AI Anda, Peraturan Anda
- Added a bundled
llama.cppcompletion provider profile forqwen3-35b-a3b, including configurable endpoint, sampling, token, penalty, and streaming defaults - Added an Ollama Cloud category in the Models library and model selector, backed by Ollama's dedicated cloud listing
- Added custom accent selection in Appearance with violet, blue, cyan, teal, emerald, amber, rose, slate, and custom color options
- Added runtime-generated accent shade scales so custom accents can drive buttons, links, focus rings, sliders, progress bars, selected states, and glow shadows
- Reworked Tailwind theme tokens to use CSS variables for
primaryandaccent, with generated custom palettes meeting white-text contrast targets - Refined light and dark neutral palettes to reduce glare while preserving contrast across app backgrounds, panels, inputs, and message surfaces
- Persisted accent preferences through frontend state, backend preferences, import/export defaults, local rehydration, logout cleanup, and demo mode
- Added accent translation keys across all supported locales and verified locale key parity against English
- Expanded demo-mode preference APIs so Appearance, generation, embedding, system-message, and default-model settings can be exercised without a backend connection
- Standardized the Libre WebUI wordmark through a shared
Logocomponent across loading, login, setup, sidebar, and settings surfaces - Replaced fixed violet styling in persona adaptive-learning controls with active-accent tokens
- Recolored Ollama library and Cloud badges from cyan to the design-system info-blue treatment
- Reduced noisy debug logging across optional auth, chat, document search, plugin lookup, plugin deletion, TTS, image generation, and WebSocket auth paths
- Returned package version in auth system info for UI/version display
- Updated Dependabot targeting to
mainand ignored incompatible Electron and ESLint major bumps until their upstream compatibility gaps are resolved
- Fixed a critical app-wide
Too many re-renderscrash inSettingsModalby memoizing image-generation model/plugin arrays - Fixed Ollama Cloud model pulls by tagging cloud library results with
:cloudbefore install/run actions - Fixed Ollama Cloud generation failures by stripping unsupported non-positive
num_predictvalues before cloud requests - Fixed cloud model pull functionality
- Fixed auto-title generation for persona/current-model workflows by resolving the real running model before sending title prompts
- Quietly handles expired or invalid JWTs in auth and WebSocket flows without dumping routine stack traces
- Kept the lint toolchain on ESLint 9 for compatibility with the current React plugin stack
- Expanded
DESIGN.mdwith custom accent presets, generated shade-scale behavior, token usage rules, light/dark neutral guidance, and contrast requirements
- Bumped package versions to
0.10.0 - Updated Electron to
41.7.1and Electron Builder to26.15.2 - Bumped frontend/backend dependencies including React Query, i18next, KaTeX, lucide-react, React Router, Vite, pdfjs-dist, TypeScript tooling, Tailwind Merge, Zustand, Express, Multer, Better SQLite3, and related lockfile entries
- Remediated npm security advisories through dependency and lockfile updates, including
qs,tmp,ip-address,brace-expansion,ws, and related transitive packages
Antara muka sembang AI yang mengutamakan privasi. Jalankan secara tempatan dengan Ollama atau sambung ke OpenAI, Anthropic, dan 9+ penyedia. Tiada telemetri. Tiada penjejakan.
npx libre-webui Memerlukan Node.js 18+ dan Ollama untuk AI tempatan
Semua Yang Anda Perlukan
Penyelesaian sembang AI lengkap yang menghormati privasi anda
AI Tempatan & Awan
Jalankan model secara tempatan dengan Ollama atau sambung ke OpenAI, Anthropic, Groq, Gemini, Mistral, dan lebih lagi. Pilihan anda.
Sembang Dokumen (RAG)
Muat naik PDF, dokumen, dan fail teks. Tanya soalan tentang dokumen anda dengan carian semantik dan vector embeddings.
Artifak Interaktif
Render HTML, SVG, dan komponen React terus dalam sembang. Pratonton langsung dengan mod skrin penuh.
Enkripsi AES-256
Enkripsi gred perusahaan untuk semua data anda. Sejarah sembang, dokumen, dan tetapan dienkripsi semasa rehat.
Persona Tersuai
Cipta personaliti AI dengan tingkah laku unik dan sistem prompt. Import/eksport persona sebagai JSON.
Teks-ke-Pertuturan
Dengar respons AI dengan pelbagai pilihan suara. Menyokong TTS pelayar dan integrasi ElevenLabs.
Penjanaan Imej
Jana imej dengan ComfyUI dan model Flux. Pelbagai saiz, pratetap kualiti dan integrasi sembang yang lancar.
Pembolehubah Plugin
Tetapan boleh dikonfigurasikan bagi setiap plugin seperti suhu, titik akhir dan token. Nilai sensitif disulitkan semasa penyimpanan.
Pintasan Papan Kekunci
Pintasan gaya VS Code untuk pengguna kuasa. Navigasi, togol tetapan, dan kawal semuanya dari papan kekunci.
Sokongan Berbilang Pengguna
Kawalan akses berasaskan peranan dengan sokongan SSO. OAuth GitHub dan Hugging Face terbina dalam.
Sambung ke Mana-mana Penyedia
Satu antara muka, kemungkinan tanpa had
Mula dalam Beberapa Saat
Pilih kaedah pemasangan pilihan anda
Cipta Plugin Tersuai
Sambung mana-mana LLM serasi OpenAI dengan fail JSON mudah
Plugin Tersedia
Plugin rasmi dari repositori Libre WebUI. Klik untuk lihat atau muat turun.
{
"id": "custom-model",
"name": "Custom Model",
"type": "completion",
"endpoint": "http://localhost:8000/v1/chat/completions",
"auth": {
"header": "Authorization",
"prefix": "Bearer ",
"key_env": "CUSTOM_MODEL_API_KEY"
},
"model_map": [
"my-fine-tuned-llama"
],
"variables": [
{
"name": "temperature",
"type": "number",
"label": "Temperature",
"default": 0.7,
"min": 0, "max": 2
}
]
}Cipta Plugin Anda Sendiri
Mulakan Pelayan LLM Anda
Jalankan mana-mana pelayan serasi OpenAI: llama.cpp, vLLM, Ollama, atau pelayan FastAPI tersuai.
Cipta Plugin JSON
Definisikan endpoint, pengesahan, dan model tersedia dalam fail JSON mudah.
Muat Naik ke Libre WebUI
Pergi ke Tetapan > Penyedia, muat naik plugin anda, dan masukkan kunci API anda.
Mula Berbual
Model tersuai anda muncul dalam pemilih model. Privasi penuh, kawalan penuh.
Rujukan Medan Plugin
id Pengecam unik (huruf kecil, sengkang dibenarkan) name Nama paparan yang ditunjukkan dalam UI type "completion" untuk sembang, "tts" untuk teks-ke-pertuturan endpoint URL API (cth., /v1/chat/completions) auth.header Nama header pengesahan (Authorization, x-api-key) auth.prefix Awalan kunci ("Bearer " atau kosong) auth.key_env Pembolehubah persekitaran untuk kunci API anda model_map Tatasusunan pengecam model tersedia variables Tetapan boleh dikonfigurasikan (suhu, titik akhir dll.) Bersedia Memiliki AI Anda?
Sertai ribuan pengguna yang menghargai privasi dan kawalan.