Add Hugging Face Inference Endpoints as Model Provider

.gitignore

@@ -49,4 +49,4 @@ src-tauri/resources/bin
 # Helper tools
 .opencode
 OpenCode.md
-archive/
+archive/flatpak/

docs/bun.lock

@@ -20,7 +20,7 @@
         "embla-carousel-react": "^8.0.0",
         "fs": "^0.0.1-security",
         "gray-matter": "^4.0.3",
-        "lucide-react": "^0.372.0",
+        "lucide-react": "^0.522.0",
         "next": "^14.1.4",
         "next-seo": "^6.5.0",
         "next-sitemap": "^4.2.3",
@@ -1503,7 +1503,7 @@
 
     "lru-cache": ["[email protected]", "", {}, "sha512-JNAzZcXrCt42VGLuYz0zfAzDfAvJWW6AfYlDBQyDV5DClI2m5sAmK+OIO7s59XfsRsWHp02jAJrRadPRGTt6SQ=="],
 
-    "lucide-react": ["lucide-react@0.372.0", "", { "peerDependencies": { "react": "^16.5.1 || ^17.0.0 || ^18.0.0" } }, "sha512-0cKdqmilHXWUwWAWnf6CrrjHD8YaqPMtLrmEHXolZusNTr9epULCsiJwIOHk2q1yFxdEwd96D4zShlAj67UJdA=="],
+    "lucide-react": ["lucide-react@0.522.0", "", { "peerDependencies": { "react": "^16.5.1 || ^17.0.0 || ^18.0.0 || ^19.0.0" } }, "sha512-jnJbw974yZ7rQHHEFKJOlWAefG3ATSCZHANZxIdx8Rk/16siuwjgA4fBULpXEAWx/RlTs3FzmKW/udWUuO0aRw=="],
 
     "lz-string": ["[email protected]", "", { "bin": { "lz-string": "bin/bin.js" } }, "sha512-h5bgJWpxJNswbU7qCrV0tIKQCaS3blPDrqKWx+QxzuzL1zGUzij9XCWLrSLsJPu5t+eWA/ycetzYAO5IOMcWAQ=="],
 

docs/src/pages/docs/remote-models/_meta.json

@@ -26,5 +26,9 @@
   "openrouter": {
     "title": "OpenRouter",
     "href": "/docs/remote-models/openrouter"
+  },
+  "huggingface": {
+    "title": "Hugging Face",
+    "href": "/docs/remote-models/huggingface"
   }
 }

