@lobehub/chat 1.22.8 → 1.22.10

package/CHANGELOG.md

@@ -2,6 +2,48 @@
 
 # Changelog
 
+### [Version 1.22.10](https://github.com/lobehub/lobe-chat/compare/v1.22.9...v1.22.10)
+
+<sup>Released on **2024-10-20**</sup>
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
+### [Version 1.22.9](https://github.com/lobehub/lobe-chat/compare/v1.22.8...v1.22.9)
+
+<sup>Released on **2024-10-18**</sup>
+
+#### 💄 Styles
+
+- **misc**: Update Fireworks AI model list.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### Styles
+
+- **misc**: Update Fireworks AI model list, closes [#4394](https://github.com/lobehub/lobe-chat/issues/4394) ([fe8ffdd](https://github.com/lobehub/lobe-chat/commit/fe8ffdd))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
 ### [Version 1.22.8](https://github.com/lobehub/lobe-chat/compare/v1.22.7...v1.22.8)
 
 <sup>Released on **2024-10-17**</sup>

package/README.md

@@ -439,15 +439,15 @@ Beside these features, LobeChat also have much better basic technique undergroun
 
 ## 🛳 Self Hosting
 
-LobeChat provides Self-Hosted Version with Vercel and [Docker Image][docker-release-link]. This allows you to deploy your own chatbot within a few minutes without any prior knowledge.
+LobeChat provides Self-Hosted Version with Vercel, Alibaba Cloud, and [Docker Image][docker-release-link]. This allows you to deploy your own chatbot within a few minutes without any prior knowledge.
 
 > \[!TIP]
 >
 > Learn more about [📘 Build your own LobeChat][docs-self-hosting] by checking it out.
 
-### `A` Deploying with Vercel, Zeabur or Sealos
+### `A` Deploying with Vercel, Zeabur , Sealos or Alibaba Cloud
 
-If you want to deploy this service yourself on either Vercel or Zeabur, you can follow these steps:
+"If you want to deploy this service yourself on Vercel, Zeabur or Alibaba Cloud, you can follow these steps:
 
 - Prepare your [OpenAI API Key](https://platform.openai.com/account/api-keys).
 - Click the button below to start deployment: Log in directly with your GitHub account, and remember to fill in the `OPENAI_API_KEY`(required) and `ACCESS_CODE` (recommended) on the environment variable section.
@@ -456,9 +456,9 @@ If you want to deploy this service yourself on either Vercel or Zeabur, you can
 
 <div align="center">
 
-|           Deploy with Vercel            |                     Deploy with Zeabur                      |                     Deploy with Sealos                      |                       Deploy with RepoCloud                       |
-| :-------------------------------------: | :---------------------------------------------------------: | :---------------------------------------------------------: | :---------------------------------------------------------------: |
-| [![][deploy-button-image]][deploy-link] | [![][deploy-on-zeabur-button-image]][deploy-on-zeabur-link] | [![][deploy-on-sealos-button-image]][deploy-on-sealos-link] | [![][deploy-on-repocloud-button-image]][deploy-on-repocloud-link] |
+|           Deploy with Vercel            |                     Deploy with Zeabur                      |                     Deploy with Sealos                      |                       Deploy with RepoCloud                       |                         Deploy with Alibaba Cloud                         |
+|:---------------------------------------:|:-----------------------------------------------------------:|:-----------------------------------------------------------:|:-----------------------------------------------------------------:|:-------------------------------------------------------------------------:|
+| [![][deploy-button-image]][deploy-link] | [![][deploy-on-zeabur-button-image]][deploy-on-zeabur-link] | [![][deploy-on-sealos-button-image]][deploy-on-sealos-link] | [![][deploy-on-repocloud-button-image]][deploy-on-repocloud-link] | [![][deploy-on-alibaba-cloud-button-image]][deploy-on-alibaba-cloud-link] |
 
