@lobehub/chat 1.36.33 → 1.36.34

package/README.md

@@ -8,7 +8,7 @@ An open-source, modern-design ChatGPT/LLMs UI/Framework.<br/>
 Supports speech-synthesis, multi-modal, and extensible ([function call][docs-functionc-call]) plugin system.<br/>
 One-click **FREE** deployment of your private OpenAI ChatGPT/Claude/Gemini/Groq/Ollama chat application.
 
-**English** · [简体中文](./README.zh-CN.md) · [日本語](./README.ja-JP.md) · [Official Site][official-site] · [Changelog](./CHANGELOG.md) · [Documents][docs] · [Blog][blog] · [Feedback][github-issues-link]
+**English** · [简体中文](./README.zh-CN.md) · [日本語](./README.ja-JP.md) · [Official Site][official-site] · [Changelog][changelog] · [Documents][docs] · [Blog][blog] · [Feedback][github-issues-link]
 
 <!-- SHIELD GROUP -->
 
@@ -141,21 +141,55 @@ In this way, LobeChat can more flexibly adapt to the needs of different users, w
 
 We have implemented support for the following model service providers:
 
-- **AWS Bedrock**: Integrated with AWS Bedrock service, supporting models such as **Claude / LLama2**, providing powerful natural language processing capabilities. [Learn more](https://aws.amazon.com/cn/bedrock)
-- **Anthropic (Claude)**: Accessed Anthropic's **Claude** series models, including Claude 3 and Claude 2, with breakthroughs in multi-modal capabilities and extended context, setting a new industry benchmark. [Learn more](https://www.anthropic.com/claude)
-- **Google AI (Gemini Pro, Gemini Vision)**: Access to Google's **Gemini** series models, including Gemini and Gemini Pro, to support advanced language understanding and generation. [Learn more](https://deepmind.google/technologies/gemini/)
-- **Groq**: Accessed Groq's AI models, efficiently processing message sequences and generating responses, capable of multi-turn dialogues and single-interaction tasks. [Learn more](https://groq.com/)
-- **OpenRouter**: Supports routing of models including **Claude 3**, **Gemma**, **Mistral**, **Llama2** and **Cohere**, with intelligent routing optimization to improve usage efficiency, open and flexible. [Learn more](https://openrouter.ai/)
-- **01.AI (Yi Model)**: Integrated the 01.AI models, with series of APIs featuring fast inference speed, which not only shortened the processing time, but also maintained excellent model performance. [Learn more](https://01.ai/)
-- **Together.ai**: Over 100 leading open-source Chat, Language, Image, Code, and Embedding models are available through the Together Inference API. For these models you pay just for what you use. [Learn more](https://www.together.ai/)
-- **ChatGLM**: Added the **ChatGLM** series models from Zhipuai (GLM-4/GLM-4-vision/GLM-3-turbo), providing users with another efficient conversation model choice. [Learn more](https://www.zhipuai.cn/)
-- **Moonshot AI (Dark Side of the Moon)**: Integrated with the Moonshot series models, an innovative AI startup from China, aiming to provide deeper conversation understanding. [Learn more](https://www.moonshot.cn/)
-- **Minimax**: Integrated the Minimax models, including the MoE model **abab6**, offers a broader range of choices. [Learn more](https://www.minimaxi.com/)
-- **DeepSeek**: Integrated with the DeepSeek series models, an innovative AI startup from China, The product has been designed to provide a model that balances performance with price. [Learn more](https://www.deepseek.com/)
-- **Qwen**: Integrated the Qwen series models, including the latest **qwen-turbo**, **qwen-plus** and **qwen-max**. [Learn more](https://help.aliyun.com/zh/dashscope/developer-reference/model-introduction)
-- **Novita AI**: Access **Llama**, **Mistral**, and other leading open-source models at cheapest prices. Engage in uncensored role-play, spark creative discussions, and foster unrestricted innovation. **Pay For What You Use.** [Learn more](https://novita.ai/llm-api?utm_source=lobechat&utm_medium=ch&utm_campaign=api)
-
-At the same time, we are also planning to support more model service providers, such as Replicate and Perplexity, to further enrich our service provider library. If you would like LobeChat to support your favorite service provider, feel free to join our [community discussion](https://github.com/lobehub/lobe-chat/discussions/1284).
+<!-- PROVIDER LIST -->
+
+- **[OpenAI](https://lobechat.com/discover/provider/openai)**: OpenAI is a global leader in artificial intelligence research, with models like the GPT series pushing the frontiers of natural language processing. OpenAI is committed to transforming multiple industries through innovative and efficient AI solutions. Their products demonstrate significant performance and cost-effectiveness, widely used in research, business, and innovative applications.
+- **[Ollama](https://lobechat.com/discover/provider/ollama)**: Ollama provides models that cover a wide range of fields, including code generation, mathematical operations, multilingual processing, and conversational interaction, catering to diverse enterprise-level and localized deployment needs.
+- **[Anthropic](https://lobechat.com/discover/provider/anthropic)**: Anthropic is a company focused on AI research and development, offering a range of advanced language models such as Claude 3.5 Sonnet, Claude 3 Sonnet, Claude 3 Opus, and Claude 3 Haiku. These models achieve an ideal balance between intelligence, speed, and cost, suitable for various applications from enterprise workloads to rapid-response scenarios. Claude 3.5 Sonnet, as their latest model, has excelled in multiple evaluations while maintaining a high cost-performance ratio.
+- **[Bedrock](https://lobechat.com/discover/provider/bedrock)**: Bedrock is a service provided by Amazon AWS, focusing on delivering advanced AI language and visual models for enterprises. Its model family includes Anthropic's Claude series, Meta's Llama 3.1 series, and more, offering a range of options from lightweight to high-performance, supporting tasks such as text generation, conversation, and image processing for businesses of varying scales and needs.
+- **[Google](https://lobechat.com/discover/provider/google)**: Google's Gemini series represents its most advanced, versatile AI models, developed by Google DeepMind, designed for multimodal capabilities, supporting seamless understanding and processing of text, code, images, audio, and video. Suitable for various environments from data centers to mobile devices, it significantly enhances the efficiency and applicability of AI models.
+- **[DeepSeek](https://lobechat.com/discover/provider/deepseek)**: DeepSeek is a company focused on AI technology research and application, with its latest model DeepSeek-V2.5 integrating general dialogue and code processing capabilities, achieving significant improvements in human preference alignment, writing tasks, and instruction following.
+- **[HuggingFace](https://lobechat.com/discover/provider/huggingface)**: The HuggingFace Inference API provides a fast and free way for you to explore thousands of models for various tasks. Whether you are prototyping for a new application or experimenting with the capabilities of machine learning, this API gives you instant access to high-performance models across multiple domains.
+- **[OpenRouter](https://lobechat.com/discover/provider/openrouter)**: OpenRouter is a service platform providing access to various cutting-edge large model interfaces, supporting OpenAI, Anthropic, LLaMA, and more, suitable for diverse development and application needs. Users can flexibly choose the optimal model and pricing based on their requirements, enhancing the AI experience.
+- **[Cloudflare Workers AI](https://lobechat.com/discover/provider/cloudflare)**: Run serverless GPU-powered machine learning models on Cloudflare's global network.
+- **[GitHub](https://lobechat.com/discover/provider/github)**: With GitHub Models, developers can become AI engineers and leverage the industry's leading AI models.
+
+<details><summary><kbd>See more providers (+26)</kbd></summary>
+
+- **[Novita](https://lobechat.com/discover/provider/novita)**: Novita AI is a platform providing a variety of large language models and AI image generation API services, flexible, reliable, and cost-effective. It supports the latest open-source models like Llama3 and Mistral, offering a comprehensive, user-friendly, and auto-scaling API solution for generative AI application development, suitable for the rapid growth of AI startups.
+- **[Together AI](https://lobechat.com/discover/provider/togetherai)**: Together AI is dedicated to achieving leading performance through innovative AI models, offering extensive customization capabilities, including rapid scaling support and intuitive deployment processes to meet various enterprise needs.
