mirror of
https://github.com/Memo-2023/mana-monorepo.git
synced 2026-05-23 19:46:42 +02:00
feat(gpu-server): complete GPU server setup with AI services, monitoring, and public access
- Set up 5 AI services on Windows GPU server (RTX 3090): - mana-llm (Port 3025): OpenAI-compatible LLM gateway via Ollama - mana-stt (Port 3020): WhisperX with word timestamps + speaker diarization - mana-tts (Port 3022): Kokoro (EN) + Edge TTS (DE) + Piper (local DE) - mana-image-gen (Port 3023): FLUX.2 klein 4B image generation - Ollama (Port 11434): gemma3:4b/12b, qwen2.5-coder:14b, nomic-embed-text - Add @manacore/shared-gpu TypeScript client package with SttClient, TtsClient, ImageClient - Add CUDA-compatible whisper_service using faster-whisper for Windows - Configure public access via Cloudflare Tunnel (gpu-llm/stt/tts/img.mana.how) - Add Loki log aggregator (Docker on Mac Mini) + log shipper on GPU server - Add GPU scrape targets to Prometheus/VictoriaMetrics config - Add Grafana Loki datasource for GPU service logs - Add health check with auto-restart, log rotation, and log shipping - Document complete setup: Always-On config, troubleshooting, architecture Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
parent
7754cf6e00
commit
16e0d99c5a
13 changed files with 1245 additions and 7 deletions
72
packages/shared-gpu/src/image-client.ts
Normal file
72
packages/shared-gpu/src/image-client.ts
Normal file
|
|
@ -0,0 +1,72 @@
|
|||
import type {
|
||||
GenerateImageOptions,
|
||||
GenerateImageResult,
|
||||
ImageGenHealthResponse,
|
||||
GpuServiceConfig,
|
||||
} from './types';
|
||||
import { resolveServiceUrl } from './resolve-url';
|
||||
|
||||
export class ImageClient {
|
||||
private baseUrl: string;
|
||||
private timeout: number;
|
||||
|
||||
constructor(config: GpuServiceConfig) {
|
||||
this.baseUrl = resolveServiceUrl(config, 'image');
|
||||
this.timeout = config.timeout ?? 120_000;
|
||||
}
|
||||
|
||||
/** Generate an image from a text prompt. */
|
||||
async generate(options: GenerateImageOptions): Promise<GenerateImageResult> {
|
||||
const controller = new AbortController();
|
||||
const timer = setTimeout(() => controller.abort(), this.timeout);
|
||||
|
||||
try {
|
||||
const response = await fetch(`${this.baseUrl}/generate`, {
|
||||
method: 'POST',
|
||||
headers: { 'Content-Type': 'application/json' },
|
||||
body: JSON.stringify({
|
||||
prompt: options.prompt,
|
||||
width: options.width ?? 1024,
|
||||
height: options.height ?? 1024,
|
||||
steps: options.steps ?? 4,
|
||||
seed: options.seed,
|
||||
output_format: options.outputFormat ?? 'png',
|
||||
}),
|
||||
signal: controller.signal,
|
||||
});
|
||||
|
||||
if (!response.ok) {
|
||||
const error = await response.json().catch(() => ({ detail: response.statusText }));
|
||||
throw new Error(
|
||||
`Image generation error ${response.status}: ${(error as { detail: string }).detail}`
|
||||
);
|
||||
}
|
||||
|
||||
return (await response.json()) as GenerateImageResult;
|
||||
} finally {
|
||||
clearTimeout(timer);
|
||||
}
|
||||
}
|
||||
|
||||
/** Get the full URL for a generated image. */
|
||||
imageUrl(relativePath: string): string {
|
||||
return `${this.baseUrl}${relativePath}`;
|
||||
}
|
||||
|
||||
/** Download a generated image as ArrayBuffer. */
|
||||
async downloadImage(relativePath: string): Promise<ArrayBuffer> {
|
||||
const response = await fetch(this.imageUrl(relativePath), {
|
||||
signal: AbortSignal.timeout(30_000),
|
||||
});
|
||||
if (!response.ok) throw new Error(`Failed to download image: ${response.status}`);
|
||||
return response.arrayBuffer();
|
||||
}
|
||||
|
||||
/** Check if the image generation service is healthy. */
|
||||
async health(): Promise<ImageGenHealthResponse> {
|
||||
const response = await fetch(`${this.baseUrl}/health`, {
|
||||
signal: AbortSignal.timeout(5000),
|
||||
});
|
||||
return (await response.json()) as ImageGenHealthResponse;
|
||||
}
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue