LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional RAG (retrieve-and-answer from scratch every time), the LLM incrementally builds and maintains a persistent wiki from your sources。
TypeScript
feat(atlascloud): integrate Atlas Cloud provider
Lucas Zhu3eb692587a1c
diff --git a/README.md b/README.mdindex 91e3afb3..19a23d6c 100644--- a/README.md+++ b/README.md@@ -24,6 +24,42 @@---+### Powered by Atlas Cloud (OpenAI-compatible)++<p align="center">+ <a href="https://www.atlascloud.ai/?utm_source=github&utm_medium=link&utm_campaign=llm_wiki">+ <img src="assets/atlas-cloud-logo.png" alt="Atlas Cloud" width="180">+ </a>+</p>++> 🎁 **[Atlas Cloud](https://www.atlascloud.ai/?utm_source=github&utm_medium=link&utm_campaign=llm_wiki)** is a full-modal, OpenAI-compatible AI inference platform. Because LLM Wiki ingests documents through any OpenAI-compatible chat endpoint, you can plug Atlas Cloud in as a drop-in backend and reach DeepSeek, Qwen, GLM, Kimi, MiniMax, Claude, GPT and Gemini through a single API — no per-vendor setup. Pick the **Atlas Cloud** preset in **Settings → LLM provider** (or set the base URL manually):++```env+# Settings → LLM provider → Atlas Cloud (custom, OpenAI-compatible)+Base URL: https://api.atlascloud.ai/v1+API Key: <your-atlascloud-api-key>+Model: deepseek-ai/deepseek-v4-pro+```++`deepseek-ai/deepseek-v4-pro` is a reasoning model — keep the context window generous (the preset defaults to 128K). Budget-friendly subscriptions: [coding plan](https://www.atlascloud.ai/console/coding-plan).++<details>+<summary>All Atlas Cloud chat models (59)</summary>++- **Anthropic (Claude):** `anthropic/claude-haiku-4.5-20251001`, `anthropic/claude-opus-4.8`, `anthropic/claude-sonnet-4.6`+- **OpenAI (GPT):** `openai/gpt-5.4`, `openai/gpt-5.5`+- **Google (Gemini):** `google/gemini-3.1-flash-lite`, `google/gemini-3.1-pro-preview`, `google/gemini-3.5-flash`+- **Alibaba (Qwen):** `qwen/qwen2.5-7b-instruct`, `Qwen/Qwen3-235B-A22B-Instruct-2507`, `qwen/qwen3-235b-a22b-thinking-2507`, `qwen/qwen3-30b-a3b`, `Qwen/Qwen3-30B-A3B-Instruct-2507`, `qwen/qwen3-30b-a3b-thinking-2507`, `qwen/qwen3-32b`, `qwen/qwen3-8b`, `Qwen/Qwen3-Coder`, `qwen/qwen3-coder-next`, `qwen/qwen3-max-2026-01-23`, `Qwen/Qwen3-Next-80B-A3B-Instruct`, `Qwen/Qwen3-Next-80B-A3B-Thinking`, `Qwen/Qwen3-VL-235B-A22B-Instruct`, `qwen/qwen3-vl-235b-a22b-thinking`, `qwen/qwen3-vl-30b-a3b-instruct`, `qwen/qwen3-vl-30b-a3b-thinking`, `qwen/qwen3-vl-8b-instruct`, `qwen/qwen3.5-122b-a10b`, `qwen/qwen3.5-27b`, `qwen/qwen3.5-35b-a3b`, `qwen/qwen3.5-397b-a17b`, `qwen/qwen3.6-35b-a3b`, `qwen/qwen3.6-plus`+- **DeepSeek:** `deepseek-ai/deepseek-ocr`, `deepseek-ai/deepseek-r1-0528`, `deepseek-ai/DeepSeek-V3-0324`, `deepseek-ai/DeepSeek-V3.1`, `deepseek-ai/DeepSeek-V3.1-Terminus`, `deepseek-ai/deepseek-v3.2`, `deepseek-ai/DeepSeek-V3.2-Exp`, `deepseek-ai/deepseek-v4-flash`, `deepseek-ai/deepseek-v4-pro`+- **Moonshot (Kimi):** `moonshotai/Kimi-K2-Instruct`, `moonshotai/Kimi-K2-Instruct-0905`, `moonshotai/Kimi-K2-Thinking`, `moonshotai/kimi-k2.5`, `moonshotai/kimi-k2.6`+- **Zhipu (GLM):** `zai-org/GLM-4.6`, `zai-org/glm-4.7`, `zai-org/glm-5`, `zai-org/glm-5-turbo`, `zai-org/glm-5.1`, `zai-org/glm-5v-turbo`+- **MiniMax:** `MiniMaxAI/MiniMax-M2`, `minimaxai/minimax-m2.1`, `minimaxai/minimax-m2.5`, `minimaxai/minimax-m2.7`+- **xAI (Grok):** `xai/grok-4.3`+- **Kuaishou (KAT):** `kwaipilot/kat-coder-pro-v2`+- **Other:** `owl`++</details>+<p align="center"><img src="assets/overview.jpg" width="100%" alt="Overview"></p>diff --git a/README_CN.md b/README_CN.mdindex abf9cbff..6a99c224 100644--- a/README_CN.md+++ b/README_CN.md@@ -24,6 +24,42 @@---+### 由 Atlas Cloud 提供支持(OpenAI 兼容)++<p align="center">+ <a href="https://www.atlascloud.ai/?utm_source=github&utm_medium=link&utm_campaign=llm_wiki">+ <img src="assets/atlas-cloud-logo.png" alt="Atlas Cloud" width="180">+ </a>+</p>++> 🎁 **[Atlas Cloud](https://www.atlascloud.ai/?utm_source=github&utm_medium=link&utm_campaign=llm_wiki)** 是一个全模态、OpenAI 兼容的 AI 推理平台。LLM Wiki 通过任意 OpenAI 兼容的对话接口摄入文档,因此可以把 Atlas Cloud 作为即插即用的后端接入,用一套 API 直接调用 DeepSeek、Qwen、GLM、Kimi、MiniMax、Claude、GPT、Gemini,无需逐家厂商单独配置。在 **设置 → LLM 服务商** 里选 **Atlas Cloud** 预设即可(也可手动填 base URL):++```env+# 设置 → LLM 服务商 → Atlas Cloud(custom,OpenAI 兼容)+Base URL: https://api.atlascloud.ai/v1+API Key: <你的 atlascloud-api-key>+Model: deepseek-ai/deepseek-v4-pro+```++`deepseek-ai/deepseek-v4-pro` 是带推理(reasoning)的模型,上下文窗口要给足(预设默认 128K)。高性价比订阅:[coding plan](https://www.atlascloud.ai/console/coding-plan)。++<details>+<summary>Atlas Cloud 全部对话模型(59 个)</summary>++- **Anthropic (Claude):** `anthropic/claude-haiku-4.5-20251001`, `anthropic/claude-opus-4.8`, `anthropic/claude-sonnet-4.6`+- **OpenAI (GPT):** `openai/gpt-5.4`, `openai/gpt-5.5`+- **Google (Gemini):** `google/gemini-3.1-flash-lite`, `google/gemini-3.1-pro-preview`, `google/gemini-3.5-flash`+- **阿里 