 </div>
 
@@ -711,6 +711,8 @@ This project is [Apache 2.0](./LICENSE) licensed.
 [deploy-on-sealos-link]: https://cloud.sealos.io/?openapp=system-template%3FtemplateName%3Dlobe-chat
 [deploy-on-zeabur-button-image]: https://zeabur.com/button.svg
 [deploy-on-zeabur-link]: https://zeabur.com/templates/VZGGTI
+[deploy-on-alibaba-cloud-button-image]: https://service-info-public.oss-cn-hangzhou.aliyuncs.com/computenest-en.svg
+[deploy-on-alibaba-cloud-link]: https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=LobeChat%E7%A4%BE%E5%8C%BA%E7%89%88
 [discord-link]: https://discord.gg/AYFPHvv2jT
 [discord-shield]: https://img.shields.io/discord/1127171173982154893?color=5865F2&label=discord&labelColor=black&logo=discord&logoColor=white&style=flat-square
 [discord-shield-badge]: https://img.shields.io/discord/1127171173982154893?color=5865F2&label=discord&labelColor=black&logo=discord&logoColor=white&style=for-the-badge

package/README.zh-CN.md

@@ -153,6 +153,7 @@ LobeChat 支持文件上传与知识库功能，你可以上传文件、图片
 - **Minimax**: 接入了 Minimax 的 AI 模型，包括 MoE 模型 **abab6**，提供了更多的选择空间。[了解更多](https://www.minimaxi.com/)
 - **DeepSeek**: 接入了 DeepSeek 的 AI 模型，包括最新的 **DeepSeek-V2**，提供兼顾性能与价格的模型。[了解更多](https://www.deepseek.com/)
 - **Qwen**: 接入了 Qwen 的 AI 模型，包括最新的 **qwen-turbo**，**qwen-plus** 和 **qwen-max** 等模型。[了解更多](https://help.aliyun.com/zh/dashscope/developer-reference/model-introduction)
+- **Novita AI**: 性价比最高的开源模型供应商，支持 **Llama**，**Mistral** 系列等最前沿的开源模型。在情感陪伴等场景表现优异，无任何内容限制或审查。 [了解更多](https://novita.ai/model-api/product/llm-api?utm_source=lobechat&utm_medium=ch&utm_campaign=api)
 
 同时，我们也在计划支持更多的模型服务商，如 Replicate 和 Perplexity 等，以进一步丰富我们的服务商库。如果你希望让 LobeChat 支持你喜爱的服务商，欢迎加入我们的[社区讨论](https://github.com/lobehub/lobe-chat/discussions/1284)。
 

package/docs/self-hosting/platform/alibaba-cloud.mdx

@@ -0,0 +1,33 @@
+---
+title: Deploy LobeChat on Alibaba Cloud
+description: Learn how to deploy the LobeChat application on Alibaba Cloud, including preparing the large model API Key, clicking the deploy button, and other operations.
+tags:
+  - Alibaba Cloud
+  - LobeChat
+  - Alibaba Cloud Compute Nest
+  - API Key
+---
+
+# Deploy LobeChat with Alibaba Cloud
+
+If you want to deploy LobeChat on Alibaba Cloud, you can follow the steps below:
+
+## Alibaba Cloud Deployment Process
+
+<Steps>
+
+### Prepare your API Key
+
+Go to [OpenAI API Key](https://platform.openai.com/account/api-keys) to get your OpenAI API Key.
+Or go to [Tongyi Qianwen API Key](https://bailian.console.aliyun.com/?apiKey=1#/api-key) to get your API Key.
+
+### One-click to deploy
+
+[![][deploy-button-image]][deploy-link]
+
+### Once deployed, you can start using it
+
+</Steps>
+
+[deploy-button-image]: https://service-info-public.oss-cn-hangzhou.aliyuncs.com/computenest-en.svg
+[deploy-link]: https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=LobeChat%E7%A4%BE%E5%8C%BA%E7%89%88