docs/src/pages/docs/remote-models/huggingface.mdx

@@ -0,0 +1,123 @@
+---
+title: Hugging Face
+description: Learn how to integrate Hugging Face Inference Endpoints with Jan for enhanced functionality.
+keywords:
+  [
+    Hugging Face,
+    Jan,
+    Jan AI,
+    Hugging Face Inference Endpoints,
+    Hugging Face API,
+    Hugging Face Integration,
+    Hugging Face API Integration
+  ]
+---
+
+import { Callout, Steps } from 'nextra/components'
+import { Settings, Plus } from 'lucide-react'
+
+# Hugging Face
+
+Jan supports lots of models hosted on [Hugging Face](https://huggingface.co/). The main thing to keep 
+in mind is that **the method you use to deploy the model via huggingface has to be compatible with the 
+OpenAI API**.
+
+## Integrate Hugging Face API with Jan
+
+<Steps>
+
+### Step 1: Navigate to the HuggingFace Model Hub
+
+Visit the [HuggingFace Model Hub](https://huggingface.co/models) (make sure you are logged in) and 
+pick the model you want to use
+
+![HuggingFace Model Hub](../_assets/hf_hub.png)
+
+### Step 2: Configure HF Inference Endpoint and Deploy
+
+After you have selected the model you want to use, click on the **Deploy** button and select a 
+deployment method. We will select HF Inference Endpoints for this one.
+
+![HuggingFace Deployment](../_assets/hf_jan_nano.png)
+<br/>
+
+This will take you to the deployment set up page. For this example, we will leave the default settings 
+as they are under the GPU tab and cick on **Create Endpoint**.
+
+![HuggingFace Deployment](../_assets/hf_jan_nano_2.png)
+<br/>
+
+Once your endpoint is ready, test that it works on the **Test your endpoint** tab.
+
+![HuggingFace Deployment](../_assets/hf_jan_nano_3.png)
+<br/>
+
+If you get a response, you can click on **Copy** to copy the endpoint URL and API key.
+
+<Callout type='info'>
+  You will need to be logged into the HuggingFace Inference Endpoints and have a credit card on file to deploy a model.
+</Callout>
+
+### Step 3: Configure Jan
+
+If you do not have an API key you can create one under **Settings** > **Access Tokens** [here](https://huggingface.co/settings/tokens). Once 
+you finish, copy the token and add it to Jan alongside you endpoint URL at **Settings** > **Model Providers** > **HuggingFace**.
+
+**3.1 HF Token**
+![Get Token](../_assets/hf_jan_nano_5.png)
+<br/>
+
+**3.2 HF Endpoint URL**
+![Endpoint URL](../_assets/hf_jan_nano_4.png)
+<br/>
+
+**3.3 Jan Settings**
+![Jan Settings](../_assets/hf_jan_nano_6.png)
+
+<Callout type='warning'>
+Make sure to add `/v1/` to the end of your endpoint URL. This is required by the OpenAI API.
+</Callout>
+
+**3.4 Add Model Details**
+![Add Model Details](../_assets/hf_jan_nano_7.png)
+
+### Step 4: Configure Jan
+
+Now you can start using the model in any chat.
+
+![Start Using the Model](../_assets/hf_jan_nano_8.png)
+
+If you want to learn how to use Jan Nano with MCP, check out [the guide here](../jan-models/jan-nano-32).
+<br/>
+
+</Steps>
+
+## Available Hugging Face Models
+
+You can follow the steps above with a large amount of models on Hugging Face and bring them to Jan. Check 
+out other models in the [Hugging Face Model Hub](https://huggingface.co/models).
+
+
+## Troubleshooting
+
+Common issues and solutions:
+
+**1. Started a chat but the model is not responding**
+- Verify your API_KEY/HF_TOKEN is correct and not expired
+- Ensure the model you're trying to use is running again since, after a while, they go 
+idle so that you don't get charged when you are not using it
+
+![Model Running](../_assets/hf_jan_nano_9.png)
+
+**2. Connection Problems**
+- Check your internet connection
+- Verify Hugging Face's system status
+- Look for error messages in [Jan's logs](/docs/troubleshooting#how-to-get-error-logs)
+
+**3. Model Unavailable**
+- Confirm your API key has access to the model
+- Check if you're using the correct model ID
+- Verify your Hugging Face account has the necessary permissions
+
+Need more help? Join our [Discord community](https://discord.gg/FTk2MvZwJH) or check the
+[Hugging Face's documentation](https://docs.huggingface.co/en/inference-endpoints/index).

extensions/engine-management-extension/engines.mjs

@@ -8,6 +8,7 @@ import mistral from './resources/mistral.json' with { type: 'json' }
 import nvidia from './resources/nvidia.json' with { type: 'json' }
 import deepseek from './resources/deepseek.json' with { type: 'json' }
 import googleGemini from './resources/google_gemini.json' with { type: 'json' }
+import huggingface from './resources/huggingface.json' with { type: 'json' }
 
 import anthropicModels from './models/anthropic.json' with { type: 'json' }
 import cohereModels from './models/cohere.json' with { type: 'json' }
@@ -19,6 +20,7 @@ import mistralModels from './models/mistral.json' with { type: 'json' }
 import nvidiaModels from './models/nvidia.json' with { type: 'json' }
 import deepseekModels from './models/deepseek.json' with { type: 'json' }
 import googleGeminiModels from './models/google_gemini.json' with { type: 'json' }
+import huggingfaceModels from './models/huggingface.json' with { type: 'json' }
 
 const engines = [
   anthropic,
@@ -31,6 +33,7 @@ const engines = [
   nvidia,
   deepseek,
   googleGemini,
+  huggingface,
 ]
 const models = [
   ...anthropicModels,
@@ -43,5 +46,6 @@ const models = [
   ...nvidiaModels,
   ...deepseekModels,
   ...googleGeminiModels,
+  ...huggingfaceModels,
 ]
 export { engines, models }

extensions/engine-management-extension/models/huggingface.json

@@ -0,0 +1 @@
+[]

