Add dat1.co as an inference provider

[ArsenyYankovsky]

🚀 Added dat1.co as a Hugging Face inference provider

Dat1.co is a low cold start, high-performance serverless inference provider that respects your privacy.

What we do:

• provide access to popular models while protecting our clients’ privacy and complying with important data protection laws (GDPR, CCPA, etc.)
• serve wide variety of image generation models, utilizing our low cold start to switch between them efficiently

Changes

• README.md - added links to dat1.co website and a list of supported models on Hugging Face
• packages/inference/src/lib/getProviderHelper.ts, packages/inference/src/providers/consts.ts, packages/inference/src/providers/dat1.ts, packages/inference/src/types.ts - integrated dat1.co with Hugging Face JS client
• packages/inference/test/InferenceClient.spec.ts - added automatic test that can be run using a fresh dat1.co account without adding a payment method

Testing

We added automatic tests and ran them using a freshly created dat1.co account (which doesn't require a payment method until you reach a certain usage threshold).

pnpm test -- --reporter verbose \ test/InferenceClient.spec.ts -t "dat1"

pnpm test -- --reporter verbose \ test/InferenceClient.spec.ts -t "dat1"

@huggingface/[email protected] test D:\dev\workspace\huggingface.js\packages\inference

vitest run --config vitest.config.mts "--reporter" "verbose" "\" "test/InferenceClient.spec.ts" "-t" "dat1"

RUN  v0.34.6 D:/dev/workspace/huggingface.js/packages/inference
stderr | unknown test

Set HF_TOKEN in the env to run the tests for better rate limits
   ↓ chatCompletion [skipped]
   ↓ chatCompletion stream [skipped]
   ↓ textToImage [skipped]
   ↓ textGeneration [skipped]
 ↓ Nebius (4) [skipped]
   ↓ chatCompletion [skipped]
   ↓ chatCompletion stream [skipped]
   ↓ textToImage [skipped]
   ↓ featureExtraction [skipped]

↓ src/vendor/fetch-event-source/parse.spec.ts (17) [skipped]

↓ parse (17) [skipped]

↓ getLines (11) [skipped]

↓ single line [skipped]

↓ multiple lines [skipped]

↓ single line split across multiple arrays [skipped]

↓ multiple lines split across multiple arrays [skipped]

↓ new line [skipped]

↓ comment line [skipped]

↓ line with no field [skipped]

↓ line with multiple colons [skipped]

↓ single byte array with multiple lines separated by \n [skipped]

↓ single byte array with multiple lines separated by \r [skipped]

↓ single byte array with multiple lines separated by \r\n [skipped]

↓ getMessages (6) [skipped]

↓ happy path [skipped]

↓ skip unknown fields [skipped]

↓ ignore non-integer retry [skipped]

↓ skip comment-only messages [skipped]

↓ should append data split across multiple lines [skipped]

↓ should reset id if sent multiple times [skipped]

✓ test/InferenceClient.spec.ts (106) 21740ms

✓ InferenceClient (106) 21740ms

↓ backward compatibility (1) [skipped]

↓ works with old HfInference name [skipped]

↓ HF Inference (49) [skipped]

↓ throws error if model does not exist [skipped]

↓ fillMask [skipped]

↓ works without model [skipped]

↓ summarization [skipped]

↓ questionAnswering [skipped]

↓ tableQuestionAnswering [skipped]

↓ documentQuestionAnswering [skipped]

↓ documentQuestionAnswering with non-array output [skipped]

↓ visualQuestionAnswering [skipped]

↓ textClassification [skipped]

↓ textGeneration - gpt2 [skipped]

↓ textGeneration - openai-community/gpt2 [skipped]

↓ textGenerationStream - meta-llama/Llama-3.2-3B [skipped]

↓ textGenerationStream - catch error [skipped]

↓ textGenerationStream - Abort [skipped]

↓ tokenClassification [skipped]

↓ translation [skipped]

↓ zeroShotClassification [skipped]

↓ sentenceSimilarity [skipped]

↓ FeatureExtraction [skipped]

↓ FeatureExtraction - auto-compatibility sentence similarity [skipped]

↓ FeatureExtraction - facebook/bart-base [skipped]

↓ FeatureExtraction - facebook/bart-base, list input [skipped]

↓ automaticSpeechRecognition [skipped]

↓ audioClassification [skipped]

↓ audioToAudio [skipped]

↓ textToSpeech [skipped]

↓ imageClassification [skipped]

↓ zeroShotImageClassification [skipped]

↓ objectDetection [skipped]

↓ imageSegmentation [skipped]

↓ imageToImage [skipped]

↓ imageToImage blob data [skipped]