package/docs/self-hosting/platform/alibaba-cloud.zh-CN.mdx

@@ -0,0 +1,33 @@
+---
+title: 在 阿里云 上部署 LobeChat
+description: 学习如何在阿里云上部署LobeChat应用，包括准备大模型 API Key、点击部署按钮等操作。
+tags:
+  - 阿里云
+  - LobeChat
+  - 部署流程
+  - 大模型 API Key
+---
+
+# 使用 阿里云计算巢 部署
+
+如果想在 阿里云 上部署 LobeChat，可以按照以下步骤进行操作：
+
+## 阿里云 部署流程
+
+<Steps>
+
+### 准备好你的 API Key
+
+前往 [OpenAI API Key](https://platform.openai.com/account/api-keys) 获取你的 OpenAI API Key
+或 前往 [通义千问 API Key](https://bailian.console.aliyun.com/?apiKey=1#/api-key) 获取你的通义千问 API Key
+
+### 点击下方按钮进行部署
+
+[![][deploy-button-image]][deploy-link]
+
+### 部署完毕后，即可开始使用
+
+</Steps>
+
+[deploy-button-image]: https://service-info-public.oss-cn-hangzhou.aliyuncs.com/computenest-en.svg
+[deploy-link]: https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=LobeChat%E7%A4%BE%E5%8C%BA%E7%89%88

package/docs/self-hosting/start.mdx

@@ -9,6 +9,7 @@ tags:
   - Vercel
   - Docker
   - Docker Compose
+  - Alibaba Cloud
 ---
 # Build Your Own Lobe Chat
 

package/docs/self-hosting/start.zh-CN.mdx

@@ -9,12 +9,13 @@ tags:
   - Docker
   - Netlify
   - Vercel
+  - 阿里云计算巢
   - 个性化
 ---
 
 # 构建属于自己的 Lobe Chat
 
-LobeChat 支持多种部署平台，包括 Vercel、Docker 和 Docker Compose 等，你可以选择适合自己的部署平台进行部署，构建属于自己的 Lobe Chat。
+LobeChat 支持多种部署平台，包括 Vercel、Docker、 Docker Compose 和 阿里云计算巢 等，你可以选择适合自己的部署平台进行部署，构建属于自己的 Lobe Chat。
 