extensions/engine-management-extension/resources/huggingface.json

@@ -0,0 +1,23 @@
+{
+  "id": "huggingface",
+  "type": "remote",
+  "engine": "huggingface",
+  "url": "https://endpoints.huggingface.co/",
+  "api_key": "",
+  "metadata": {
+    "get_models_url": "{{base_url}}/models",
+    "header_template": "Authorization: Bearer {{api_key}}",
+    "transform_req": {
+      "chat_completions": {
+        "url": "{{base_url}}/chat/completions",
+        "template": "{ {% set first = true %} {% for key, value in input_request %} {% if key == \"messages\" or key == \"model\" or key == \"temperature\" or key == \"store\" or key == \"max_tokens\" or key == \"stream\" or key == \"presence_penalty\" or key == \"metadata\" or key == \"frequency_penalty\" or key == \"tools\" or key == \"tool_choice\" or key == \"logprobs\" or key == \"top_logprobs\" or key == \"logit_bias\" or key == \"n\" or key == \"modalities\" or key == \"prediction\" or key == \"response_format\" or key == \"service_tier\" or key == \"seed\" or key == \"stop\" or key == \"stream_options\" or key == \"top_p\" or key == \"parallel_tool_calls\" or key == \"user\" %} {% if not first %},{% endif %} \"{{ key }}\": {{ tojson(value) }} {% set first = false %} {% endif %} {% endfor %} }"
+      }
+    },
+    "transform_resp": {
+      "chat_completions": {
+        "template": "{{tojson(input_request)}}"
+      }
+    },
+    "explore_models_url": "https://endpoints.huggingface.co/catalog"
+  }
+}

extensions/yarn.lock

@@ -659,64 +659,89 @@ __metadata:
 
 "@janhq/core@file:../../core/package.tgz::locator=%40janhq%2Fassistant-extension%40workspace%3Aassistant-extension":
   version: 0.1.10
-  resolution: "@janhq/core@file:../../core/package.tgz#../../core/package.tgz::hash=5531aa&locator=%40janhq%2Fassistant-extension%40workspace%3Aassistant-extension"
+  resolution: "@janhq/core@file:../../core/package.tgz#../../core/package.tgz::hash=5ea857&locator=%40janhq%2Fassistant-extension%40workspace%3Aassistant-extension"
   dependencies:
     rxjs: "npm:^7.8.1"
     ulidx: "npm:^2.3.0"
-  checksum: 10c0/ee7fe21267cf795dba890781d1e7807a6cb3ecb915ce9ecbd3a8386a2ebc916a8b70a775ce5d9d9f74d2ec29e20b65cea4ef6cdd0ea250a8ff2d5e6bd2237b1e
+  checksum: 10c0/a528493357eb030270765b8df165a9d4d9ad736e61f0066d5888a7efe5a9f9cc2ed10aac02c485b93f5e70d2469718f69c68b5d030d0b0555ffeadaab0240e13
   languageName: node
   linkType: hard
 
 "@janhq/core@file:../../core/package.tgz::locator=%40janhq%2Fconversational-extension%40workspace%3Aconversational-extension":
   version: 0.1.10
-  resolution: "@janhq/core@file:../../core/package.tgz#../../core/package.tgz::hash=5531aa&locator=%40janhq%2Fconversational-extension%40workspace%3Aconversational-extension"
+  resolution: "@janhq/core@file:../../core/package.tgz#../../core/package.tgz::hash=5ea857&locator=%40janhq%2Fconversational-extension%40workspace%3Aconversational-extension"
   dependencies:
     rxjs: "npm:^7.8.1"
     ulidx: "npm:^2.3.0"
-  checksum: 10c0/ee7fe21267cf795dba890781d1e7807a6cb3ecb915ce9ecbd3a8386a2ebc916a8b70a775ce5d9d9f74d2ec29e20b65cea4ef6cdd0ea250a8ff2d5e6bd2237b1e
+  checksum: 10c0/a528493357eb030270765b8df165a9d4d9ad736e61f0066d5888a7efe5a9f9cc2ed10aac02c485b93f5e70d2469718f69c68b5d030d0b0555ffeadaab0240e13
+  languageName: node
+  linkType: hard
+
+"@janhq/core@file:../../core/package.tgz::locator=%40janhq%2Fdownload-extension%40workspace%3Adownload-extension":
+  version: 0.1.10
+  resolution: "@janhq/core@file:../../core/package.tgz#../../core/package.tgz::hash=5ea857&locator=%40janhq%2Fdownload-extension%40workspace%3Adownload-extension"
+  dependencies:
+    rxjs: "npm:^7.8.1"
+    ulidx: "npm:^2.3.0"
+  checksum: 10c0/a528493357eb030270765b8df165a9d4d9ad736e61f0066d5888a7efe5a9f9cc2ed10aac02c485b93f5e70d2469718f69c68b5d030d0b0555ffeadaab0240e13
   languageName: node
   linkType: hard
 
