Feat/novita

.github/workflows/test.yml

@@ -46,6 +46,7 @@ jobs:
           HF_REPLICATE_KEY: dummy
           HF_SAMBANOVA_KEY: dummy
           HF_TOGETHER_KEY: dummy
+          HF_NOVITA_KEY: dummy
           HF_FIREWORKS_KEY: dummy
 
   browser:
@@ -88,6 +89,7 @@ jobs:
           HF_REPLICATE_KEY: dummy
           HF_SAMBANOVA_KEY: dummy
           HF_TOGETHER_KEY: dummy
+          HF_NOVITA_KEY: dummy
           HF_FIREWORKS_KEY: dummy
 
   e2e:
@@ -157,4 +159,5 @@ jobs:
           HF_REPLICATE_KEY: dummy
           HF_SAMBANOVA_KEY: dummy
           HF_TOGETHER_KEY: dummy
+          HF_NOVITA_KEY: dummy
           HF_FIREWORKS_KEY: dummy

packages/inference/README.md

@@ -50,6 +50,7 @@ Currently, we support the following providers:
 - [Fal.ai](https://fal.ai)
 - [Fireworks AI](https://fireworks.ai)
 - [Nebius](https://studio.nebius.ai)
+- [Novita](https://novita.ai/?utm_source=github_huggingface&utm_medium=github_readme&utm_campaign=link)
 - [Replicate](https://replicate.com)
 - [Sambanova](https://sambanova.ai)
 - [Together](https://together.xyz)

packages/inference/src/lib/makeRequestOptions.ts

@@ -4,6 +4,7 @@ import { NEBIUS_API_BASE_URL } from "../providers/nebius";
 import { REPLICATE_API_BASE_URL } from "../providers/replicate";
 import { SAMBANOVA_API_BASE_URL } from "../providers/sambanova";
 import { TOGETHER_API_BASE_URL } from "../providers/together";
+import { NOVITA_API_BASE_URL } from "../providers/novita";
 import { FIREWORKS_AI_API_BASE_URL } from "../providers/fireworks-ai";
 import type { InferenceProvider } from "../types";
 import type { InferenceTask, Options, RequestArgs } from "../types";
@@ -213,6 +214,7 @@ function makeUrl(params: {
 			}
 			return baseUrl;
 		}
+
 		case "fireworks-ai": {
 			const baseUrl = shouldProxy
 				? HF_HUB_INFERENCE_PROXY_TEMPLATE.replace("{{PROVIDER}}", params.provider)
@@ -222,6 +224,18 @@ function makeUrl(params: {
 			}
 			return baseUrl;
 		}
+		case "novita": {
+			const baseUrl = shouldProxy
+				? HF_HUB_INFERENCE_PROXY_TEMPLATE.replace("{{PROVIDER}}", params.provider)
+				: NOVITA_API_BASE_URL;
+			if (params.taskHint === "text-generation") {
+				if (params.chatCompletion) {
+					return `${baseUrl}/chat/completions`;
+				}
+				return `${baseUrl}/completions`;
+			}
+			return baseUrl;
+		}
 		default: {
 			const baseUrl = HF_HUB_INFERENCE_PROXY_TEMPLATE.replaceAll("{{PROVIDER}}", "hf-inference");
 			const url = params.forceTask

packages/inference/src/providers/consts.ts

@@ -23,4 +23,5 @@ export const HARDCODED_MODEL_ID_MAPPING: Record<InferenceProvider, Record<ModelI
 	replicate: {},
 	sambanova: {},
 	together: {},
+	novita: {},
 };

packages/inference/src/providers/novita.ts

@@ -0,0 +1,18 @@
+export const NOVITA_API_BASE_URL = "https://api.novita.ai/v3/openai";
+
+/**
+ * See the registered mapping of HF model ID => Novita model ID here:
+ *
+ * https://huggingface.co/api/partners/novita/models
+ *
+ * This is a publicly available mapping.
+ *
+ * If you want to try to run inference for a new model locally before it's registered on huggingface.co,
+ * you can add it to the dictionary "HARDCODED_MODEL_ID_MAPPING" in consts.ts, for dev purposes.
+ *
+ * - If you work at Novita and want to update this mapping, please use the model mapping API we provide on huggingface.co
+ * - If you're a community member and want to add a new supported HF model to Novita, please open an issue on the present repo
+ * and we will tag Novita team members.
+ *
+ * Thanks!
+ */ 

packages/inference/src/types.ts

@@ -36,7 +36,9 @@ export const INFERENCE_PROVIDERS = [
 	"replicate",
 	"sambanova",
 	"together",
+	"novita",
 ] as const;
+
 export type InferenceProvider = (typeof INFERENCE_PROVIDERS)[number];
 
 export interface BaseArgs {

packages/inference/test/HfInference.spec.ts

@@ -1175,4 +1175,52 @@ describe.concurrent("HfInference", () => {
 		},
 		TIMEOUT
 	);
+
+	describe.concurrent(
+		"Novita",
+		() => {
+			const client = new HfInference(env.HF_NOVITA_KEY);
+
+			HARDCODED_MODEL_ID_MAPPING["novita"] = {
+				"meta-llama/llama-3.1-8b-instruct": "meta-llama/llama-3.1-8b-instruct",
+				"deepseek/deepseek-r1-distill-qwen-14b": "deepseek/deepseek-r1-distill-qwen-14b",
+			};
+
+			it("chatCompletion", async () => {
+				const res = await client.chatCompletion({
+					model: "meta-llama/llama-3.1-8b-instruct",
+					provider: "novita",
+					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: "deepseek/deepseek-r1-distill-qwen-14b",
+					provider: "novita",
+					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
+	);
 });