+- **[Fireworks AI](https://lobechat.com/discover/provider/fireworksai)**: Fireworks AI is a leading provider of advanced language model services, focusing on functional calling and multimodal processing. Its latest model, Firefunction V2, is based on Llama-3, optimized for function calling, conversation, and instruction following. The visual language model FireLLaVA-13B supports mixed input of images and text. Other notable models include the Llama series and Mixtral series, providing efficient multilingual instruction following and generation support.
+- **[Groq](https://lobechat.com/discover/provider/groq)**: Groq's LPU inference engine has excelled in the latest independent large language model (LLM) benchmarks, redefining the standards for AI solutions with its remarkable speed and efficiency. Groq represents instant inference speed, demonstrating strong performance in cloud-based deployments.
+- **[Perplexity](https://lobechat.com/discover/provider/perplexity)**: Perplexity is a leading provider of conversational generation models, offering various advanced Llama 3.1 models that support both online and offline applications, particularly suited for complex natural language processing tasks.
+- **[Mistral](https://lobechat.com/discover/provider/mistral)**: Mistral provides advanced general, specialized, and research models widely used in complex reasoning, multilingual tasks, and code generation. Through functional calling interfaces, users can integrate custom functionalities for specific applications.
+- **[Ai21Labs](https://lobechat.com/discover/provider/ai21)**: AI21 Labs builds foundational models and AI systems for enterprises, accelerating the application of generative AI in production.
+- **[Upstage](https://lobechat.com/discover/provider/upstage)**: Upstage focuses on developing AI models for various business needs, including Solar LLM and document AI, aiming to achieve artificial general intelligence (AGI) for work. It allows for the creation of simple conversational agents through Chat API and supports functional calling, translation, embedding, and domain-specific applications.
+- **[xAI](https://lobechat.com/discover/provider/xai)**: xAI is a company dedicated to building artificial intelligence to accelerate human scientific discovery. Our mission is to advance our collective understanding of the universe.
+- **[Qwen](https://lobechat.com/discover/provider/qwen)**: Tongyi Qianwen is a large-scale language model independently developed by Alibaba Cloud, featuring strong natural language understanding and generation capabilities. It can answer various questions, create written content, express opinions, and write code, playing a role in multiple fields.
+- **[Wenxin](https://lobechat.com/discover/provider/wenxin)**: An enterprise-level one-stop platform for large model and AI-native application development and services, providing the most comprehensive and user-friendly toolchain for the entire process of generative artificial intelligence model development and application development.
+- **[Hunyuan](https://lobechat.com/discover/provider/hunyuan)**: A large language model developed by Tencent, equipped with powerful Chinese creative capabilities, logical reasoning abilities in complex contexts, and reliable task execution skills.
+- **[Spark](https://lobechat.com/discover/provider/spark)**: iFlytek's Spark model provides powerful AI capabilities across multiple domains and languages, utilizing advanced natural language processing technology to build innovative applications suitable for smart hardware, smart healthcare, smart finance, and other vertical scenarios.
+- **[ZhiPu](https://lobechat.com/discover/provider/zhipu)**: Zhipu AI offers an open platform for multimodal and language models, supporting a wide range of AI application scenarios, including text processing, image understanding, and programming assistance.
+- **[01.AI](https://lobechat.com/discover/provider/zeroone)**: 01.AI focuses on AI 2.0 era technologies, vigorously promoting the innovation and application of 'human + artificial intelligence', using powerful models and advanced AI technologies to enhance human productivity and achieve technological empowerment.
+- **[SenseNova](https://lobechat.com/discover/provider/sensenova)**: SenseNova, backed by SenseTime's robust infrastructure, offers efficient and user-friendly full-stack large model services.
+- **[Stepfun](https://lobechat.com/discover/provider/stepfun)**: StepFun's large model possesses industry-leading multimodal and complex reasoning capabilities, supporting ultra-long text understanding and powerful autonomous scheduling search engine functions.
+- **[Moonshot](https://lobechat.com/discover/provider/moonshot)**: Moonshot is an open-source platform launched by Beijing Dark Side Technology Co., Ltd., providing various natural language processing models with a wide range of applications, including but not limited to content creation, academic research, intelligent recommendations, and medical diagnosis, supporting long text processing and complex generation tasks.
+- **[Baichuan](https://lobechat.com/discover/provider/baichuan)**: Baichuan Intelligence is a company focused on the research and development of large AI models, with its models excelling in domestic knowledge encyclopedias, long text processing, and generative creation tasks in Chinese, surpassing mainstream foreign models. Baichuan Intelligence also possesses industry-leading multimodal capabilities, performing excellently in multiple authoritative evaluations. Its models include Baichuan 4, Baichuan 3 Turbo, and Baichuan 3 Turbo 128k, each optimized for different application scenarios, providing cost-effective solutions.
+- **[Minimax](https://lobechat.com/discover/provider/minimax)**: MiniMax is a general artificial intelligence technology company established in 2021, dedicated to co-creating intelligence with users. MiniMax has independently developed general large models of different modalities, including trillion-parameter MoE text models, voice models, and image models, and has launched applications such as Conch AI.
+- **[360 AI](https://lobechat.com/discover/provider/ai360)**: 360 AI is an AI model and service platform launched by 360 Company, offering various advanced natural language processing models, including 360GPT2 Pro, 360GPT Pro, 360GPT Turbo, and 360GPT Turbo Responsibility 8K. These models combine large-scale parameters and multimodal capabilities, widely applied in text generation, semantic understanding, dialogue systems, and code generation. With flexible pricing strategies, 360 AI meets diverse user needs, supports developer integration, and promotes the innovation and development of intelligent applications.
+- **[Taichu](https://lobechat.com/discover/provider/taichu)**: The Institute of Automation, Chinese Academy of Sciences, and Wuhan Artificial Intelligence Research Institute have launched a new generation of multimodal large models, supporting comprehensive question-answering tasks such as multi-turn Q\&A, text creation, image generation, 3D understanding, and signal analysis, with stronger cognitive, understanding, and creative abilities, providing a new interactive experience.
+- **[InternLM](https://lobechat.com/discover/provider/internlm)**: An open-source organization dedicated to the research and development of large model toolchains. It provides an efficient and user-friendly open-source platform for all AI developers, making cutting-edge large models and algorithm technologies easily accessible.
+- **[SiliconCloud](https://lobechat.com/discover/provider/siliconcloud)**: SiliconFlow is dedicated to accelerating AGI for the benefit of humanity, enhancing large-scale AI efficiency through an easy-to-use and cost-effective GenAI stack.
+- **[Higress](https://lobechat.com/discover/provider/higress)**: Higress is a cloud-native API gateway that was developed internally at Alibaba to address the issues of Tengine reload affecting long-lived connections and the insufficient load balancing capabilities for gRPC/Dubbo.
+- **[Gitee AI](https://lobechat.com/discover/provider/giteeai)**: Gitee AI's Serverless API provides AI developers with an out of the box large model inference API service.
+
+</details>
+
+> 📊 Total providers: [<kbd>**36**</kbd>](https://lobechat.com/discover/providers)
+
+ <!-- PROVIDER LIST -->
+
+At the same time, we are also planning to support more model service providers. If you would like LobeChat to support your favorite service provider, feel free to join our [💬 community discussion](https://github.com/lobehub/lobe-chat/discussions/1284).
 