 "@janhq/core@file:../../core/package.tgz::locator=%40janhq%2Fengine-management-extension%40workspace%3Aengine-management-extension":
   version: 0.1.10
-  resolution: "@janhq/core@file:../../core/package.tgz#../../core/package.tgz::hash=5531aa&locator=%40janhq%2Fengine-management-extension%40workspace%3Aengine-management-extension"
+  resolution: "@janhq/core@file:../../core/package.tgz#../../core/package.tgz::hash=5ea857&locator=%40janhq%2Fengine-management-extension%40workspace%3Aengine-management-extension"
   dependencies:
     rxjs: "npm:^7.8.1"
     ulidx: "npm:^2.3.0"
-  checksum: 10c0/ee7fe21267cf795dba890781d1e7807a6cb3ecb915ce9ecbd3a8386a2ebc916a8b70a775ce5d9d9f74d2ec29e20b65cea4ef6cdd0ea250a8ff2d5e6bd2237b1e
+  checksum: 10c0/a528493357eb030270765b8df165a9d4d9ad736e61f0066d5888a7efe5a9f9cc2ed10aac02c485b93f5e70d2469718f69c68b5d030d0b0555ffeadaab0240e13
   languageName: node
   linkType: hard
 
 "@janhq/core@file:../../core/package.tgz::locator=%40janhq%2Fhardware-management-extension%40workspace%3Ahardware-management-extension":
   version: 0.1.10
-  resolution: "@janhq/core@file:../../core/package.tgz#../../core/package.tgz::hash=5531aa&locator=%40janhq%2Fhardware-management-extension%40workspace%3Ahardware-management-extension"
+  resolution: "@janhq/core@file:../../core/package.tgz#../../core/package.tgz::hash=5ea857&locator=%40janhq%2Fhardware-management-extension%40workspace%3Ahardware-management-extension"
   dependencies:
     rxjs: "npm:^7.8.1"
     ulidx: "npm:^2.3.0"
-  checksum: 10c0/ee7fe21267cf795dba890781d1e7807a6cb3ecb915ce9ecbd3a8386a2ebc916a8b70a775ce5d9d9f74d2ec29e20b65cea4ef6cdd0ea250a8ff2d5e6bd2237b1e
+  checksum: 10c0/a528493357eb030270765b8df165a9d4d9ad736e61f0066d5888a7efe5a9f9cc2ed10aac02c485b93f5e70d2469718f69c68b5d030d0b0555ffeadaab0240e13
   languageName: node
   linkType: hard
 
 "@janhq/core@file:../../core/package.tgz::locator=%40janhq%2Finference-cortex-extension%40workspace%3Ainference-cortex-extension":
   version: 0.1.10
-  resolution: "@janhq/core@file:../../core/package.tgz#../../core/package.tgz::hash=5531aa&locator=%40janhq%2Finference-cortex-extension%40workspace%3Ainference-cortex-extension"
+  resolution: "@janhq/core@file:../../core/package.tgz#../../core/package.tgz::hash=5ea857&locator=%40janhq%2Finference-cortex-extension%40workspace%3Ainference-cortex-extension"
   dependencies:
     rxjs: "npm:^7.8.1"
     ulidx: "npm:^2.3.0"
-  checksum: 10c0/ee7fe21267cf795dba890781d1e7807a6cb3ecb915ce9ecbd3a8386a2ebc916a8b70a775ce5d9d9f74d2ec29e20b65cea4ef6cdd0ea250a8ff2d5e6bd2237b1e
+  checksum: 10c0/a528493357eb030270765b8df165a9d4d9ad736e61f0066d5888a7efe5a9f9cc2ed10aac02c485b93f5e70d2469718f69c68b5d030d0b0555ffeadaab0240e13
   languageName: node
   linkType: hard
 
 "@janhq/core@file:../../core/package.tgz::locator=%40janhq%2Fmodel-extension%40workspace%3Amodel-extension":
   version: 0.1.10
-  resolution: "@janhq/core@file:../../core/package.tgz#../../core/package.tgz::hash=5531aa&locator=%40janhq%2Fmodel-extension%40workspace%3Amodel-extension"
+  resolution: "@janhq/core@file:../../core/package.tgz#../../core/package.tgz::hash=5ea857&locator=%40janhq%2Fmodel-extension%40workspace%3Amodel-extension"
   dependencies:
     rxjs: "npm:^7.8.1"
     ulidx: "npm:^2.3.0"
-  checksum: 10c0/ee7fe21267cf795dba890781d1e7807a6cb3ecb915ce9ecbd3a8386a2ebc916a8b70a775ce5d9d9f74d2ec29e20b65cea4ef6cdd0ea250a8ff2d5e6bd2237b1e
+  checksum: 10c0/a528493357eb030270765b8df165a9d4d9ad736e61f0066d5888a7efe5a9f9cc2ed10aac02c485b93f5e70d2469718f69c68b5d030d0b0555ffeadaab0240e13
   languageName: node
   linkType: hard
 