 ## 快速部署
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lobehub/chat",
-  "version": "1.22.8",
+  "version": "1.22.10",
   "description": "Lobe Chat - an open-source, high-performance chatbot framework that supports speech synthesis, multimodal, and extensible Function Call plugin system. Supports one-click free deployment of your private ChatGPT/LLM web application.",
   "keywords": [
     "framework",
@@ -99,74 +99,74 @@
     ]
   },
   "dependencies": {
-    "@ant-design/icons": "^5.4.0",
-    "@ant-design/pro-components": "^2.7.10",
-    "@anthropic-ai/sdk": "^0.29.0",
+    "@ant-design/icons": "^5.5.1",
+    "@ant-design/pro-components": "^2.7.18",
+    "@anthropic-ai/sdk": "^0.29.2",
     "@auth/core": "^0.34.2",
-    "@aws-sdk/client-bedrock-runtime": "^3.637.0",
-    "@aws-sdk/client-s3": "^3.637.0",
-    "@aws-sdk/s3-request-presigner": "^3.637.0",
+    "@aws-sdk/client-bedrock-runtime": "^3.675.0",
+    "@aws-sdk/client-s3": "^3.675.0",
+    "@aws-sdk/s3-request-presigner": "^3.675.0",
     "@azure/core-rest-pipeline": "1.16.0",
     "@azure/openai": "1.0.0-beta.12",
     "@baiducloud/qianfan": "^0.1.9",
-    "@cfworker/json-schema": "^2.0.0",
-    "@clerk/localizations": "^3.0.4",
-    "@clerk/nextjs": "^5.3.3",
-    "@clerk/themes": "^2.1.27",
-    "@codesandbox/sandpack-react": "^2.19.8",
-    "@cyntler/react-doc-viewer": "^1.16.6",
-    "@google/generative-ai": "^0.16.0",
+    "@cfworker/json-schema": "^2.0.1",
+    "@clerk/localizations": "^3.3.0",
+    "@clerk/nextjs": "^5.7.5",
+    "@clerk/themes": "^2.1.37",
+    "@codesandbox/sandpack-react": "^2.19.9",
+    "@cyntler/react-doc-viewer": "^1.17.0",
+    "@google/generative-ai": "^0.16.1",
     "@huggingface/inference": "^2.8.1",
     "@icons-pack/react-simple-icons": "9.6.0",
     "@khmyznikov/pwa-install": "^0.3.9",
-    "@langchain/community": "^0.2.31",
+    "@langchain/community": "^0.2.33",
     "@lobehub/chat-plugin-sdk": "^1.32.4",
     "@lobehub/chat-plugins-gateway": "^1.9.0",
-    "@lobehub/icons": "^1.35.3",
-    "@lobehub/tts": "^1.24.3",
-    "@lobehub/ui": "^1.150.3",
-    "@neondatabase/serverless": "^0.10.0",
-    "@next/third-parties": "^14.2.6",
-    "@react-spring/web": "^9.7.3",
-    "@sentry/nextjs": "^7.119.0",
-    "@serwist/next": "^9.0.8",
-    "@t3-oss/env-nextjs": "^0.11.0",
-    "@tanstack/react-query": "^5.52.1",
+    "@lobehub/icons": "^1.35.4",
+    "@lobehub/tts": "^1.25.1",
+    "@lobehub/ui": "^1.151.5",
+    "@neondatabase/serverless": "^0.10.1",
+    "@next/third-parties": "^14.2.15",
+    "@react-spring/web": "^9.7.5",
+    "@sentry/nextjs": "^7.119.2",
+    "@serwist/next": "^9.0.9",
+    "@t3-oss/env-nextjs": "^0.11.1",
+    "@tanstack/react-query": "^5.59.15",
     "@trpc/client": "next",
     "@trpc/next": "next",
     "@trpc/react-query": "next",
     "@trpc/server": "next",
     "@vercel/analytics": "^1.3.1",
-    "@vercel/edge-config": "^1.2.1",
+    "@vercel/edge-config": "^1.3.0",
     "@vercel/speed-insights": "^1.0.12",
     "ahooks": "^3.8.1",
-    "ai": "^3.3.16",
-    "antd": "^5.21.1",
-    "antd-style": "^3.6.3",
+    "ai": "^3.4.16",
+    "antd": "^5.21.4",
+    "antd-style": "^3.7.0",
     "brotli-wasm": "^3.0.1",
