[Inference Provider]: Add TextCLF as an inference provider

packages/inference/README.md

@@ -71,6 +71,8 @@ Currently, we support the following providers:
 - [Groq](https://groq.com)
 - [Wavespeed.ai](https://wavespeed.ai/)
 - [Z.ai](https://z.ai/)
+- [TextCLF](https://textclf.com)
+
 
 To send requests to a third-party provider, you have to pass the `provider` parameter to the inference function. The default value of the `provider` parameter is "auto", which will select the first of the providers available for the model, sorted by your preferred order in https://hf.co/settings/inference-providers.
 
@@ -109,6 +111,7 @@ Only a subset of models are supported when requesting third-party providers. You
 - [Cerebras supported models](https://huggingface.co/api/partners/cerebras/models)
 - [DeepInfra supported models](https://huggingface.co/api/partners/deepinfra/models)
 - [Groq supported models](https://console.groq.com/docs/models)
+- [TextCLF supported models](https://huggingface.co/api/partners/textclf/models)
 - [Novita AI supported models](https://huggingface.co/api/partners/novita/models)
 - [Wavespeed.ai supported models](https://huggingface.co/api/partners/wavespeed/models)
 - [Z.ai supported models](https://huggingface.co/api/partners/zai-org/models)

packages/inference/src/lib/getProviderHelper.ts

@@ -17,6 +17,7 @@ import * as Nvidia from "../providers/nvidia.js";
 import * as OpenAI from "../providers/openai.js";
 import * as OvhCloud from "../providers/ovhcloud.js";
 import * as PublicAI from "../providers/publicai.js";
+import * as TextCLF from "../providers/textclf.js";
 import type {
 	AudioClassificationTaskHelper,
 	AudioToAudioTaskHelper,
@@ -182,6 +183,10 @@ export const PROVIDERS: Record<InferenceProvider, Partial<Record<InferenceTask,
 		"text-generation": new Scaleway.ScalewayTextGenerationTask(),
 		"feature-extraction": new Scaleway.ScalewayFeatureExtractionTask(),
 	},
+	textclf: {
+		conversational: new TextCLF.TextCLFConversationalTask(),
+		"text-generation": new TextCLF.TextCLFTextGenerationTask(),
+	},
 	together: {
 		"text-to-image": new Together.TogetherTextToImageTask(),
 		conversational: new Together.TogetherConversationalTask(),

packages/inference/src/providers/consts.ts

@@ -40,6 +40,7 @@ export const HARDCODED_MODEL_INFERENCE_MAPPING: Record<
 	replicate: {},
 	sambanova: {},
 	scaleway: {},
+	textclf: {},
 	together: {},
 	wavespeed: {},
 	"zai-org": {},

packages/inference/src/types.ts

@@ -67,6 +67,7 @@ export const INFERENCE_PROVIDERS = [
 	"replicate",
 	"sambanova",
 	"scaleway",
+	"textclf",
 	"together",
 	"wavespeed",
 	"zai-org",
@@ -106,6 +107,7 @@ export const PROVIDERS_HUB_ORGS: Record<InferenceProvider, string> = {
 	replicate: "replicate",
 	sambanova: "sambanovasystems",
 	scaleway: "scaleway",
+	textclf: "textclf",
 	together: "togethercomputer",
 	wavespeed: "wavespeed",
 	"zai-org": "zai-org",

packages/inference/test/InferenceClient.spec.ts

@@ -2208,6 +2208,58 @@ describe.skip("InferenceClient", () => {
 		},
 		TIMEOUT,
 	);
+	describe.concurrent(
+		"TextCLF",
+		() => {
+			const client = new InferenceClient(env.HF_TEXTCLF_KEY ?? "dummy");
+
+			HARDCODED_MODEL_INFERENCE_MAPPING["textclf"] = {
+				"meta-llama/Llama-3.1-8B-Instruct": {
+					provider: "groq",
+					hfModelId: "meta-llama/Llama-3.1-8B-Instruct",
+					providerId: "meta-llama/Llama-3.1-8B-Instruct",
+					status: "live",
+					task: "conversational",
+				},
+			};
+
+			it("chatCompletion", async () => {
+				const res = await client.chatCompletion({
+					model: "meta-llama/Llama-3.1-8B-Instruct",
+					provider: "textclf",
+					messages: [{ role: "user", content: "Complete this sentence with words, one plus one is equal " }],
+				});
+				if (res.choices && res.choices.length > 0) {
+					const completion = res.choices[0].message?.content;
+					expect(completion).toContain("two");
+				}
+			});
+
+			it("chatCompletion stream", async () => {
+				const stream = client.chatCompletionStream({
+					model: "meta-llama/Llama-3.1-8B-Instruct",
+					provider: "textclf",
+					messages: [{ role: "user", content: "Say 'this is a test'" }],
+					stream: true,
+				}) as AsyncGenerator<ChatCompletionStreamOutput>;
+
+				let fullResponse = "";
+				for await (const chunk of stream) {
+					if (chunk.choices && chunk.choices.length > 0) {
+						const content = chunk.choices[0].delta?.content;
+						if (content) {
+							fullResponse += content;
+						}
+					}
+				}
+
+				// Verify we got a meaningful response
+				expect(fullResponse).toBeTruthy();
+				expect(fullResponse.length).toBeGreaterThan(0);
+			});
+		},
+		TIMEOUT,
+	);
 	describe.concurrent(
 		"ZAI",
 		() => {