server: introduce API for serving / loading / unloading multiple models (#17470)
* server: add model management and proxy * fix compile error * does this fix windows? * fix windows build * use subprocess.h, better logging * add test * fix windows * feat: Model/Router server architecture WIP * more stable * fix unsafe pointer * also allow terminate loading model * add is_active() * refactor: Architecture improvements * tmp apply upstream fix * address most problems * address thread safety issue * address review comment * add docs (first version) * address review comment * feat: Improved UX for model information, modality interactions etc * chore: update webui build output * refactor: Use only the message data `model` property for displaying model used info * chore: update webui build output * add --models-dir param * feat: New Model Selection UX WIP * chore: update webui build output * feat: Add auto-mic setting * feat: Attachments UX improvements * implement LRU * remove default model path * better --models-dir * add env for args * address review comments * fix compile * refactor: Chat Form Submit component * ad endpoint docs * Merge remote-tracking branch 'webui/allozaur/server_model_management_v1_2' into xsn/server_model_maagement_v1_2 Co-authored-by: Aleksander <aleksander.grygier@gmail.com> * feat: Add copy to clipboard to model name in model info dialog * feat: Model unavailable UI state for model selector * feat: Chat Form Actions UI logic improvements * feat: Auto-select model from last assistant response * chore: update webui build output * expose args and exit_code in API * add note * support extra_args on loading model * allow reusing args if auto_load * typo docs * oai-compat /models endpoint * cleaner * address review comments * feat: Use `model` property for displaying the `repo/model-name` naming format * refactor: Attachments data * chore: update webui build output * refactor: Enum imports * feat: Improve Model Selector responsiveness * chore: update webui build output * refactor: Cleanup * refactor: Cleanup * refactor: Formatters * chore: update webui build output * refactor: Copy To Clipboard Icon component * chore: update webui build output * refactor: Cleanup * chore: update webui build output * refactor: UI badges * chore: update webui build output * refactor: Cleanup * refactor: Cleanup * chore: update webui build output * add --models-allow-extra-args for security * nits * add stdin_file * fix merge * fix: Retrieve lost setting after resolving merge conflict * refactor: DatabaseStore -> DatabaseService * refactor: Database, Conversations & Chat services + stores architecture improvements (WIP) * refactor: Remove redundant settings * refactor: Multi-model business logic WIP * chore: update webui build output * feat: Switching models logic for ChatForm or when regenerating messges + modality detection logic * chore: update webui build output * fix: Add `untrack` inside chat processing info data logic to prevent infinite effect * fix: Regenerate * feat: Remove redundant settigns + rearrange * fix: Audio attachments * refactor: Icons * chore: update webui build output * feat: Model management and selection features WIP * chore: update webui build output * refactor: Improve server properties management * refactor: Icons * chore: update webui build output * feat: Improve model loading/unloading status updates * chore: update webui build output * refactor: Improve API header management via utility functions * remove support for extra args * set hf_repo/docker_repo as model alias when posible * refactor: Remove ConversationsService * refactor: Chat requests abort handling * refactor: Server store * tmp webui build * refactor: Model modality handling * chore: update webui build output * refactor: Processing state reactivity * fix: UI * refactor: Services/Stores syntax + logic improvements Refactors components to access stores directly instead of using exported getter functions. This change centralizes store access and logic, simplifying component code and improving maintainability by reducing the number of exported functions and promoting direct store interaction. Removes exported getter functions from `chat.svelte.ts`, `conversations.svelte.ts`, `models.svelte.ts` and `settings.svelte.ts`. * refactor: Architecture cleanup * feat: Improve statistic badges * feat: Condition available models based on modality + better model loading strategy & UX * docs: Architecture documentation * feat: Update logic for PDF as Image * add TODO for http client * refactor: Enhance model info and attachment handling * chore: update webui build output * refactor: Components naming * chore: update webui build output * refactor: Cleanup * refactor: DRY `getAttachmentDisplayItems` function + fix UI * chore: update webui build output * fix: Modality detection improvement for text-based PDF attachments * refactor: Cleanup * docs: Add info comment * refactor: Cleanup * re * refactor: Cleanup * refactor: Cleanup * feat: Attachment logic & UI improvements * refactor: Constants * feat: Improve UI sidebar background color * chore: update webui build output * refactor: Utils imports + move types to `app.d.ts` * test: Fix Storybook mocks * chore: update webui build output * test: Update Chat Form UI tests * refactor: Tooltip Provider from core layout * refactor: Tests to separate location * decouple server_models from server_routes * test: Move demo test to tests/server * refactor: Remove redundant method * chore: update webui build output * also route anthropic endpoints * fix duplicated arg * fix invalid ptr to shutdown_handler * server : minor * rm unused fn * add ?autoload=true|false query param * refactor: Remove redundant code * docs: Update README documentations + architecture & data flow diagrams * fix: Disable autoload on calling server props for the model * chore: update webui build output * fix ubuntu build * fix: Model status reactivity * fix: Modality detection for MODEL mode * chore: update webui build output --------- Co-authored-by: Aleksander Grygier <aleksander.grygier@gmail.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Xuan-Son Nguyen