     "chroma-js": "^2.6.0",
     "dayjs": "^1.11.13",
-    "debug": "^4.3.6",
+    "debug": "^4.3.7",
     "dexie": "^3.2.7",
     "diff": "^5.2.0",
-    "drizzle-orm": "^0.34.0",
+    "drizzle-orm": "^0.34.1",
     "drizzle-zod": "^0.5.1",
     "fast-deep-equal": "^3.1.3",
-    "file-type": "^19.4.1",
-    "framer-motion": "^11.2.6",
-    "gpt-tokenizer": "^2.2.1",
-    "i18next": "^23.14.0",
+    "file-type": "^19.6.0",
+    "framer-motion": "^11.11.9",
+    "gpt-tokenizer": "^2.5.0",
+    "i18next": "^23.16.1",
     "i18next-browser-languagedetector": "^7.2.1",
     "i18next-resources-to-backend": "^1.2.1",
     "idb-keyval": "^6.2.1",
     "immer": "^10.1.1",
     "ip": "^2.0.1",
-    "jose": "^5.7.0",
+    "jose": "^5.9.4",
     "js-sha256": "^0.11.0",
     "jsonl-parse-stringify": "^1.0.3",
-    "langchain": "^0.3.0",
-    "langfuse": "^3.19.0",
-    "langfuse-core": "^3.19.0",
+    "langchain": "^0.3.2",
+    "langfuse": "^3.27.0",
+    "langfuse-core": "^3.27.0",
     "lodash-es": "^4.17.21",
     "lucide-react": "latest",
     "mammoth": "^1.8.0",
@@ -175,51 +175,51 @@
     "next": "14.2.8",
     "next-auth": "beta",
     "next-mdx-remote": "^4.4.1",
-    "nextjs-toploader": "^3.6.15",
+    "nextjs-toploader": "^3.7.15",
     "numeral": "^2.0.6",
-    "nuqs": "^1.17.8",
-    "officeparser": "^4.1.1",
-    "ollama": "^0.5.8",
-    "openai": "^4.56.0",
-    "openapi-fetch": "^0.9.7",
+    "nuqs": "^1.20.0",
+    "officeparser": "^4.2.0",
+    "ollama": "^0.5.9",
+    "openai": "^4.68.1",
+    "openapi-fetch": "^0.9.8",
     "partial-json": "^0.1.7",
     "pdf-parse": "^1.1.1",
     "pdfjs-dist": "4.4.168",
-    "pg": "^8.12.0",
-    "pino": "^9.3.2",
+    "pg": "^8.13.0",
+    "pino": "^9.5.0",
     "polished": "^4.3.1",
-    "posthog-js": "^1.157.2",
-    "pwa-install-handler": "^2.6.0",
-    "query-string": "^9.1.0",
+    "posthog-js": "^1.174.2",
+    "pwa-install-handler": "^2.6.1",
+    "query-string": "^9.1.1",
     "random-words": "^2.0.1",
     "react": "^18.3.1",
     "react-confetti": "^6.1.0",
     "react-dom": "^18.3.1",
     "react-fast-marquee": "^1.6.5",
-    "react-hotkeys-hook": "^4.5.0",
+    "react-hotkeys-hook": "^4.5.1",
     "react-i18next": "14.0.2",
     "react-layout-kit": "^1.9.0",
     "react-lazy-load": "^4.0.1",
-    "react-pdf": "^9.1.0",
-    "react-virtuoso": "^4.10.1",
+    "react-pdf": "^9.1.1",
+    "react-virtuoso": "^4.12.0",
     "react-wrap-balancer": "^1.1.1",
     "remark": "^14.0.3",
     "remark-gfm": "^3.0.1",
     "remark-html": "^15.0.2",
     "request-filtering-agent": "^2.0.1",
-    "resolve-accept-language": "^3.1.5",
+    "resolve-accept-language": "^3.1.8",
     "rtl-detect": "^1.1.2",
     "semver": "^7.6.3",
     "sharp": "^0.33.5",
-    "shiki": "^1.21.0",
-    "stripe": "^15.8.0",
+    "shiki": "^1.22.0",
+    "stripe": "^15.12.0",
     "superjson": "^2.2.1",
-    "svix": "^1.30.0",
+    "svix": "^1.37.0",
     "swr": "^2.2.5",
     "systemjs": "^6.15.1",
     "ts-md5": "^1.3.1",
-    "ua-parser-js": "^1.0.38",
-    "unstructured-client": "^0.18.0",
+    "ua-parser-js": "^1.0.39",
+    "unstructured-client": "^0.18.1",
     "url-join": "^5.0.0",
     "use-merge-value": "^1.2.0",
     "utility-types": "^3.11.0",