 <div align="right">
 
@@ -248,12 +282,12 @@ In addition, these plugins are not limited to news aggregation, but can also ext
 
 | Recent Submits                                                                                                 | Description                                                                                                          |
 | -------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------- |
-| [Google CSE](https://chat-preview.lobehub.com/settings/agent)<br/><sup>By **vsnthdev** on **2024-12-02**</sup> | Searches Google through their official CSE API.<br/>`web` `search`                                                   |
-| [Google CSE](https://chat-preview.lobehub.com/settings/agent)<br/><sup>By **vsnthdev** on **2024-12-02**</sup> | Searches Google through their official CSE API.<br/>`web` `search`                                                   |
-| [Speak](https://chat-preview.lobehub.com/settings/agent)<br/><sup>By **speak** on **2024-12-02**</sup>         | Learn how to say anything in another language with Speak, your AI-powered language tutor.<br/>`education` `language` |
-| [Speak](https://chat-preview.lobehub.com/settings/agent)<br/><sup>By **speak** on **2024-12-02**</sup>         | Learn how to say anything in another language with Speak, your AI-powered language tutor.<br/>`education` `language` |
+| [Google CSE](https://lobechat.com/discover/plugin/google-cse)<br/><sup>By **vsnthdev** on **2024-12-02**</sup> | Searches Google through their official CSE API.<br/>`web` `search`                                                   |
+| [Google CSE](https://lobechat.com/discover/plugin/google-cse)<br/><sup>By **vsnthdev** on **2024-12-02**</sup> | Searches Google through their official CSE API.<br/>`web` `search`                                                   |
+| [Speak](https://lobechat.com/discover/plugin/speak)<br/><sup>By **speak** on **2024-12-02**</sup>              | Learn how to say anything in another language with Speak, your AI-powered language tutor.<br/>`education` `language` |
+| [Speak](https://lobechat.com/discover/plugin/speak)<br/><sup>By **speak** on **2024-12-02**</sup>              | Learn how to say anything in another language with Speak, your AI-powered language tutor.<br/>`education` `language` |
 
-> 📊 Total plugins: [<kbd>**98**</kbd>](https://github.com/lobehub/lobe-chat-plugins)
+> 📊 Total plugins: [<kbd>**98**</kbd>](https://lobechat.com/discover/plugins)
 
  <!-- PLUGIN LIST -->
 
@@ -285,14 +319,14 @@ Our marketplace is not just a showcase platform but also a collaborative space.
 
 <!-- AGENT LIST -->
 
-| Recent Submits                                                                                                                                                                       | Description                                                                                                                                                              |
-| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| [System Instruction Expert](https://chat-preview.lobehub.com/market?agent=instructer)<br/><sup>By **[yuyun2000](https://github.com/yuyun2000)** on **undefined**</sup>               | Skilled in refining and generating efficient system instructions<br/>`system-instructions` `writing` `detail-optimization` `user-needs`                                  |
-| [Japanese Memory Helper](https://chat-preview.lobehub.com/market?agent=japan-language-helper)<br/><sup>By **[sharkbear212](https://github.com/sharkbear212)** on **undefined**</sup> | Specializes in Japanese Hiragana, Katakana, vocabulary, and memory techniques for explanations and phrases<br/>`explanation` `memory-techniques` `japanese-teaching`     |
-| [Poetry Card Designer](https://chat-preview.lobehub.com/market?agent=poetry-card-designer)<br/><sup>By **[lianxin255](https://github.com/lianxin255)** on **undefined**</sup>        | Skilled in designing poetry cards to enhance artistic sense and appeal<br/>`poetry-card-design` `card` `creativity` `artistic-expression`                                |
-| [Daily Doctor](https://chat-preview.lobehub.com/market?agent=yunchat-docter)<br/><sup>By **[yuyun2000](https://github.com/yuyun2000)** on **undefined**</sup>                        | Specializes in surgical diagnosis and personalized health management<br/>`general-medicine` `surgery` `health-consultation` `personalized-treatment` `medical-education` |
+| Recent Submits                                                                                                                                                                  | Description                                                                                                                                                              |
+| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| [System Instruction Expert](https://lobechat.com/discover/assistant/instructer)<br/><sup>By **[yuyun2000](https://github.com/yuyun2000)** on **2024-12-04**</sup>               | Skilled in refining and generating efficient system instructions<br/>`system-instructions` `writing` `detail-optimization` `user-needs`                                  |
+| [Japanese Memory Helper](https://lobechat.com/discover/assistant/japan-language-helper)<br/><sup>By **[sharkbear212](https://github.com/sharkbear212)** on **2024-12-04**</sup> | Specializes in Japanese Hiragana, Katakana, vocabulary, and memory techniques for explanations and phrases<br/>`explanation` `memory-techniques` `japanese-teaching`     |
+| [Poetry Card Designer](https://lobechat.com/discover/assistant/poetry-card-designer)<br/><sup>By **[lianxin255](https://github.com/lianxin255)** on **2024-12-03**</sup>        | Skilled in designing poetry cards to enhance artistic sense and appeal<br/>`poetry-card-design` `card` `creativity` `artistic-expression`                                |
+| [Daily Doctor](https://lobechat.com/discover/assistant/yunchat-docter)<br/><sup>By **[yuyun2000](https://github.com/yuyun2000)** on **2024-11-30**</sup>                        | Specializes in surgical diagnosis and personalized health management<br/>`general-medicine` `surgery` `health-consultation` `personalized-treatment` `medical-education` |
 
-> 📊 Total agents: [<kbd>**453**</kbd> ](https://github.com/lobehub/lobe-chat-agents)
+> 📊 Total agents: [<kbd>**453**</kbd> ](https://lobechat.com/discover/assistants)
 
  <!-- AGENT LIST -->
 
@@ -692,6 +726,7 @@ This project is [Apache 2.0](./LICENSE) licensed.
 
 [back-to-top]: https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square
 [blog]: https://lobehub.com/blog
+[changelog]: https://lobehub.com/changelog
 [chat-desktop]: https://raw.githubusercontent.com/lobehub/lobe-chat/lighthouse/lighthouse/chat/desktop/pagespeed.svg
 [chat-desktop-report]: https://lobehub.github.io/lobe-chat/lighthouse/chat/desktop/chat_preview_lobehub_com_chat.html
 [chat-mobile]: https://raw.githubusercontent.com/lobehub/lobe-chat/lighthouse/lighthouse/chat/mobile/pagespeed.svg

package/README.zh-CN.md

@@ -8,7 +8,7 @@
 支持语音合成、多模态、可扩展的（[function call][docs-functionc-call]）插件系统<br/>
 一键**免费**拥有你自己的 ChatGPT/Gemini/Claude/Ollama 应用
 
-[English](./README.md) · **简体中文** · [日本語](./README.ja-JP.md) · [官网][official-site] · [更新日志](./CHANGELOG.md) · [文档][docs] · [博客][blog] · [反馈问题][github-issues-link]
+[English](./README.md) · **简体中文** · [日本語](./README.ja-JP.md) · [官网][official-site] · [更新日志][changelog] · [文档][docs] · [博客][blog] · [反馈问题][github-issues-link]
 