Qwen:** `qwen/qwen2.5-7b-instruct`, `Qwen/Qwen3-235B-A22B-Instruct-2507`, `qwen/qwen3-235b-a22b-thinking-2507`, `qwen/qwen3-30b-a3b`, `Qwen/Qwen3-30B-A3B-Instruct-2507`, `qwen/qwen3-30b-a3b-thinking-2507`, `qwen/qwen3-32b`, `qwen/qwen3-8b`, `Qwen/Qwen3-Coder`, `qwen/qwen3-coder-next`, `qwen/qwen3-max-2026-01-23`, `Qwen/Qwen3-Next-80B-A3B-Instruct`, `Qwen/Qwen3-Next-80B-A3B-Thinking`, `Qwen/Qwen3-VL-235B-A22B-Instruct`, `qwen/qwen3-vl-235b-a22b-thinking`, `qwen/qwen3-vl-30b-a3b-instruct`, `qwen/qwen3-vl-30b-a3b-thinking`, `qwen/qwen3-vl-8b-instruct`, `qwen/qwen3.5-122b-a10b`, `qwen/qwen3.5-27b`, `qwen/qwen3.5-35b-a3b`, `qwen/qwen3.5-397b-a17b`, `qwen/qwen3.6-35b-a3b`, `qwen/qwen3.6-plus`+- **DeepSeek:** `deepseek-ai/deepseek-ocr`, `deepseek-ai/deepseek-r1-0528`, `deepseek-ai/DeepSeek-V3-0324`, `deepseek-ai/DeepSeek-V3.1`, `deepseek-ai/DeepSeek-V3.1-Terminus`, `deepseek-ai/deepseek-v3.2`, `deepseek-ai/DeepSeek-V3.2-Exp`, `deepseek-ai/deepseek-v4-flash`, `deepseek-ai/deepseek-v4-pro`+- **Moonshot (Kimi):** `moonshotai/Kimi-K2-Instruct`, `moonshotai/Kimi-K2-Instruct-0905`, `moonshotai/Kimi-K2-Thinking`, `moonshotai/kimi-k2.5`, `moonshotai/kimi-k2.6`+- **智谱 GLM:** `zai-org/GLM-4.6`, `zai-org/glm-4.7`, `zai-org/glm-5`, `zai-org/glm-5-turbo`, `zai-org/glm-5.1`, `zai-org/glm-5v-turbo`+- **MiniMax:** `MiniMaxAI/MiniMax-M2`, `minimaxai/minimax-m2.1`, `minimaxai/minimax-m2.5`, `minimaxai/minimax-m2.7`+- **xAI (Grok):** `xai/grok-4.3`+- **快手 KAT:** `kwaipilot/kat-coder-pro-v2`+- **其他:** `owl`++</details>+<p align="center"><img src="assets/overview.jpg" width="100%" alt="概览"></p>diff --git a/README_JA.md b/README_JA.mdindex 0c8bc031..3f7bbb54 100644--- a/README_JA.md+++ b/README_JA.md@@ -24,6 +24,42 @@---+### Atlas Cloud で動作(OpenAI 互換)++<p align="center">+ <a href="https://www.atlascloud.ai/?utm_source=github&utm_medium=link&utm_campaign=llm_wiki">+ <img src="assets/atlas-cloud-logo.png" alt="Atlas Cloud" width="180">+ </a>+</p>++> 🎁 **[Atlas Cloud](https://www.atlascloud.ai/?utm_source=github&utm_medium=link&utm_campaign=llm_wiki)** は、OpenAI 互換のフルモーダル AI 推論プラットフォームです。LLM Wiki は任意の OpenAI 互換チャットエンドポイント経由でドキュメントを取り込むため、Atlas Cloud をドロップイン・バックエンドとして接続し、DeepSeek・Qwen・GLM・Kimi・MiniMax・Claude・GPT・Gemini を単一の API で利用できます(ベンダーごとの個別設定は不要)。**設定 → LLM プロバイダー** で **Atlas Cloud** プリセットを選択してください(base URL を手動で設定することも可能):++```env+# 設定 → LLM プロバイダー → Atlas Cloud(custom, OpenAI 互換)+Base URL: https://api.atlascloud.ai/v1+API Key: <your-atlascloud-api-key>+Model: deepseek-ai/deepseek-v4-pro+```++`deepseek-ai/deepseek-v4-pro` は推論(reasoning)モデルです。コンテキストウィンドウは十分に確保してください(プリセットの既定は 128K)。お得なサブスクリプション: [coding plan](https://www.atlascloud.ai/console/coding-plan)。