@@ -227,60 +227,60 @@
     "ws": "^8.18.0",
     "y-protocols": "^1.0.6",
     "y-webrtc": "^10.3.0",
-    "yaml": "^2.5.0",
-    "yjs": "^13.6.18",
+    "yaml": "^2.6.0",
+    "yjs": "^13.6.20",
     "zod": "^3.23.8",
     "zustand": "^4.5.5",
     "zustand-utils": "^1.3.2"
   },
   "devDependencies": {
-    "@commitlint/cli": "^19.4.0",
-    "@edge-runtime/vm": "^4.0.2",
-    "@huggingface/tasks": "^0.12.12",
-    "@lobehub/i18n-cli": "^1.19.1",
+    "@commitlint/cli": "^19.5.0",
+    "@edge-runtime/vm": "^4.0.3",
+    "@huggingface/tasks": "^0.12.22",
+    "@lobehub/i18n-cli": "^1.20.0",
     "@lobehub/lint": "^1.24.4",
     "@lobehub/seo-cli": "^1.4.2",
-    "@next/bundle-analyzer": "^14.2.6",
-    "@next/eslint-plugin-next": "^14.2.6",
+    "@next/bundle-analyzer": "^14.2.15",
+    "@next/eslint-plugin-next": "^14.2.15",
     "@peculiar/webcrypto": "^1.5.0",
-    "@testing-library/jest-dom": "^6.4.8",
-    "@testing-library/react": "^16.0.0",
+    "@testing-library/jest-dom": "^6.6.2",
+    "@testing-library/react": "^16.0.1",
     "@types/chroma-js": "^2.4.4",
     "@types/debug": "^4.1.12",
-    "@types/diff": "^5.2.1",
+    "@types/diff": "^5.2.3",
     "@types/ip": "^1.1.3",
     "@types/json-schema": "^7.0.15",
-    "@types/lodash": "^4.17.7",
+    "@types/lodash": "^4.17.12",
     "@types/lodash-es": "^4.17.12",
-    "@types/node": "^20.16.1",
+    "@types/node": "^20.16.13",
     "@types/numeral": "^2.0.5",
-    "@types/pg": "^8.11.6",
-    "@types/react": "^18.3.4",
-    "@types/react-dom": "^18.3.0",
+    "@types/pg": "^8.11.10",
+    "@types/react": "^18.3.11",
+    "@types/react-dom": "^18.3.1",
     "@types/rtl-detect": "^1.0.3",
     "@types/semver": "^7.5.8",
-    "@types/systemjs": "^6.13.5",
+    "@types/systemjs": "^6.15.1",
     "@types/ua-parser-js": "^0.7.39",
     "@types/unist": "^3.0.3",
     "@types/uuid": "^10.0.0",
     "@types/ws": "^8.5.12",
     "@vitest/coverage-v8": "~1.2.2",
     "ajv-keywords": "^5.1.0",
-    "commitlint": "^19.4.0",
+    "commitlint": "^19.5.0",
     "consola": "^3.2.3",
     "dotenv": "^16.4.5",
     "dpdm": "^3.14.0",
     "drizzle-kit": "^0.25.0",
-    "eslint": "^8.57.0",
+    "eslint": "^8.57.1",
     "eslint-plugin-mdx": "^2.3.4",
     "eslint-plugin-unused-imports": "4.0.1",
     "fake-indexeddb": "^6.0.0",
     "glob": "^11.0.0",
     "gray-matter": "^4.0.3",
-    "happy-dom": "^15.0.0",
-    "husky": "^9.1.5",
+    "happy-dom": "^15.7.4",
+    "husky": "^9.1.6",
     "just-diff": "^6.0.2",
-    "lint-staged": "^15.2.9",
+    "lint-staged": "^15.2.10",
     "lodash": "^4.17.21",
     "markdown-table": "^3.0.3",
     "node-fetch": "^3.3.2",
@@ -291,14 +291,14 @@
     "remark-cli": "^11.0.0",
     "remark-parse": "^10.0.2",
     "semantic-release": "^21.1.2",
-    "serwist": "^9.0.8",
+    "serwist": "^9.0.9",
     "stylelint": "^15.11.0",
-    "supports-color": "8",
-    "tsx": "^4.17.0",
-    "typescript": "^5.5.4",
+    "supports-color": "^8.1.1",
+    "tsx": "^4.19.1",
+    "typescript": "^5.6.3",
     "unified": "^11.0.5",
     "unist-util-visit": "^5.0.0",
-    "vite": "^5.4.2",
+    "vite": "^5.4.9",
     "vitest": "~1.2.2",
     "vitest-canvas-mock": "^0.3.3"
   },

