV™ RAG shared-prefix KV-cache reuse #250

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
298ec61
feat: aiDAPTIV™ RAG shared-prefix KV-cache reuse (Approach A)
TingyinKuo-Phison Jun 30, 2026
696b795
feat: refine aiDAPTIV™ preset name and descriptions
YuchengKuo-Phison Jul 6, 2026
4e8636b
Merge pull request #1 from YuchengKuo-Phison/feature/aidaptiv-rag-kvc…
TingyinKuo-Phison Jul 6, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
31 changes: 23 additions & 8 deletions WebUI/electron/main.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -101,7 +101,12 @@ import { externalResourcesDir, getMediaDir } from './util.ts'
import { packagedResourcesRoot } from './aipgRoot.ts'
import { loadDemoProfile, type DemoProfile } from './demoProfile.ts'
import type { ModelPaths } from '@/assets/js/store/models.ts'
import type { IndexedDocument, EmbedInquiry } from '@/assets/js/store/textInference.ts'
import type {
IndexedDocument,
EmbedInquiry,
WarmupRequest,
PhisonKmIngestConfig,
} from '@/assets/js/store/textInference.ts'
import { BackendServiceName } from '@/assets/js/store/backendServices.ts'
import {
detectGpuHardwareDevices,
Expand Down Expand Up @@ -1275,13 +1280,15 @@ function initEventHandle() {

ipcMain.handle('getPlatform', () => process.platform)

ipcMain.handle('addDocumentToRAGList', (_event, document: IndexedDocument) => {
return handleUtilityFunction<IndexedDocument, IndexedDocument>(
'addDocumentToRAGList',
langchainChild,
document,
)
})
ipcMain.handle(
'addDocumentToRAGList',
(_event, document: IndexedDocument, phisonKmConfig?: PhisonKmIngestConfig) => {
return handleUtilityFunction<
{ document: IndexedDocument; phisonKmConfig?: PhisonKmIngestConfig },
IndexedDocument
>('addDocumentToRAGList', langchainChild, { document, phisonKmConfig })
},
)

ipcMain.handle('embedInputUsingRag', (_event, embedInquiry: EmbedInquiry) => {
return handleUtilityFunction<EmbedInquiry, KVObject>(
Expand All @@ -1291,6 +1298,14 @@ function initEventHandle() {
)
})

ipcMain.handle('warmupKVCacheForDocument', (_event, request: WarmupRequest) => {
return handleUtilityFunction<WarmupRequest, { success: boolean }>(
'warmupKVCacheForDocument',
langchainChild,
request,
)
})

ipcMain.on('openDevTools', () => {
win?.webContents.openDevTools({ mode: 'detach', activate: true })
})
Expand Down
12 changes: 10 additions & 2 deletions WebUI/electron/preload.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,12 @@ import { contextBridge, ipcRenderer, webUtils } from 'electron'
import pkg from '../package.json'
import { LocalSettings } from './main'
import { ModelPaths } from '@/assets/js/store/models'
import { EmbedInquiry, IndexedDocument } from '@/assets/js/store/textInference'
import {
EmbedInquiry,
IndexedDocument,
WarmupRequest,
PhisonKmIngestConfig,
} from '@/assets/js/store/textInference'

contextBridge.exposeInMainWorld('envVars', {
platformTitle: import.meta.env.VITE_PLATFORM_TITLE,
Expand Down Expand Up @@ -80,9 +85,12 @@ contextBridge.exposeInMainWorld('electronAPI', {
callback(seriveName, normalExit),
),
existsPath: (path: string) => ipcRenderer.invoke('existsPath', path),
addDocumentToRAGList: (doc: IndexedDocument) => ipcRenderer.invoke('addDocumentToRAGList', doc),
addDocumentToRAGList: (doc: IndexedDocument, phisonKmConfig?: PhisonKmIngestConfig) =>
ipcRenderer.invoke('addDocumentToRAGList', doc, phisonKmConfig),
embedInputUsingRag: (embedInquiry: EmbedInquiry) =>
ipcRenderer.invoke('embedInputUsingRag', embedInquiry),
warmupKVCacheForDocument: (request: WarmupRequest) =>
ipcRenderer.invoke('warmupKVCacheForDocument', request),
getEmbeddingServerUrl: (serviceName: string) =>
ipcRenderer.invoke('getEmbeddingServerUrl', serviceName),
getInitSetting: () => ipcRenderer.invoke('getInitSetting'),
Expand Down
Loading