++<details>+<summary>Atlas Cloud のすべてのチャットモデル(59)</summary>++- **Anthropic (Claude):** `anthropic/claude-haiku-4.5-20251001`, `anthropic/claude-opus-4.8`, `anthropic/claude-sonnet-4.6`+- **OpenAI (GPT):** `openai/gpt-5.4`, `openai/gpt-5.5`+- **Google (Gemini):** `google/gemini-3.1-flash-lite`, `google/gemini-3.1-pro-preview`, `google/gemini-3.5-flash`+- **Alibaba (Qwen):** `qwen/qwen2.5-7b-instruct`, `Qwen/Qwen3-235B-A22B-Instruct-2507`, `qwen/qwen3-235b-a22b-thinking-2507`, `qwen/qwen3-30b-a3b`, `Qwen/Qwen3-30B-A3B-Instruct-2507`, `qwen/qwen3-30b-a3b-thinking-2507`, `qwen/qwen3-32b`, `qwen/qwen3-8b`, `Qwen/Qwen3-Coder`, `qwen/qwen3-coder-next`, `qwen/qwen3-max-2026-01-23`, `Qwen/Qwen3-Next-80B-A3B-Instruct`, `Qwen/Qwen3-Next-80B-A3B-Thinking`, `Qwen/Qwen3-VL-235B-A22B-Instruct`, `qwen/qwen3-vl-235b-a22b-thinking`, `qwen/qwen3-vl-30b-a3b-instruct`, `qwen/qwen3-vl-30b-a3b-thinking`, `qwen/qwen3-vl-8b-instruct`, `qwen/qwen3.5-122b-a10b`, `qwen/qwen3.5-27b`, `qwen/qwen3.5-35b-a3b`, `qwen/qwen3.5-397b-a17b`, `qwen/qwen3.6-35b-a3b`, `qwen/qwen3.6-plus`+- **DeepSeek:** `deepseek-ai/deepseek-ocr`, `deepseek-ai/deepseek-r1-0528`, `deepseek-ai/DeepSeek-V3-0324`, `deepseek-ai/DeepSeek-V3.1`, `deepseek-ai/DeepSeek-V3.1-Terminus`, `deepseek-ai/deepseek-v3.2`, `deepseek-ai/DeepSeek-V3.2-Exp`, `deepseek-ai/deepseek-v4-flash`, `deepseek-ai/deepseek-v4-pro`+- **Moonshot (Kimi):** `moonshotai/Kimi-K2-Instruct`, `moonshotai/Kimi-K2-Instruct-0905`, `moonshotai/Kimi-K2-Thinking`, `moonshotai/kimi-k2.5`, `moonshotai/kimi-k2.6`+- **Zhipu (GLM):** `zai-org/GLM-4.6`, `zai-org/glm-4.7`, `zai-org/glm-5`, `zai-org/glm-5-turbo`, `zai-org/glm-5.1`, `zai-org/glm-5v-turbo`+- **MiniMax:** `MiniMaxAI/MiniMax-M2`, `minimaxai/minimax-m2.1`, `minimaxai/minimax-m2.5`, `minimaxai/minimax-m2.7`+- **xAI (Grok):** `xai/grok-4.3`+- **Kuaishou (KAT):** `kwaipilot/kat-coder-pro-v2`+- **Other:** `owl`++</details>+<p align="center"><img src="assets/overview.jpg" width="100%" alt="概要"></p>diff --git a/README_KO.md b/README_KO.mdindex 7d062342..47c670e4 100644--- a/README_KO.md+++ b/README_KO.md@@ -24,6 +24,42 @@---+### Atlas Cloud 기반 (OpenAI 호환)++<p align="center">+ <a href="https://www.atlascloud.ai/?utm_source=github&utm_medium=link&utm_campaign=llm_wiki">+ <img src="assets/atlas-cloud-logo.png" alt="Atlas Cloud" width="180">+ </a>+</p>++> 🎁 **[Atlas Cloud](https://www.atlascloud.ai/?utm_source=github&utm_medium=link&utm_campaign=llm_wiki)** 는 OpenAI 호환의 풀모달 AI 추론 플랫폼입니다. LLM