+"@janhq/download-extension@workspace:download-extension":
+  version: 0.0.0-use.local
+  resolution: "@janhq/download-extension@workspace:download-extension"
+  dependencies:
+    "@janhq/core": ../../core/package.tgz
+    "@tauri-apps/api": "npm:^2.5.0"
+    cpx: "npm:^1.5.0"
+    rimraf: "npm:^3.0.2"
+    rolldown: "npm:1.0.0-beta.1"
+    run-script-os: "npm:^1.1.6"
+    typescript: "npm:5.8.3"
+    vitest: "npm:^3.0.6"
+  languageName: unknown
+  linkType: soft
+
 "@janhq/engine-management-extension@workspace:engine-management-extension":
   version: 0.0.0-use.local
   resolution: "@janhq/engine-management-extension@workspace:engine-management-extension"
@@ -1436,6 +1461,13 @@ __metadata:
   languageName: node
   linkType: hard
 
+"@tauri-apps/api@npm:^2.5.0":
+  version: 2.6.0
+  resolution: "@tauri-apps/api@npm:2.6.0"
+  checksum: 10c0/211353d951c7e3e5298f074ec762b5853ff0cdee261478c27db1e450fcf3d6f2c03a616483abbf9dfc79f13c6dfcfa7db0b790c1384c113951c0d694809f05ef
+  languageName: node
+  linkType: hard
+
 "@tybys/wasm-util@npm:^0.9.0":
   version: 0.9.0
   resolution: "@tybys/wasm-util@npm:0.9.0"
@@ -6979,6 +7011,16 @@ __metadata:
   languageName: node
   linkType: hard
 
+"typescript@npm:5.8.3":
+  version: 5.8.3
+  resolution: "typescript@npm:5.8.3"
+  bin:
+    tsc: bin/tsc
+    tsserver: bin/tsserver
+  checksum: 10c0/5f8bb01196e542e64d44db3d16ee0e4063ce4f3e3966df6005f2588e86d91c03e1fb131c2581baf0fb65ee79669eea6e161cd448178986587e9f6844446dbb48
+  languageName: node
+  linkType: hard
+
 "typescript@npm:^5.3.3, typescript@npm:^5.7.2":
   version: 5.7.2
   resolution: "typescript@npm:5.7.2"
@@ -6999,6 +7041,16 @@ __metadata:
   languageName: node
   linkType: hard
 
+"typescript@patch:typescript@npm%3A5.8.3#optional!builtin<compat/typescript>":
+  version: 5.8.3
+  resolution: "typescript@patch:typescript@npm%3A5.8.3#optional!builtin<compat/typescript>::version=5.8.3&hash=5786d5"
+  bin:
+    tsc: bin/tsc
+    tsserver: bin/tsserver
+  checksum: 10c0/39117e346ff8ebd87ae1510b3a77d5d92dae5a89bde588c747d25da5c146603a99c8ee588c7ef80faaf123d89ed46f6dbd918d534d641083177d5fac38b8a1cb
+  languageName: node
+  linkType: hard
+
 "typescript@patch:typescript@npm%3A^5.3.3#optional!builtin<compat/typescript>, typescript@patch:typescript@npm%3A^5.7.2#optional!builtin<compat/typescript>":
   version: 5.7.2
   resolution: "typescript@patch:typescript@npm%3A5.7.2#optional!builtin<compat/typescript>::version=5.7.2&hash=5786d5"

web-app/src/lib/utils.ts

@@ -31,6 +31,8 @@ export function getProviderLogo(provider: string) {
       return '/images/model-provider/deepseek.svg'
     case 'openai':
       return '/images/model-provider/openai.svg'
+    case 'huggingface':
+      return '/images/model-provider/hugging-face.svg'
     default:
       return undefined
   }
@@ -46,6 +48,8 @@ export const getProviderTitle = (provider: string) => {
       return 'OpenRouter'
     case 'gemini':
       return 'Gemini'
+    case 'huggingface':
+      return 'Hugging Face'
     default:
       return provider.charAt(0).toUpperCase() + provider.slice(1)
   }