 <!-- SHIELD GROUP -->
 
@@ -141,21 +141,55 @@ LobeChat 支持文件上传与知识库功能，你可以上传文件、图片
 
 我们已经实现了对以下模型服务商的支持：
 
-- **AWS Bedrock**：集成了 AWS Bedrock 服务，支持了 **Claude / LLama2** 等模型，提供了强大的自然语言处理能力。[了解更多](https://aws.amazon.com/cn/bedrock)
-- **Google AI (Gemini Pro、Gemini Vision)**：接入了 Google 的 **Gemini** 系列模型，包括 Gemini 和 Gemini Pro，以支持更高级的语言理解和生成。[了解更多](https://deepmind.google/technologies/gemini/)
-- **Anthropic (Claude)**：接入了 Anthropic 的 **Claude** 系列模型，包括 Claude 3 和 Claude 2，多模态突破，超长上下文，树立行业新基准。[了解更多](https://www.anthropic.com/claude)
-- **ChatGLM**：加入了智谱的 **ChatGLM** 系列模型（GLM-4/GLM-4-vision/GLM-3-turbo），为用户提供了另一种高效的会话模型选择。[了解更多](https://www.zhipuai.cn/)
-- **Moonshot AI (月之暗面)**：集成了 Moonshot 系列模型，这是一家来自中国的创新性 AI 创业公司，旨在提供更深层次的会话理解。[了解更多](https://www.moonshot.cn/)
-- **Together.ai**：集成部署了数百种开源模型和向量模型，无需本地部署即可随时访问这些模型。[了解更多](https://www.together.ai/)
-- **01.AI (零一万物)**：集成了零一万物模型，系列 API 具备较快的推理速度，这不仅缩短了处理时间，同时也保持了出色的模型效果。[了解更多](https://www.lingyiwanwu.com/)
-- **Groq**：接入了 Groq 的 AI 模型，高效处理消息序列，生成回应，胜任多轮对话及单次交互任务。[了解更多](https://groq.com/)
-- **OpenRouter**：其支持包括 **Claude 3**，**Gemma**，**Mistral**，**Llama2**和**Cohere**等模型路由，支持智能路由优化，提升使用效率，开放且灵活。[了解更多](https://openrouter.ai/)
-- **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)。
+<!-- PROVIDER LIST -->
+
+- **[OpenAI](https://lobechat.com/discover/provider/openai)**: OpenAI 是全球领先的人工智能研究机构，其开发的模型如 GPT 系列推动了自然语言处理的前沿。OpenAI 致力于通过创新和高效的 AI 解决方案改变多个行业。他们的产品具有显著的性能和经济性，广泛用于研究、商业和创新应用。
+- **[Ollama](https://lobechat.com/discover/provider/ollama)**: Ollama 提供的模型广泛涵盖代码生成、数学运算、多语种处理和对话互动等领域，支持企业级和本地化部署的多样化需求。
+- **[Anthropic](https://lobechat.com/discover/provider/anthropic)**: Anthropic 是一家专注于人工智能研究和开发的公司，提供了一系列先进的语言模型，如 Claude 3.5 Sonnet、Claude 3 Sonnet、Claude 3 Opus 和 Claude 3 Haiku。这些模型在智能、速度和成本之间取得了理想的平衡，适用于从企业级工作负载到快速响应的各种应用场景。Claude 3.5 Sonnet 作为其最新模型，在多项评估中表现优异，同时保持了较高的性价比。
+- **[Bedrock](https://lobechat.com/discover/provider/bedrock)**: Bedrock 是亚马逊 AWS 提供的一项服务，专注于为企业提供先进的 AI 语言模型和视觉模型。其模型家族包括 Anthropic 的 Claude 系列、Meta 的 Llama 3.1 系列等，涵盖从轻量级到高性能的多种选择，支持文本生成、对话、图像处理等多种任务，适用于不同规模和需求的企业应用。
+- **[Google](https://lobechat.com/discover/provider/google)**: Google 的 Gemini 系列是其最先进、通用的 AI 模型，由 Google DeepMind 打造，专为多模态设计，支持文本、代码、图像、音频和视频的无缝理解与处理。适用于从数据中心到移动设备的多种环境，极大提升了 AI 模型的效率与应用广泛性。
+- **[DeepSeek](https://lobechat.com/discover/provider/deepseek)**: DeepSeek 是一家专注于人工智能技术研究和应用的公司，其最新模型 DeepSeek-V2.5 融合了通用对话和代码处理能力，并在人类偏好对齐、写作任务和指令跟随等方面实现了显著提升。
+- **[HuggingFace](https://lobechat.com/discover/provider/huggingface)**: HuggingFace Inference API 提供了一种快速且免费的方式，让您可以探索成千上万种模型，适用于各种任务。无论您是在为新应用程序进行原型设计，还是在尝试机器学习的功能，这个 API 都能让您即时访问多个领域的高性能模型。
+- **[OpenRouter](https://lobechat.com/discover/provider/openrouter)**: OpenRouter 是一个提供多种前沿大模型接口的服务平台，支持 OpenAI、Anthropic、LLaMA 及更多，适合多样化的开发和应用需求。用户可根据自身需求灵活选择最优的模型和价格，助力 AI 体验的提升。
+- **[Cloudflare Workers AI](https://lobechat.com/discover/provider/cloudflare)**: 在 Cloudflare 的全球网络上运行由无服务器 GPU 驱动的机器学习模型。
+- **[GitHub](https://lobechat.com/discover/provider/github)**: 通过 GitHub 模型，开发人员可以成为 AI 工程师，并使用行业领先的 AI 模型进行构建。
+
+<details><summary><kbd>See more providers (+26)</kbd></summary>
+
+- **[Novita](https://lobechat.com/discover/provider/novita)**: Novita AI 是一个提供多种大语言模型与 AI 图像生成的 API 服务的平台，灵活、可靠且具有成本效益。它支持 Llama3、Mistral 等最新的开源模型，并为生成式 AI 应用开发提供了全面、用户友好且自动扩展的 API 解决方案，适合 AI 初创公司的快速发展。
+- **[Together AI](https://lobechat.com/discover/provider/togetherai)**: Together AI 致力于通过创新的 AI 模型实现领先的性能，提供广泛的自定义能力，包括快速扩展支持和直观的部署流程，满足企业的各种需求。
+- **[Fireworks AI](https://lobechat.com/discover/provider/fireworksai)**: Fireworks AI 是一家领先的高级语言模型服务商，专注于功能调用和多模态处理。其最新模型 Firefunction V2 基于 Llama-3，优化用于函数调用、对话及指令跟随。视觉语言模型 FireLLaVA-13B 支持图像和文本混合输入。其他 notable 模型包括 Llama 系列和 Mixtral 系列，提供高效的多语言指令跟随与生成支持。
+- **[Groq](https://lobechat.com/discover/provider/groq)**: Groq 的 LPU 推理引擎在最新的独立大语言模型（LLM）基准测试中表现卓越，以其惊人的速度和效率重新定义了 AI 解决方案的标准。Groq 是一种即时推理速度的代表，在基于云的部署中展现了良好的性能。
+- **[Perplexity](https://lobechat.com/discover/provider/perplexity)**: Perplexity 是一家领先的对话生成模型提供商，提供多种先进的 Llama 3.1 模型，支持在线和离线应用，特别适用于复杂的自然语言处理任务。
+- **[Mistral](https://lobechat.com/discover/provider/mistral)**: Mistral 提供先进的通用、专业和研究型模型，广泛应用于复杂推理、多语言任务、代码生成等领域，通过功能调用接口，用户可以集成自定义功能，实现特定应用。
+- **[Ai21Labs](https://lobechat.com/discover/provider/ai21)**: AI21 Labs 为企业构建基础模型和人工智能系统，加速生成性人工智能在生产中的应用。
+- **[Upstage](https://lobechat.com/discover/provider/upstage)**: Upstage 专注于为各种商业需求开发 AI 模型，包括 Solar LLM 和文档 AI，旨在实现工作的人造通用智能（AGI）。通过 Chat API 创建简单的对话代理，并支持功能调用、翻译、嵌入以及特定领域应用。
+- **[xAI](https://lobechat.com/discover/provider/xai)**: xAI 是一家致力于构建人工智能以加速人类科学发现的公司。我们的使命是推动我们对宇宙的共同理解。
+- **[Qwen](https://lobechat.com/discover/provider/qwen)**: 通义千问是阿里云自主研发的超大规模语言模型，具有强大的自然语言理解和生成能力。它可以回答各种问题、创作文字内容、表达观点看法、撰写代码等，在多个领域发挥作用。
+- **[Wenxin](https://lobechat.com/discover/provider/wenxin)**: 企业级一站式大模型与 AI 原生应用开发及服务平台，提供最全面易用的生成式人工智能模型开发、应用开发全流程工具链
+- **[Hunyuan](https://lobechat.com/discover/provider/hunyuan)**: 由腾讯研发的大语言模型，具备强大的中文创作能力，复杂语境下的逻辑推理能力，以及可靠的任务执行能力
+- **[Spark](https://lobechat.com/discover/provider/spark)**: 科大讯飞星火大模型提供多领域、多语言的强大 AI 能力，利用先进的自然语言处理技术，构建适用于智能硬件、智慧医疗、智慧金融等多种垂直场景的创新应用。
+- **[ZhiPu](https://lobechat.com/discover/provider/zhipu)**: 智谱 AI 提供多模态与语言模型的开放平台，支持广泛的 AI 应用场景，包括文本处理、图像理解与编程辅助等。
+- **[01.AI](https://lobechat.com/discover/provider/zeroone)**: 零一万物致力于推动以人为本的 AI 2.0 技术革命，旨在通过大语言模型创造巨大的经济和社会价值，并开创新的 AI 生态与商业模式。
+- **[SenseNova](https://lobechat.com/discover/provider/sensenova)**: 商汤日日新，依托商汤大装置的强大的基础支撑，提供高效易用的全栈大模型服务。
+- **[Stepfun](https://lobechat.com/discover/provider/stepfun)**: 阶级星辰大模型具备行业领先的多模态及复杂推理能力，支持超长文本理解和强大的自主调度搜索引擎功能。
+- **[Moonshot](https://lobechat.com/discover/provider/moonshot)**: Moonshot 是由北京月之暗面科技有限公司推出的开源平台，提供多种自然语言处理模型，应用领域广泛，包括但不限于内容创作、学术研究、智能推荐、医疗诊断等，支持长文本处理和复杂生成任务。
+- **[Baichuan](https://lobechat.com/discover/provider/baichuan)**: 百川智能是一家专注于人工智能大模型研发的公司，其模型在国内知识百科、长文本处理和生成创作等中文任务上表现卓越，超越了国外主流模型。百川智能还具备行业领先的多模态能力，在多项权威评测中表现优异。其模型包括 Baichuan 4、Baichuan 3 Turbo 和 Baichuan 3 Turbo 128k 等，分别针对不同应用场景进行优化，提供高性价比的解决方案。
+- **[Minimax](https://lobechat.com/discover/provider/minimax)**: MiniMax 是 2021 年成立的通用人工智能科技公司，致力于与用户共创智能。MiniMax 自主研发了不同模态的通用大模型，其中包括万亿参数的 MoE 文本大模型、语音大模型以及图像大模型。并推出了海螺 AI 等应用。
+- **[360 AI](https://lobechat.com/discover/provider/ai360)**: 360 AI 是 360 公司推出的 AI 模型和服务平台，提供多种先进的自然语言处理模型，包括 360GPT2 Pro、360GPT Pro、360GPT Turbo 和 360GPT Turbo Responsibility 8K。这些模型结合了大规模参数和多模态能力，广泛应用于文本生成、语义理解、对话系统与代码生成等领域。通过灵活的定价策略，360 AI 满足多样化用户需求，支持开发者集成，推动智能化应用的革新和发展。
+- **[Taichu](https://lobechat.com/discover/provider/taichu)**: 中科院自动化研究所和武汉人工智能研究院推出新一代多模态大模型，支持多轮问答、文本创作、图像生成、3D 理解、信号分析等全面问答任务，拥有更强的认知、理解、创作能力，带来全新互动体验。
+- **[InternLM](https://lobechat.com/discover/provider/internlm)**: 致力于大模型研究与开发工具链的开源组织。为所有 AI 开发者提供高效、易用的开源平台，让最前沿的大模型与算法技术触手可及
+- **[SiliconCloud](https://lobechat.com/discover/provider/siliconcloud)**: SiliconCloud，基于优秀开源基础模型的高性价比 GenAI 云服务
+- **[Higress](https://lobechat.com/discover/provider/higress)**: Higress 是一款云原生 API 网关，在阿里内部为解决 Tengine reload 对长连接业务有损，以及 gRPC/Dubbo 负载均衡能力不足而诞生。
+- **[Gitee AI](https://lobechat.com/discover/provider/giteeai)**: Gitee AI 的 Serverless API 为 AI 开发者提供开箱即用的大模型推理 API 服务。
+
+</details>
+
+> 📊 Total providers: [<kbd>**36**</kbd>](https://lobechat.com/discover/providers)
+
+ <!-- PROVIDER LIST -->
+
+同时，我们也在计划支持更多的模型服务商，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)。
 