↓ textToImage [skipped]

↓ textToImage with parameters [skipped]

↓ imageToText [skipped]

↓ request - openai-community/gpt2 [skipped]

↓ tabularRegression [skipped]

↓ tabularClassification [skipped]

↓ endpoint - makes request to specified endpoint [skipped]

↓ endpoint - makes request to specified endpoint - alternative syntax [skipped]

↓ chatCompletion modelId - OpenAI Specs [skipped]

↓ chatCompletionStream modelId - OpenAI Specs [skipped]

↓ chatCompletionStream modelId Fail - OpenAI Specs [skipped]

↓ chatCompletion - OpenAI Specs [skipped]

↓ chatCompletionStream - OpenAI Specs [skipped]

↓ custom mistral - OpenAI Specs [skipped]

↓ custom openai - OpenAI Specs [skipped]

↓ OpenAI client side routing - model should have provider as prefix [skipped]

✓ dat1 (3) 21740ms

✓ chatCompletion 4946ms

✓ chatCompletion stream 9329ms

✓ textToImage 21702ms

↓ Fal AI (4) [skipped]

↓ textToImage - black-forest-labs/FLUX.1-schnell [skipped]

↓ textToImage - SD LoRAs [skipped]

↓ textToImage - Flux LoRAs [skipped]

↓ automaticSpeechRecognition - openai/whisper-large-v3 [skipped]

↓ Featherless (3) [skipped]

↓ chatCompletion [skipped]

↓ chatCompletion stream [skipped]

↓ textGeneration [skipped]

↓ Replicate (11) [skipped]

↓ textToImage canonical - black-forest-labs/FLUX.1-schnell [skipped]

↓ textToImage canonical - black-forest-labs/FLUX.1-dev [skipped]

↓ textToImage - all Flux LoRAs [skipped]

↓ textToImage canonical - stabilityai/stable-diffusion-3.5-large-turbo [skipped]

↓ textToImage versioned - ByteDance/SDXL-Lightning [skipped]

↓ textToImage versioned - ByteDance/Hyper-SD [skipped]

↓ textToImage versioned - playgroundai/playground-v2.5-1024px-aesthetic [skipped]

↓ textToImage versioned - stabilityai/stable-diffusion-xl-base-1.0 [skipped]

↓ textToSpeech versioned [skipped]

↓ textToSpeech OuteTTS -  usually Cold [skipped]

↓ textToSpeech Kokoro [skipped]

↓ SambaNova (3) [skipped]

↓ chatCompletion [skipped]

↓ chatCompletion stream [skipped]

↓ featureExtraction [skipped]

↓ Together (4) [skipped]

↓ chatCompletion [skipped]

↓ chatCompletion stream [skipped]

↓ textToImage [skipped]

↓ textGeneration [skipped]

↓ Nebius (4) [skipped]

↓ chatCompletion [skipped]

↓ chatCompletion stream [skipped]

↓ textToImage [skipped]

↓ featureExtraction [skipped]

↓ 3rd party providers (1) [skipped]

↓ chatCompletion - fails with unsupported model [skipped]

↓ Fireworks (2) [skipped]

↓ chatCompletion [skipped]

↓ chatCompletion stream [skipped]

↓ Hyperbolic (4) [skipped]

↓ chatCompletion - hyperbolic [skipped]

↓ chatCompletion stream [skipped]

↓ textToImage [skipped]

↓ textGeneration [skipped]

↓ Novita (2) [skipped]

↓ chatCompletion [skipped]

↓ chatCompletion stream [skipped]

↓ Black Forest Labs (2) [skipped]

↓ textToImage [skipped]

↓ textToImage URL [skipped]

↓ Cohere (2) [skipped]

↓ chatCompletion [skipped]

↓ chatCompletion stream [skipped]

↓ Cerebras (2) [skipped]

↓ chatCompletion [skipped]

↓ chatCompletion stream [skipped]

↓ Nscale (3) [skipped]

↓ chatCompletion [skipped]

↓ chatCompletion stream [skipped]

↓ textToImage [skipped]

↓ Groq (2) [skipped]

↓ chatCompletion [skipped]

↓ chatCompletion stream [skipped]

↓ OVHcloud (4) [skipped]

↓ chatCompletion [skipped]

↓ chatCompletion stream [skipped]

↓ textGeneration [skipped]

↓ textGeneration stream [skipped]
Test Files  1 passed | 1 skipped (2)

Tests  3 passed | 120 skipped (123)

Start at  12:43:22

Duration  22.58s (transform 397ms, setup 28ms, collect 507ms, tests 21.74s, environment 0ms, prepare 140ms)