💄 style: update Novita AI model info & add NOVITA_MODEL_LIST support

Dockerfile

@@ -127,7 +127,7 @@ ENV \
     # Moonshot
     MOONSHOT_API_KEY="" MOONSHOT_PROXY_URL="" \
     # Novita
-    NOVITA_API_KEY="" \
+    NOVITA_API_KEY="" NOVITA_MODEL_LIST="" \
     # Ollama
     OLLAMA_MODEL_LIST="" OLLAMA_PROXY_URL="" \
     # OpenAI

Dockerfile.database

@@ -159,7 +159,7 @@ ENV \
     # Moonshot
     MOONSHOT_API_KEY="" MOONSHOT_PROXY_URL="" \
     # Novita
-    NOVITA_API_KEY="" \
+    NOVITA_API_KEY="" NOVITA_MODEL_LIST="" \
     # Ollama
     OLLAMA_MODEL_LIST="" OLLAMA_PROXY_URL="" \
     # OpenAI

src/config/llm.ts

@@ -81,6 +81,7 @@ export const getLLMConfig = () => {
 
       ENABLED_NOVITA: z.boolean(),
       NOVITA_API_KEY: z.string().optional(),
+      NOVITA_MODEL_LIST: z.string().optional(),
 
       ENABLED_BAICHUAN: z.boolean(),
       BAICHUAN_API_KEY: z.string().optional(),
@@ -176,6 +177,7 @@ export const getLLMConfig = () => {
 
       ENABLED_NOVITA: !!process.env.NOVITA_API_KEY,
       NOVITA_API_KEY: process.env.NOVITA_API_KEY,
+      NOVITA_MODEL_LIST: process.env.NOVITA_MODEL_LIST,
 
       ENABLED_BAICHUAN: !!process.env.BAICHUAN_API_KEY,
       BAICHUAN_API_KEY: process.env.BAICHUAN_API_KEY,

src/config/modelProviders/novita.ts

@@ -1,30 +1,47 @@
 import { ModelProviderCard } from '@/types/llm';
 