 <div align="right">
 
@@ -239,14 +273,14 @@ LobeChat 的插件生态系统是其核心功能的重要扩展，它极大地
 
 <!-- PLUGIN LIST -->
 
-| 最近新增                                                                                                               | 插件描述                                                                                                           |
-| ---------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------ |
-| [谷歌自定义搜索引擎](https://chat-preview.lobehub.com/settings/agent)<br/><sup>By **vsnthdev** on **2024-12-02**</sup> | 通过他们的官方自定义搜索引擎 API 搜索谷歌。<br/>`网络` `搜索`                                                      |
-| [Speak](https://chat-preview.lobehub.com/settings/agent)<br/><sup>By **speak** on **2024-12-02**</sup>                 | 使用 Speak，您的 AI 语言导师，学习如何用另一种语言说任何事情。<br/>`教育` `语言`                                   |
-| [通义万象图像生成器](https://chat-preview.lobehub.com/settings/agent)<br/><sup>By **YoungTx** on **2024-08-09**</sup>  | 此插件使用阿里巴巴的通义万象模型根据文本提示生成图像。<br/>`图像` `通义` `万象`                                    |
-| [购物工具](https://chat-preview.lobehub.com/settings/agent)<br/><sup>By **shoppingtools** on **2024-07-19**</sup>      | 在 eBay 和 AliExpress 上搜索产品，查找 eBay 活动和优惠券。获取快速示例。<br/>`购物` `e-bay` `ali-express` `优惠券` |
+| 最近新增                                                                                                                     | 描述                                                                                                               |
+| ---------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------ |
+| [谷歌自定义搜索引擎](https://lobechat.com/discover/plugin/google-cse)<br/><sup>By **vsnthdev** on **2024-12-02**</sup>       | 通过他们的官方自定义搜索引擎 API 搜索谷歌。<br/>`网络` `搜索`                                                      |
+| [Speak](https://lobechat.com/discover/plugin/speak)<br/><sup>By **speak** on **2024-12-02**</sup>                            | 使用 Speak，您的 AI 语言导师，学习如何用另一种语言说任何事情。<br/>`教育` `语言`                                   |
+| [通义万象图像生成器](https://lobechat.com/discover/plugin/alps-tongyi-image)<br/><sup>By **YoungTx** on **2024-08-09**</sup> | 此插件使用阿里巴巴的通义万象模型根据文本提示生成图像。<br/>`图像` `通义` `万象`                                    |
+| [购物工具](https://lobechat.com/discover/plugin/ShoppingTools)<br/><sup>By **shoppingtools** on **2024-07-19**</sup>         | 在 eBay 和 AliExpress 上搜索产品，查找 eBay 活动和优惠券。获取快速示例。<br/>`购物` `e-bay` `ali-express` `优惠券` |
 
-> 📊 Total plugins: [<kbd>**49**</kbd>](https://github.com/lobehub/lobe-chat-plugins)
+> 📊 Total plugins: [<kbd>**49**</kbd>](https://lobechat.com/discover/plugins)
 
