Spaces:
Running
Running
File size: 2,813 Bytes
ffe59ba 0df0841 ffe59ba 4e0f10e ffe59ba 4e0f10e ffe59ba 4e0f10e ffe59ba 4e0f10e ffe59ba | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 | export type ModelOption = {
id: string;
label: string;
description: string;
gpuRequired?: boolean;
/** Adapter-specific options passed via SIE's `options` field. */
options?: Record<string, unknown>;
};
export const RECOGNITION_MODELS: ModelOption[] = [
{
id: "lightonai/LightOnOCR-2-1B",
label: "LightOnOCR-2-1B (default)",
description: "Pixtral encoder + Qwen3 decoder, 2.1B. Strong Markdown output across dense layouts. ~4 GB to download on first call.",
},
{
id: "PaddlePaddle/PaddleOCR-VL-1.5",
label: "PaddleOCR-VL-1.5 (GPU image)",
description: "Paddle's VLM-OCR, 1.5B. Six task modes. Available on the CUDA image (compose.gpu.yml).",
options: { task: "ocr" },
gpuRequired: true,
},
{
id: "zai-org/GLM-OCR",
label: "GLM-OCR (GPU only)",
description: "CogViT + GLM-0.5B decoder, 9B in bfloat16. Premium quality, needs ~18 GB VRAM (compose.gpu.yml).",
gpuRequired: true,
},
];
export const STRUCTURED_MODELS: ModelOption[] = [
{
id: "naver-clova-ix/donut-base-finetuned-cord-v2",
label: "Donut on CORD (receipts)",
description: "Fine-tuned for the CORD receipt schema. Pixels in, nested JSON out.",
},
{
id: "naver-clova-ix/donut-base-finetuned-docvqa",
label: "Donut on DocVQA",
description: "Same Donut architecture, fine-tuned for visual question answering. Returns text answers.",
},
{
id: "naver-clova-ix/donut-base-finetuned-rvlcdip",
label: "Donut on RVL-CDIP (doc classification)",
description: "Same Donut architecture, fine-tuned for document-type classification across 16 classes (invoice, receipt, form, ...).",
},
];
export const NER_MODELS: ModelOption[] = [
{
id: "urchade/gliner_multi-v2.1",
label: "GLiNER multi (multilingual)",
description: "280M, zero-shot NER, 100+ languages. Good default.",
},
{
id: "urchade/gliner_large-v2.1",
label: "GLiNER large (English)",
description: "440M, English-focused, higher quality on English text.",
},
{
id: "urchade/gliner_multi_pii-v1",
label: "GLiNER multi PII",
description: "GLiNER fine-tuned for PII extraction. Good for redaction-style pipelines on documents.",
},
{
id: "numind/NuNER_Zero",
label: "NuNER Zero",
description: "NuMind's zero-shot NER. Different architecture from GLiNER; useful for comparing zero-shot NER families on the same input text.",
},
];
export const config = {
sieUrl: process.env.SIE_URL ?? "http://localhost:8080",
sieApiKey: process.env.SIE_API_KEY,
defaults: {
recognition: RECOGNITION_MODELS[0].id,
structured: STRUCTURED_MODELS[0].id,
ner: NER_MODELS[0].id,
},
paths: {
samples: "data/samples/index.json",
sampleDir: "data/samples",
},
port: Number(process.env.PORT ?? 3032),
} as const;
|