+// ref: https://novita.ai/model-api/product/llm-api
 const Novita: ModelProviderCard = {
   chatModels: [
     {
-      displayName: 'Llama3 8B Instruct',
+      displayName: 'Llama3.1 8B Instruct',
+      enabled: true,
+      id: 'meta-llama/llama-3.1-8b-instruct',
+      tokens: 8192,
+    },
+    {
+      displayName: 'Llama3.1 70B Instruct',
       enabled: true,
+      id: 'meta-llama/llama-3.1-70b-instruct',
+      tokens: 131_072,
+    },
+    {
+      displayName: 'Llama3.1 405B Instruct',
+      enabled: true,
+      id: 'meta-llama/llama-3.1-405b-instruct',
+      tokens: 32768,
+    },
+    {
+      displayName: 'Llama3 8B Instruct',
       id: 'meta-llama/llama-3-8b-instruct',
       tokens: 8192,
     },
     {
       displayName: 'Llama3 70B Instruct',
-      enabled: true,
       id: 'meta-llama/llama-3-70b-instruct',
       tokens: 8192,
     },
     {
-      displayName: 'Nous Hermes 2 Pro - Llama3 8B',
+      displayName: 'Gemma 2 9B',
       enabled: true,
-      id: 'nousresearch/hermes-2-pro-llama-3-8b',
+      id: 'google/gemma-2-9b-it',
       tokens: 8192,
     },
     {
-      displayName: 'Nous Hermes - Llama2 8B',
+      displayName: 'Mistral Nemo',
       enabled: true,
-      id: 'nousresearch/nous-hermes-llama2-13b',
-      tokens: 4096,
+      id: 'mistralai/mistral-nemo',
+      tokens: 32_768,
     },
     {
       displayName: 'Mistral 7B Instruct',
@@ -33,55 +50,44 @@ const Novita: ModelProviderCard = {
       tokens: 32_768,
     },
     {
-      displayName: 'Dolphin Mixtral 8x22B',
+      displayName: 'WizardLM 2 7B',
       enabled: true,
-      id: 'cognitivecomputations/dolphin-mixtral-8x22b',
-      tokens: 16_000,
+      id: 'microsoft/wizardlm 2-7b',
+      tokens: 32_768,
     },
     {
-      displayName: 'L3-70b-Euryale-v2.1',
+      displayName: 'WizardLM-2 8x22B',
       enabled: true,
-      id: 'sao10k/l3-70b-euryale-v2.1',
-      tokens: 16_000,
+      id: 'microsoft/wizardlm-2-8x22b',
+      tokens: 65_535,
     },
     {
-      displayName: 'Midnight Rose 70B',
-      enabled: true,
-      id: 'sophosympatheia/midnight-rose-70b',
-      tokens: 4096,
+      displayName: 'Dolphin Mixtral 8x22B',
+      id: 'cognitivecomputations/dolphin-mixtral-8x22b',
+      tokens: 16_000,
     },
     {
-      displayName: 'Mythomax L2 13b',
-      enabled: true,
-      id: 'gryphe/mythomax-l2-13b',
-      tokens: 4096,
+      displayName: 'Hermes 2 Pro Llama 3 8B',
+      id: 'nousresearch/hermes-2-pro-llama-3-8b',
+      tokens: 8192,
     },
     {
-      displayName: 'Nous Hermes 2 - Mixtral 8x7B-DPO',
-      enabled: true,
+      displayName: 'Hermes 2 Mixtral 8x7B DPO',
       id: 'Nous-Hermes-2-Mixtral-8x7B-DPO',
       tokens: 32_768,
     },
     {
-      displayName: 'Lzlv 70b',
-      enabled: true,
-      id: 'lzlv_70b',
+      displayName: 'MythoMax l2 13B',
+      id: 'gryphe/mythomax-l2-13b',
       tokens: 4096,
     },
     {
-      displayName: 'Open Hermes 2.5 Mistral 7B',
-      enabled: true,
-      id: 'teknium/openhermes-2.5-mistral-7b',
+      displayName: 'OpenChat 7B',
+      id: 'openchat/openchat-7b',
       tokens: 4096,
     },
-    {
-      displayName: 'Wizardlm2 8x22B',
-      enabled: true,
-      id: 'microsoft/wizardlm-2-8x22b',
-      tokens: 65_535,
-    },
   ],
-  checkModel: 'meta-llama/llama-3-70b-instruct',
+  checkModel: 'meta-llama/llama-3.1-8b-instruct',
   disableBrowserRequest: true,
   id: 'novita',
   modelList: { showModelFetcher: true },

src/server/globalConfig/index.ts

@@ -4,6 +4,7 @@ import { fileEnv } from '@/config/file';
 import { langfuseEnv } from '@/config/langfuse';
 import { getLLMConfig } from '@/config/llm';
 import {
+  NovitaProviderCard,
   OllamaProviderCard,
   OpenAIProviderCard,
   OpenRouterProviderCard,
@@ -39,7 +40,9 @@ export const getServerGlobalConfig = () => {
     ENABLED_ANTHROPIC,
     ENABLED_MINIMAX,
     ENABLED_MISTRAL,
+
     ENABLED_NOVITA,
+    NOVITA_MODEL_LIST,
 
     ENABLED_QWEN,
     QWEN_MODEL_LIST,
@@ -100,7 +103,14 @@ export const getServerGlobalConfig = () => {
       minimax: { enabled: ENABLED_MINIMAX },
       mistral: { enabled: ENABLED_MISTRAL },
       moonshot: { enabled: ENABLED_MOONSHOT },
-      novita: { enabled: ENABLED_NOVITA },
+      novita: {
+        enabled: ENABLED_NOVITA,
+        enabledModels: extractEnabledModels(NOVITA_MODEL_LIST),
+        serverModelCards: transformToChatModelCards({
+          defaultChatModels: NovitaProviderCard.chatModels,
+          modelString: NOVITA_MODEL_LIST,
+        }),
+      },
       ollama: {
         enabled: ENABLED_OLLAMA,
         fetchOnClient: !OLLAMA_PROXY_URL,