  <!-- PLUGIN LIST -->
 
@@ -274,14 +308,14 @@ LobeChat 的插件生态系统是其核心功能的重要扩展，它极大地
 
 <!-- AGENT LIST -->
 
-| 最近新增                                                                                                                                                                     | 助手说明                                                                                  |
-| ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------- |
-| [系统指令专家](https://chat-preview.lobehub.com/market?agent=instructer)<br/><sup>By **[yuyun2000](https://github.com/yuyun2000)** on **undefined**</sup>                    | 擅长精炼与生成高效系统指令<br/>`系统指令` `写作` `细节优化` `用户需求`                    |
-| [日语帮助记忆师](https://chat-preview.lobehub.com/market?agent=japan-language-helper)<br/><sup>By **[sharkbear212](https://github.com/sharkbear212)** on **undefined**</sup> | 擅长日语五十音，平假名，片假名，单词和短语解释与记忆技巧<br/>`解释` `记忆技巧` `日语教学` |
-| [诗词卡片设计师](https://chat-preview.lobehub.com/market?agent=poetry-card-designer)<br/><sup>By **[lianxin255](https://github.com/lianxin255)** on **undefined**</sup>      | 擅长设计诗词卡片，提升艺术感与吸引力<br/>`诗词卡片设计` `卡片` `创意` `艺术表现`          |
-| [日常医生](https://chat-preview.lobehub.com/market?agent=yunchat-docter)<br/><sup>By **[yuyun2000](https://github.com/yuyun2000)** on **undefined**</sup>                    | 擅长外科诊疗与个性化健康管理<br/>`全科医学` `外科` `健康咨询` `个性化治疗` `医学教育`     |
+| 最近新增                                                                                                                                                                | 描述                                                                                      |
+| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------- |
+| [系统指令专家](https://lobechat.com/discover/assistant/instructer)<br/><sup>By **[yuyun2000](https://github.com/yuyun2000)** on **2024-12-04**</sup>                    | 擅长精炼与生成高效系统指令<br/>`系统指令` `写作` `细节优化` `用户需求`                    |
+| [日语帮助记忆师](https://lobechat.com/discover/assistant/japan-language-helper)<br/><sup>By **[sharkbear212](https://github.com/sharkbear212)** on **2024-12-04**</sup> | 擅长日语五十音，平假名，片假名，单词和短语解释与记忆技巧<br/>`解释` `记忆技巧` `日语教学` |
+| [诗词卡片设计师](https://lobechat.com/discover/assistant/poetry-card-designer)<br/><sup>By **[lianxin255](https://github.com/lianxin255)** on **2024-12-03**</sup>      | 擅长设计诗词卡片，提升艺术感与吸引力<br/>`诗词卡片设计` `卡片` `创意` `艺术表现`          |
+| [日常医生](https://lobechat.com/discover/assistant/yunchat-docter)<br/><sup>By **[yuyun2000](https://github.com/yuyun2000)** on **2024-11-30**</sup>                    | 擅长外科诊疗与个性化健康管理<br/>`全科医学` `外科` `健康咨询` `个性化治疗` `医学教育`     |
 
-> 📊 Total agents: [<kbd>**453**</kbd> ](https://github.com/lobehub/lobe-chat-agents)
+> 📊 Total agents: [<kbd>**453**</kbd> ](https://lobechat.com/discover/assistants)
 
  <!-- AGENT LIST -->
 
@@ -714,6 +748,7 @@ This project is [Apache 2.0](./LICENSE) licensed.
 
 [back-to-top]: https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square
 [blog]: https://lobehub.com/zh/blog
+[changelog]: https://lobehub.com/changelog
 [chat-desktop]: https://raw.githubusercontent.com/lobehub/lobe-chat/lighthouse/lighthouse/chat/desktop/pagespeed.svg
 [chat-desktop-report]: https://lobehub.github.io/lobe-chat/lighthouse/chat/desktop/chat_preview_lobehub_com_chat.html
 [chat-mobile]: https://raw.githubusercontent.com/lobehub/lobe-chat/lighthouse/lighthouse/chat/mobile/pagespeed.svg

package/changelog/v1.json

@@ -1,4 +1,13 @@
 [
+  {
+    "children": {
+      "fixes": [
+        "Fix pdf preview with capital ext."
+      ]
+    },
+    "date": "2024-12-18",
+    "version": "1.36.34"
+  },
   {
     "children": {
       "fixes": [

package/locales/ar/models.json

@@ -23,20 +23,6 @@
   "4.0Ultra": {
     "description": "Spark4.0 Ultra هو أقوى إصدار في سلسلة نماذج Spark، حيث يعزز فهم النصوص وقدرات التلخيص مع تحسين روابط البحث عبر الإنترنت. إنه حل شامل يهدف إلى تعزيز إنتاجية المكتب والاستجابة الدقيقة للاحتياجات، ويعتبر منتجًا ذكيًا رائدًا في الصناعة."
   },
-  "@cf/meta/llama-3-8b-instruct-awq": {},
-  "@cf/openchat/openchat-3.5-0106": {},
-  "@cf/qwen/qwen1.5-14b-chat-awq": {},
-  "@hf/google/gemma-7b-it": {},
-  "@hf/meta-llama/meta-llama-3-8b-instruct": {
-    "description": "من جيل إلى جيل، يظهر Meta Llama 3 أداءً متقدمًا في مجموعة واسعة من معايير الصناعة ويقدم قدرات جديدة، بما في ذلك تحسين التفكير."
-  },
-  "@hf/mistral/mistral-7b-instruct-v0.2": {},
-  "@hf/nexusflow/starling-lm-7b-beta": {},
-  "@hf/nousresearch/hermes-2-pro-mistral-7b": {},
-  "@hf/thebloke/deepseek-coder-6.7b-instruct-awq": {},
-  "@hf/thebloke/neural-chat-7b-v3-1-awq": {},
-  "@hf/thebloke/openhermes-2.5-mistral-7b-awq": {},
-  "@hf/thebloke/zephyr-7b-beta-awq": {},
   "Baichuan2-Turbo": {
     "description": "يستخدم تقنية تعزيز البحث لتحقيق الربط الشامل بين النموذج الكبير والمعرفة الميدانية والمعرفة من جميع أنحاء الشبكة. يدعم تحميل مستندات PDF وWord وغيرها من المدخلات، مما يضمن الحصول على المعلومات بشكل سريع وشامل، ويقدم نتائج دقيقة واحترافية."
   },
@@ -127,7 +113,6 @@
   "Nous-Hermes-2-Mixtral-8x7B-DPO": {
     "description": "Hermes 2 Mixtral 8x7B DPO هو دمج متعدد النماذج مرن للغاية، يهدف إلى تقديم تجربة إبداعية ممتازة."
   },
-  "NousResearch/Hermes-3-Llama-3.1-8B": {},
   "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": {
     "description": "Nous Hermes 2 - Mixtral 8x7B-DPO (46.7B) هو نموذج تعليمات عالي الدقة، مناسب للحسابات المعقدة."
   },
@@ -530,9 +515,6 @@
   "cohere-command-r-plus": {
     "description": "نموذج RAG محسّن من الطراز الأول مصمم للتعامل مع أحمال العمل على مستوى المؤسسات."
   },
-  "command-light": {
-    "description": ""
-  },
   "command-r": {
     "description": "Command R هو نموذج LLM محسن لمهام الحوار والسياقات الطويلة، مناسب بشكل خاص للتفاعل الديناميكي وإدارة المعرفة."
   },
@@ -794,9 +776,6 @@
   "hunyuan-functioncall": {
     "description": "نموذج Hunyuan الأحدث من نوع MOE FunctionCall، تم تدريبه على بيانات FunctionCall عالية الجودة، مع نافذة سياق تصل إلى 32K، ويحتل مرتبة متقدمة في مؤشرات التقييم عبر عدة أبعاد."
   },
-  "hunyuan-large": {
-    "description": ""
-  },
   "hunyuan-lite": {
     "description": "تم الترقية إلى هيكل MOE، مع نافذة سياق تصل إلى 256k، متفوقًا على العديد من النماذج مفتوحة المصدر في تقييمات NLP، البرمجة، الرياضيات، والصناعات."
   },
@@ -830,8 +809,6 @@
   "internlm2.5-latest": {
     "description": "سلسلة نماذجنا الأحدث، تتمتع بأداء استدلال ممتاز، تدعم طول سياق يصل إلى 1 مليون، بالإضافة إلى قدرة أقوى على اتباع التعليمات واستدعاء الأدوات."
   },
-  "jamba-1.5-large": {},
-  "jamba-1.5-mini": {},
   "learnlm-1.5-pro-experimental": {
     "description": "LearnLM هو نموذج لغوي تجريبي محدد المهام، تم تدريبه ليتماشى مع مبادئ علوم التعلم، يمكنه اتباع التعليمات النظامية في سيناريوهات التعليم والتعلم، ويعمل كمدرب خبير."
   },
@@ -1027,7 +1004,6 @@
   "meta.llama3-8b-instruct-v1:0": {
     "description": "Meta Llama 3 هو نموذج لغوي كبير مفتوح (LLM) موجه للمطورين والباحثين والشركات، يهدف إلى مساعدتهم في بناء وتجربة وتوسيع أفكارهم في الذكاء الاصطناعي بشكل مسؤول. كجزء من نظام الابتكار المجتمعي العالمي، فهو مثالي للأجهزة ذات القدرة الحاسوبية والموارد المحدودة، والأجهزة الطرفية، وأوقات التدريب الأسرع."
   },
-  "microsoft/Phi-3.5-mini-instruct": {},
   "microsoft/WizardLM-2-8x22B": {
     "description": "WizardLM 2 هو نموذج لغوي تقدمه Microsoft AI، يتميز بأداء ممتاز في المحادثات المعقدة، واللغات المتعددة، والاستدلال، ومساعدات الذكاء."
   },