@@ -3,8 +3,7 @@
|
||||
* Ensures only compatible file types are processed based on model capabilities
|
||||
*/
|
||||
|
||||
import { getFileTypeCategory } from '$lib/utils/file-type';
|
||||
import { supportsVision, supportsAudio } from '$lib/stores/server.svelte';
|
||||
import { getFileTypeCategory } from '$lib/utils';
|
||||
import {
|
||||
FileExtensionAudio,
|
||||
FileExtensionImage,
|
||||
@@ -15,15 +14,26 @@ import {
|
||||
MimeTypeApplication,
|
||||
MimeTypeText,
|
||||
FileTypeCategory
|
||||
} from '$lib/enums/files';
|
||||
} from '$lib/enums';
|
||||
|
||||
/** Modality capabilities for file validation */
|
||||
export interface ModalityCapabilities {
|
||||
hasVision: boolean;
|
||||
hasAudio: boolean;
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if a file type is supported by the current model's modalities
|
||||
* Check if a file type is supported by the given modalities
|
||||
* @param filename - The filename to check
|
||||
* @param mimeType - The MIME type of the file
|
||||
* @returns true if the file type is supported by the current model
|
||||
* @param capabilities - The modality capabilities to check against
|
||||
* @returns true if the file type is supported
|
||||
*/
|
||||
export function isFileTypeSupportedByModel(filename: string, mimeType?: string): boolean {
|
||||
export function isFileTypeSupportedByModel(
|
||||
filename: string,
|
||||
mimeType: string | undefined,
|
||||
capabilities: ModalityCapabilities
|
||||
): boolean {
|
||||
const category = mimeType ? getFileTypeCategory(mimeType) : null;
|
||||
|
||||
// If we can't determine the category from MIME type, fall back to general support check
|
||||
@@ -44,11 +54,11 @@ export function isFileTypeSupportedByModel(filename: string, mimeType?: string):
|
||||
|
||||
case FileTypeCategory.IMAGE:
|
||||
// Images require vision support
|
||||
return supportsVision();
|
||||
return capabilities.hasVision;
|
||||
|
||||
case FileTypeCategory.AUDIO:
|
||||
// Audio files require audio support
|
||||
return supportsAudio();
|
||||
return capabilities.hasAudio;
|
||||
|
||||
default:
|
||||
// Unknown categories - be conservative and allow
|
||||
@@ -59,9 +69,13 @@ export function isFileTypeSupportedByModel(filename: string, mimeType?: string):
|
||||
/**
|
||||
* Filter files based on model modalities and return supported/unsupported lists
|
||||
* @param files - Array of files to filter
|
||||
* @param capabilities - The modality capabilities to check against
|
||||
* @returns Object with supportedFiles and unsupportedFiles arrays
|
||||
*/
|
||||
export function filterFilesByModalities(files: File[]): {
|
||||
export function filterFilesByModalities(
|
||||
files: File[],
|
||||
capabilities: ModalityCapabilities
|
||||
): {
|
||||
supportedFiles: File[];
|
||||
unsupportedFiles: File[];
|
||||
modalityReasons: Record<string, string>;
|
||||
@@ -70,8 +84,7 @@ export function filterFilesByModalities(files: File[]): {
|
||||
const unsupportedFiles: File[] = [];
|
||||
const modalityReasons: Record<string, string> = {};
|
||||
|
||||
const hasVision = supportsVision();
|
||||
const hasAudio = supportsAudio();
|
||||
const { hasVision, hasAudio } = capabilities;
|
||||
|
||||
for (const file of files) {
|
||||
const category = getFileTypeCategory(file.type);
|
||||
@@ -119,16 +132,17 @@ export function filterFilesByModalities(files: File[]): {
|
||||
* Generate a user-friendly error message for unsupported files
|
||||
* @param unsupportedFiles - Array of unsupported files
|
||||
* @param modalityReasons - Reasons why files are unsupported
|
||||
* @param capabilities - The modality capabilities to check against
|
||||
* @returns Formatted error message
|
||||
*/
|
||||
export function generateModalityErrorMessage(
|
||||
unsupportedFiles: File[],
|
||||
modalityReasons: Record<string, string>
|
||||
modalityReasons: Record<string, string>,
|
||||
capabilities: ModalityCapabilities
|
||||
): string {
|
||||
if (unsupportedFiles.length === 0) return '';
|
||||
|
||||
const hasVision = supportsVision();
|
||||
const hasAudio = supportsAudio();
|
||||
const { hasVision, hasAudio } = capabilities;
|
||||
|
||||
let message = '';
|
||||
|
||||
@@ -152,12 +166,12 @@ export function generateModalityErrorMessage(
|
||||
}
|
||||
|
||||
/**
|
||||
* Generate file input accept string based on current model modalities
|
||||
* Generate file input accept string based on model modalities
|
||||
* @param capabilities - The modality capabilities to check against
|
||||
* @returns Accept string for HTML file input element
|
||||
*/
|
||||
export function generateModalityAwareAcceptString(): string {
|
||||
const hasVision = supportsVision();
|
||||
const hasAudio = supportsAudio();
|
||||
export function generateModalityAwareAcceptString(capabilities: ModalityCapabilities): string {
|
||||
const { hasVision, hasAudio } = capabilities;
|
||||
|
||||
const acceptedExtensions: string[] = [];
|
||||
const acceptedMimeTypes: string[] = [];
|
||||
|
||||
Reference in New Issue
Block a user