Wiki는 OpenAI 호환 채팅 엔드포인트를 통해 문서를 수집하므로, Atlas Cloud를 드롭인 백엔드로 연결하여 DeepSeek, Qwen, GLM, Kimi, MiniMax, Claude, GPT, Gemini를 단일 API로 사용할 수 있습니다(벤더별 개별 설정 불필요). **설정 → LLM 제공자** 에서 **Atlas Cloud** 프리셋을 선택하세요(base URL 직접 입력도 가능):++```env+# 설정 → LLM 제공자 → Atlas Cloud (custom, OpenAI 호환)+Base URL: https://api.atlascloud.ai/v1+API Key: <your-atlascloud-api-key>+Model: deepseek-ai/deepseek-v4-pro+```++`deepseek-ai/deepseek-v4-pro` 는 추론(reasoning) 모델이므로 컨텍스트 윈도우를 넉넉히 설정하세요(프리셋 기본값 128K). 합리적인 구독: [coding plan](https://www.atlascloud.ai/console/coding-plan).++<details>+<summary>Atlas Cloud의 모든 채팅 모델 (59개)</summary>++- **Anthropic (Claude):** `anthropic/claude-haiku-4.5-20251001`, `anthropic/claude-opus-4.8`, `anthropic/claude-sonnet-4.6`+- **OpenAI (GPT):** `openai/gpt-5.4`, `openai/gpt-5.5`+- **Google (Gemini):** `google/gemini-3.1-flash-lite`, `google/gemini-3.1-pro-preview`, `google/gemini-3.5-flash`+- **Alibaba (Qwen):** `qwen/qwen2.5-7b-instruct`, `Qwen/Qwen3-235B-A22B-Instruct-2507`, `qwen/qwen3-235b-a22b-thinking-2507`, `qwen/qwen3-30b-a3b`, `Qwen/Qwen3-30B-A3B-Instruct-2507`, `qwen/qwen3-30b-a3b-thinking-2507`, `qwen/qwen3-32b`, `qwen/qwen3-8b`, `Qwen/Qwen3-Coder`, `qwen/qwen3-coder-next`, `qwen/qwen3-max-2026-01-23`, `Qwen/Qwen3-Next-80B-A3B-Instruct`, `Qwen/Qwen3-Next-80B-A3B-Thinking`, `Qwen/Qwen3-VL-235B-A22B-Instruct`, `qwen/qwen3-vl-235b-a22b-thinking`, `qwen/qwen3-vl-30b-a3b-instruct`, `qwen/qwen3-vl-30b-a3b-thinking`, `qwen/qwen3-vl-8b-instruct`, `qwen/qwen3.5-122b-a10b`, `qwen/qwen3.5-27b`, `qwen/qwen3.5-35b-a3b`, `qwen/qwen3.5-397b-a17b`, `qwen/qwen3.6-35b-a3b`, `qwen/qwen3.6-plus`+- **DeepSeek:** `deepseek-ai/deepseek-ocr`, `deepseek-ai/deepseek-r1-0528`, `deepseek-ai/DeepSeek-V3-0324`, `deepseek-ai/DeepSeek-V3.1`, `deepseek-ai/DeepSeek-V3.1-Terminus`, `deepseek-ai/deepseek-v3.2`, `deepseek-ai/DeepSeek-V3.2-Exp`, `deepseek-ai/deepseek-v4-flash`, `deepseek-ai/deepseek-v4-pro`+- **Moonshot (Kimi):** `moonshotai/Kimi-K2-Instruct`, `moonshotai/Kimi-K2-Instruct-0905`, `moonshotai/Kimi-K2-Thinking`, `moonshotai/kimi-k2.5`, `moonshotai/kimi-k2.6`+- **Zhipu (GLM):** `zai-org/GLM-4.6`, `zai-org/glm-4.7`, `zai-org/glm-5`, `zai-org/glm-5-turbo`, `zai-org/glm-5.1`, `zai-org/glm-5v-turbo`+- **MiniMax:** `MiniMaxAI/MiniMax-M2`, `minimaxai/minimax-m2.1`, `minimaxai/minimax-m2.5`, `minimaxai/minimax-m2.7`+- **xAI (Grok):** `xai/grok-4.3`+- **Kuaishou (KAT):** `kwaipilot/kat-coder-pro-v2`+- **Other:** `owl`++</details>+<p align="center"><img