package/locales/ar/providers.json

@@ -1,5 +1,7 @@
 {
-  "ai21": {},
+  "ai21": {
+    "description": "تقوم AI21 Labs ببناء نماذج أساسية وأنظمة ذكاء اصطناعي للشركات، مما يسرع من تطبيق الذكاء الاصطناعي التوليدي في الإنتاج."
+  },
   "ai360": {
     "description": "AI 360 هي منصة نماذج وخدمات الذكاء الاصطناعي التي أطلقتها شركة 360، تقدم مجموعة متنوعة من نماذج معالجة اللغة الطبيعية المتقدمة، بما في ذلك 360GPT2 Pro و360GPT Pro و360GPT Turbo و360GPT Turbo Responsibility 8K. تجمع هذه النماذج بين المعلمات الكبيرة والقدرات متعددة الوسائط، وتستخدم على نطاق واسع في توليد النصوص، وفهم المعاني، وأنظمة الحوار، وتوليد الشيفرات. من خلال استراتيجيات تسعير مرنة، تلبي AI 360 احتياجات المستخدمين المتنوعة، وتدعم المطورين في التكامل، مما يعزز الابتكار والتطوير في التطبيقات الذكية."
   },
@@ -15,7 +17,9 @@
   "bedrock": {
     "description": "Bedrock هي خدمة تقدمها أمازون AWS، تركز على توفير نماذج لغة ورؤية متقدمة للذكاء الاصطناعي للشركات. تشمل عائلة نماذجها سلسلة Claude من Anthropic وسلسلة Llama 3.1 من Meta، وتغطي مجموعة من الخيارات من النماذج الخفيفة إلى عالية الأداء، وتدعم مهام مثل توليد النصوص، والحوار، ومعالجة الصور، مما يجعلها مناسبة لتطبيقات الشركات بمختلف أحجامها واحتياجاتها."
   },
-  "cloudflare": {},
+  "cloudflare": {
+    "description": "تشغيل نماذج التعلم الآلي المدفوعة بوحدات معالجة الرسوميات بدون خادم على شبكة Cloudflare العالمية."
+  },
   "deepseek": {
     "description": "DeepSeek هي شركة تركز على أبحاث وتطبيقات تقنيات الذكاء الاصطناعي، حيث يجمع نموذجها الأحدث DeepSeek-V2.5 بين قدرات الحوار العامة ومعالجة الشيفرات، وقد حقق تحسينات ملحوظة في محاذاة تفضيلات البشر، ومهام الكتابة، واتباع التعليمات."
   },
@@ -35,7 +39,7 @@
     "description": "يتميز محرك الاستدلال LPU من Groq بأداء ممتاز في أحدث اختبارات المعايير لنماذج اللغة الكبيرة المستقلة (LLM)، حيث أعاد تعريف معايير حلول الذكاء الاصطناعي بسرعته وكفاءته المذهلة. Groq يمثل سرعة استدلال فورية، ويظهر أداءً جيدًا في النشر القائم على السحابة."
   },
   "higress": {
-    "description": ""
+    "description": "Higress هو بوابة API سحابية الأصل، تم تطويرها داخل علي بابا لحل مشاكل إعادة تحميل Tengine التي تؤثر سلبًا على الأعمال ذات الاتصالات الطويلة، بالإضافة إلى نقص قدرات توازن الحمل لـ gRPC/Dubbo."
   },
   "huggingface": {
     "description": "تقدم واجهة برمجة التطبيقات الخاصة بـ HuggingFace طريقة سريعة ومجانية لاستكشاف الآلاف من النماذج لمجموعة متنوعة من المهام. سواء كنت تقوم بتصميم نموذج أولي لتطبيق جديد أو تحاول استكشاف إمكانيات التعلم الآلي، فإن هذه الواجهة تتيح لك الوصول الفوري إلى نماذج عالية الأداء في مجالات متعددة."
@@ -73,7 +77,9 @@
   "qwen": {
     "description": "Qwen هو نموذج لغة ضخم تم تطويره ذاتيًا بواسطة Alibaba Cloud، يتمتع بقدرات قوية في فهم وتوليد اللغة الطبيعية. يمكنه الإجابة على مجموعة متنوعة من الأسئلة، وكتابة المحتوى، والتعبير عن الآراء، وكتابة الشيفرات، ويؤدي دورًا في مجالات متعددة."
   },
-  "sensenova": {},
+  "sensenova": {
+    "description": "تقدم شركة SenseTime خدمات نماذج كبيرة شاملة وسهلة الاستخدام، مدعومة بقوة من البنية التحتية الكبيرة لشركة SenseTime."
+  },
   "siliconcloud": {
     "description": "تسعى SiliconFlow إلى تسريع الذكاء الاصطناعي العام (AGI) لفائدة البشرية، من خلال تحسين كفاءة الذكاء الاصطناعي على نطاق واسع باستخدام حزمة GenAI سهلة الاستخدام وذات التكلفة المنخفضة."
   },