package/src/config/modelProviders/fireworksai.ts

@@ -30,6 +30,40 @@ const FireworksAI: ModelProviderCard = {
       tokens: 4096,
       vision: true,
     },
+    {
+      description:
+        'Llama 3.2 1B 指令模型是Meta推出的一款轻量级多语言模型。该模型旨在提高效率，与更大型的模型相比，在延迟和成本方面提供了显著的改进。该模型的示例用例包括检索和摘要。',
+      displayName: 'Llama 3.2 1B Instruct',
+      enabled: true,
+      id: 'accounts/fireworks/models/llama-v3p2-1b-instruct',
+      tokens: 131_072,
+    },
+    {
+      description:
+        'Llama 3.2 3B 指令模型是Meta推出的一款轻量级多语言模型。该模型旨在提高效率，与更大型的模型相比，在延迟和成本方面提供了显著的改进。该模型的示例用例包括查询和提示重写以及写作辅助。',
+      displayName: 'Llama 3.2 3B Instruct',
+      enabled: true,
+      id: 'accounts/fireworks/models/llama-v3p2-3b-instruct',
+      tokens: 131_072,
+    },
+    {
+      description:
+        'Meta的11B参数指令调整图像推理模型。该模型针对视觉识别、图像推理、图像描述和回答关于图像的一般性问题进行了优化。该模型能够理解视觉数据，如图表和图形，并通过生成文本描述图像细节来弥合视觉与语言之间的差距。',
+      displayName: 'Llama 3.2 11B Vision Instruct',
+      enabled: true,
+      id: 'accounts/fireworks/models/llama-v3p2-11b-vision-instruct',
+      tokens: 131_072,
+      vision: true,
+    },
+    {
+      description:
+        'Meta的90B参数指令调整图像推理模型。该模型针对视觉识别、图像推理、图像描述和回答关于图像的一般性问题进行了优化。该模型能够理解视觉数据，如图表和图形，并通过生成文本描述图像细节来弥合视觉与语言之间的差距。',
+      displayName: 'Llama 3.2 90B Vision Instruct',
+      enabled: true,
+      id: 'accounts/fireworks/models/llama-v3p2-90b-vision-instruct',
+      tokens: 131_072,
+      vision: true,
+    },
     {
       description:
         'Llama 3.1 8B 指令模型，专为多语言对话优化，能够在常见行业基准上超越多数开源及闭源模型。',
@@ -87,15 +121,6 @@ const FireworksAI: ModelProviderCard = {
       id: 'accounts/fireworks/models/llama-v3-70b-instruct-hf',
       tokens: 8192,
     },
-    {
-      description:
-        'Gemma 2 9B 指令模型，基于之前的Google技术，适合回答问题、总结和推理等多种文本生成任务。',
-      displayName: 'Gemma 2 9B Instruct',
-      enabled: true,
-      functionCall: false,
-      id: 'accounts/fireworks/models/gemma2-9b-it',
-      tokens: 8192,
-    },
     {
       description: 'Mixtral MoE 8x7B 指令模型，多专家架构提供高效的指令跟随及执行。',
       displayName: 'Mixtral MoE 8x7B Instruct',
@@ -123,14 +148,22 @@ const FireworksAI: ModelProviderCard = {
     },
     {
       description:
-        'Phi 3 Vision 指令模型，轻量级多模态模型，能够处理复杂的视觉和文本信息，具备较强的推理能力。',
-      displayName: 'Phi 3 Vision Instruct',
+        'Phi-3-Vision-128K-Instruct 是一个轻量级的、最先进的开放多模态模型，它基于包括合成数据和经过筛选的公开网站在内的数据集构建，专注于非常高质量、推理密集型的数据，这些数据既包括文本也包括视觉。该模型属于 Phi-3 模型系列，其多模态版本支持 128K 的上下文长度（以标记为单位）。该模型经过严格的增强过程，结合了监督微调和直接偏好优化，以确保精确遵循指令和强大的安全措施。',
+      displayName: 'Phi 3.5 Vision Instruct',
       enabled: true,
       functionCall: false,
       id: 'accounts/fireworks/models/phi-3-vision-128k-instruct',
-      tokens: 8192,
+      tokens: 32_064,
       vision: true,
     },
+    {
+      description: 'Qwen2.5 是由阿里云 Qwen 团队开发的一系列仅包含解码器的语言模型。这些模型提供不同的大小，包括 0.5B、1.5B、3B、7B、14B、32B 和 72B，并且有基础版（base）和指令版（instruct）两种变体。',
+      displayName: 'Qwen2.5 72B Instruct',
+      enabled: true,
+      functionCall: false,
+      id: 'accounts/fireworks/models/qwen2p5-72b-instruct',
+      tokens: 32_768,
+    },
     {
       description: 'Yi-Large 模型，具备卓越的多语言处理能力，可用于各类语言生成和理解任务。',
       displayName: 'Yi-Large',

package/src/libs/next-auth/sso-providers/azure-ad.ts

@@ -14,7 +14,7 @@ const provider = {
     // TODO(NextAuth ENVs Migration): Remove once nextauth envs migration time end
     clientId: authEnv.AZURE_AD_CLIENT_ID ?? process.env.AUTH_AZURE_AD_ID,
     clientSecret: authEnv.AZURE_AD_CLIENT_SECRET ?? process.env.AUTH_AZURE_AD_SECRET,
-    tenantId: authEnv.AZURE_AD_TENANT_ID ?? process.env.AUTH_AZURE_AD_TENANT_ID,
+    // tenantId: authEnv.AZURE_AD_TENANT_ID ?? process.env.AUTH_AZURE_AD_TENANT_ID,
     // Remove end
     // TODO(NextAuth): map unique user id to `providerAccountId` field
     // profile(profile) {