src="assets/overview.jpg" width="100%" alt="개요"></p>diff --git a/assets/atlas-cloud-logo.png b/assets/atlas-cloud-logo.pngnew file mode 100644index 00000000..780a4769Binary files /dev/null and b/assets/atlas-cloud-logo.png differdiff --git a/src/components/settings/llm-presets.ts b/src/components/settings/llm-presets.tsindex 9e88d687..879eaa11 100644--- a/src/components/settings/llm-presets.ts+++ b/src/components/settings/llm-presets.ts@@ -184,6 +184,35 @@ export const LLM_PRESETS: LlmPreset[] = [],suggestedContextSize: 64000,},+ {+ id: "atlascloud",+ label: "Atlas Cloud",+ hint: "api.atlascloud.ai",+ provider: "custom",+ baseUrl: "https://api.atlascloud.ai/v1",+ defaultModel: "deepseek-ai/deepseek-v4-pro",+ apiMode: "chat_completions",+ // Atlas Cloud is a full-modal inference platform exposing many model+ // families (DeepSeek, Qwen, GLM, Kimi, MiniMax, Claude, GPT, Gemini…)+ // behind a single OpenAI-compatible /v1/chat/completions endpoint, so+ // it reuses the generic chat-completions wire like the other hosted+ // gateways above. `deepseek-v4-pro` is a reasoning model — leave the+ // context window generous. Full catalog is large and rotates; this is+ // a practical subset and users can type any other id into the input.+ suggestedModels: [+ "deepseek-ai/deepseek-v4-pro",+ "deepseek-ai/deepseek-v4-flash",+ "deepseek-ai/deepseek-v3.2",+ "Qwen/Qwen3-Next-80B-A3B-Instruct",+ "moonshotai/kimi-k2.6",+ "zai-org/glm-5",+ "minimaxai/minimax-m2.7",+ "anthropic/claude-sonnet-4.6",+ "openai/gpt-5.5",+ "google/gemini-3.5-flash",+ ],+ suggestedContextSize: 128000,+ },{id: "groq",label: "Groq",diff --git a/src/components/settings/preset-resolver.test.ts b/src/components/settings/preset-resolver.test.tsindex da551da6..2c0dd264 100644--- a/src/components/settings/preset-resolver.test.ts+++ b/src/components/settings/preset-resolver.test.ts@@ -30,6 +30,16 @@ describe("resolveConfig", () => {])})+ it("exposes Atlas Cloud as an OpenAI-compatible chat-completions preset", () => {+ const atlas = LLM_PRESETS.find((preset) => preset.id === "atlascloud")++ expect(atlas?.provider).toBe("custom")+ expect(atlas?.baseUrl).toBe("https://api.atlascloud.ai/v1")+ expect(atlas?.apiMode).toBe("chat_completions")+ expect(atlas?.defaultModel).toBe("deepseek-ai/deepseek-v4-pro")+ expect(atlas?.suggestedModels).toContain("deepseek-ai/deepseek-v4-pro")+ })+it("keeps Xiaomi MiMo presets aligned with current official and Token Plan endpoints", () => {const mimo = LLM_PRESETS.find((preset) => preset.id === "xiaomi-mimo")