package/locales/bg-BG/models.json

@@ -23,20 +23,6 @@
   "4.0Ultra": {
     "description": "Spark4.0 Ultra е най-мощната версия в серията Starfire, която подобрява разбирането и обобщаването на текстовото съдържание, докато надгражда свързаните търсения. Това е всестранно решение за повишаване на производителността в офиса и точно отговаряне на нуждите, водещо в индустрията интелигентно решение."
   },
-  "@cf/meta/llama-3-8b-instruct-awq": {},
-  "@cf/openchat/openchat-3.5-0106": {},
-  "@cf/qwen/qwen1.5-14b-chat-awq": {},
-  "@hf/google/gemma-7b-it": {},
-  "@hf/meta-llama/meta-llama-3-8b-instruct": {
-    "description": "Поколение след поколение, Meta Llama 3 демонстрира най-съвременна производителност в широк спектър от индустриални оценки и предлага нови възможности, включително подобрено разсъждение."
-  },
-  "@hf/mistral/mistral-7b-instruct-v0.2": {},
-  "@hf/nexusflow/starling-lm-7b-beta": {},
-  "@hf/nousresearch/hermes-2-pro-mistral-7b": {},
-  "@hf/thebloke/deepseek-coder-6.7b-instruct-awq": {},
-  "@hf/thebloke/neural-chat-7b-v3-1-awq": {},
-  "@hf/thebloke/openhermes-2.5-mistral-7b-awq": {},
-  "@hf/thebloke/zephyr-7b-beta-awq": {},
   "Baichuan2-Turbo": {
     "description": "Използва технологии за подобряване на търсенето, за да свърже голям модел с областни знания и знания от интернет. Поддържа качване на различни документи като PDF, Word и вход на уебсайтове, с бърз и цялостен достъп до информация, предоставяйки точни и професионални резултати."
   },
@@ -127,7 +113,6 @@
   "Nous-Hermes-2-Mixtral-8x7B-DPO": {
     "description": "Hermes 2 Mixtral 8x7B DPO е високо гъвкава многомоделна комбинация, предназначена да предостави изключителен креативен опит."
   },
-  "NousResearch/Hermes-3-Llama-3.1-8B": {},
   "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": {
     "description": "Nous Hermes 2 - Mixtral 8x7B-DPO (46.7B) е модел с висока точност за инструкции, подходящ за сложни изчисления."
   },
@@ -530,9 +515,6 @@
   "cohere-command-r-plus": {
     "description": "Command R+ е модел, оптимизиран за RAG, проектиран да се справя с натоварвания на ниво предприятие."
   },
-  "command-light": {
-    "description": ""
-  },
   "command-r": {
     "description": "Command R е LLM, оптимизиран за диалогови и дълги контекстуални задачи, особено подходящ за динамично взаимодействие и управление на знания."
   },
@@ -794,9 +776,6 @@
   "hunyuan-functioncall": {
     "description": "Най-новият модел на HunYuan с MOE архитектура за извикване на функции, обучен с висококачествени данни за извикване на функции, с контекстен прозорец от 32K, водещ в множество измерения на оценъчните показатели."
   },
-  "hunyuan-large": {
-    "description": ""
-  },
   "hunyuan-lite": {
     "description": "Актуализиран до MOE структура, контекстният прозорец е 256k, водещ в множество оценъчни набори в NLP, код, математика и индустрия, пред много от отворените модели."
   },
@@ -830,8 +809,6 @@
   "internlm2.5-latest": {
     "description": "Нашата най-нова серия модели с изключителни способности за извеждане, поддържаща контекстна дължина от 1M и по-силни способности за следване на инструкции и извикване на инструменти."
   },
-  "jamba-1.5-large": {},
-  "jamba-1.5-mini": {},
   "learnlm-1.5-pro-experimental": {
     "description": "LearnLM е експериментален езиков модел, специфичен за задачи, обучен да отговаря на принципите на научното обучение, способен да следва системни инструкции в учебни и обучителни сценарии, да действа като експертен ментор и др."
   },
@@ -1027,7 +1004,6 @@
   "meta.llama3-8b-instruct-v1:0": {
     "description": "Meta Llama 3 е отворен голям езиков модел (LLM), насочен към разработчици, изследователи и предприятия, предназначен да им помогне да изградят, експериментират и отговорно разширят своите идеи за генеративен ИИ. Като част от основната система на глобалната общност за иновации, той е особено подходящ за устройства с ограничени изчислителни ресурси и по-бързо време за обучение."
   },
-  "microsoft/Phi-3.5-mini-instruct": {},
   "microsoft/WizardLM-2-8x22B": {
     "description": "WizardLM 2 е езиков модел, предоставен от Microsoft AI, който показва особени способности в сложни разговори, многоезичност, разсъждения и интелигентни асистенти."
   },

package/locales/bg-BG/providers.json

@@ -1,5 +1,7 @@
 {
-  "ai21": {},
+  "ai21": {
+    "description": "AI21 Labs изгражда основни модели и системи за изкуствен интелект за предприятия, ускорявайки приложението на генеративния изкуствен интелект в производството."
+  },
   "ai360": {
     "description": "360 AI е платформа за AI модели и услуги, предлагана от компания 360, предлагаща множество напреднали модели за обработка на естествен език, включително 360GPT2 Pro, 360GPT Pro, 360GPT Turbo и 360GPT Turbo Responsibility 8K. Тези модели комбинират голям брой параметри и мултимодални способности, широко използвани в текстово генериране, семантично разбиране, диалогови системи и генериране на код. Чрез гъвкава ценова стратегия, 360 AI отговаря на разнообразни потребителски нужди, поддържайки интеграция за разработчици и насърчавайки иновации и развитие на интелигентни приложения."
   },
@@ -15,7 +17,9 @@
   "bedrock": {
     "description": "Bedrock е услуга, предоставяна от Amazon AWS, фокусирана върху предоставянето на напреднали AI езикови и визуални модели за предприятия. Семейството на моделите включва серията Claude на Anthropic, серията Llama 3.1 на Meta и други, обхващащи разнообразие от опции от леки до високо производителни, поддържащи текстово генериране, диалог, обработка на изображения и много други задачи, подходящи за различни мащаби и нужди на бизнес приложения."
   },
-  "cloudflare": {},
+  "cloudflare": {
+    "description": "Работа с модели на машинно обучение, задвижвани от безсървърни GPU, в глобалната мрежа на Cloudflare."
+  },
   "deepseek": {
     "description": "DeepSeek е компания, специализирана в изследвания и приложения на технологии за изкуствен интелект, чийто най-нов модел DeepSeek-V2.5 комбинира способности за общи диалози и обработка на код, постигайки значителни подобрения в съответствието с човешките предпочитания, писателските задачи и следването на инструкции."
   },
@@ -35,7 +39,7 @@
     "description": "Инженерният двигател LPU на Groq показва изключителни резултати в последните независими тестове на големи езикови модели (LLM), преосмисляйки стандартите за AI решения с невероятната си скорост и ефективност. Groq е представител на мигновен скорост на изводите, демонстрирайки добро представяне в облачни внедрения."
   },
   "higress": {
-    "description": ""
+    "description": "Higress е облачно роден API шлюз, създаден в Alibaba, за да реши проблемите с Tengine reload, които вредят на дългосрочните връзки, и недостатъчните възможности за баланс на натоварването на gRPC/Dubbo."
   },
   "huggingface": {
     "description": "HuggingFace Inference API предлагава бърз и безплатен начин да изследвате хиляди модели, подходящи за различни задачи. Независимо дали проектирате прототип за ново приложение, или опитвате функционалността на машинното обучение, този API ви предоставя незабавен достъп до високопроизводителни модели в множество области."
@@ -73,7 +77,9 @@
   "qwen": {
     "description": "Qwen е самостоятелно разработен свръхголям езиков модел на Alibaba Cloud, с мощни способности за разбиране и генериране на естествен език. Може да отговаря на различни въпроси, да създава текстово съдържание, да изразява мнения и да пише код, играейки роля в множество области."
   },
-  "sensenova": {},
+  "sensenova": {
+    "description": "SenseNova, с мощната основа на SenseTime, предлага ефективни и лесни за използване услуги за големи модели с пълен стек."
+  },
   "siliconcloud": {
     "description": "SiliconFlow се стреми да ускори AGI, за да бъде от полза за човечеството, повишавайки ефективността на мащабния AI чрез лесен за използване и икономически изгоден GenAI стек."
   },