BREAKING CHANGE(local-ai): Update image docker.io/localai/localai v3.12.1 → v4.0.0 (#46171)
This PR contains the following updates: | Package | Update | Change | |---|---|---| | [docker.io/localai/localai](https://redirect.github.com/mudler/LocalAI) | major | `558efc7` → `b841e2b` | --- > [!WARNING] > Some dependencies could not be looked up. Check the [Dependency Dashboard](../issues/18710) for more information. Add the preset `:preserveSemverRanges` to your config if you don't want to pin your dependencies. --- ### Release Notes <details> <summary>mudler/LocalAI (docker.io/localai/localai)</summary> ### [`v4.0.0`](https://redirect.github.com/mudler/LocalAI/releases/tag/v4.0.0) [Compare Source](https://redirect.github.com/mudler/LocalAI/compare/v3.12.1...v4.0.0) <!-- Release notes generated using configuration in .github/release.yml at master --> *** ### 🎉 LocalAI 4.0.0 Release! 🚀 <h1 align="center"> <br> <img height="300" src="https://raw.githubusercontent.com/mudler/LocalAI/refs/heads/master/core/http/static/logo.png"> <br> <br> </h1> LocalAI 4.0.0 is out! This major release transforms LocalAI into a complete AI orchestration platform. We’ve embedded agentic and hybrid search capabilities directly into the core, completely overhauled the user interface with React for a modern experience, and are thrilled to introduce **Agenthub** ( [link](https://agenthub.localai.io) ) a brand new community hub to easily share and import agents. Alongside these massive updates, we've introduced powerful new features like Canvas mode for code artifacts, MCP apps and full MCP client-side support. | Feature | Summary | | ------------------------------------ | ---------------------------------------------------------------------------------------- | | **Agentic Orchestration & Agenthub** | Native agent management with memory, skills, and the new Agenthub for community sharing. | | **Revamped React UI** | Complete frontend rewrite for lightning-fast performance and modern UX. | | **Canvas Mode** | Preview code blocks and artifacts side-by-side in the chat interface. | | **MCP Client-Side** | Full Model Context Protocol support, MCP Apps, and tool streaming in chat. | | **WebRTC Realtime** | WebRTC support for low-latency realtime audio conversations. | | **New Backends** | Added experimental **MLX Distributed**, fish-speech, ace-step.cpp, and faster-qwen3-tts. | | **Infrastructure** | Podman documentation, shell completion, and persistent data path separation. | *** #### 🚀 Key Features ##### 🤖 Native Agentic Orchestration & Agenthub LocalAI now includes agentic capabilities embedded directly in the core. You can manage, import, start, and stop agents via the new UI. - 🌐 **Agenthub:** We are launching **[Agenthub](https://agenthub.localai.io/)**! This is a centralized community space to share common agents and import them effortlessly into your LocalAI instance. - **Agent Management:** Full lifecycle management via the React UI. Create Agents, connect them to Slack, configure MCP servers and skills. - **Skills Management:** Centralized skill database for AI agents. - **Memory:** Agents can utilize memory with Hybrid search (PostgreSQL) or embedded in-memory storage (Chromem). - **Observability:** New "Events" column in the Agents list to track observables and status. - 📚 **Documentation:** Dive into the new capabilities in our [official Agents documentation](https://localai.io/features/agents). <https://github.com/user-attachments/assets/6270b331-e21d-4087-a540-6290006b381a> ##### 🎨 Revamped UI & Canvas Mode The Web interface has been completely migrated to **React**, bringing a smoother experience and powerful new capabilities: - **Canvas Mode:** Enable "canvas mode" in the chat to see code blocks and artifacts generated by the LLM in a dedicated preview bar on the right. - **System View:** Tabbed navigation separating Models and Backends for better organization. - **Model Size Warnings:** Visual warnings when model storage exceeds system RAM to prevent lockups. - **Traces:** Improved trace display using accordions for better readability. <https://github.com/user-attachments/assets/08cbb692-57da-48f7-963d-2e7b43883c18> ##### 🔌 MCP Apps & Client-Side Support We’ve expanded support for the Model Context Protocol (MCP): - **MCP Apps:** Select which servers to enable for the chat directly from the UI. - **Tool Streaming:** Tools from MCP servers are automatically injected into the standard chat interface. - **Client-Side Support:** Full client-side integration for MCP tools and streaming. - **Disable Option:** Add `LOCALAI_DISABLE_MCP` to completely disable MCP support for security. <img width="1920" height="912" alt="mcp apps" src="https://github.com/user-attachments/assets/ea50d29f-4a3b-412f-8c14-b8c3fb417278" /> ##### 🎵 New Backends, Audio & Video Enhancements - **MLX Distributed (Experimental):** We've added an experimental backend for running distributed workloads using Apple's MLX framework! [Check out the docs here](https://localai.io/features/mlx-distributed/index.html). - **New Audio Backends:** Introduced **fish-speech**, **ace-step.cpp**, and **faster-qwen3-tts** (CUDA-only). - **WeRTC Realtime:** WebRTC support added to the Realtime API and Talk page for better low-latency audio handling. - **TTS Improvements:** Added `sample_rate` support via post-processing and multi-voice support for Qwen TTS. - **Video Generation:** Fixed model selection dropdown sync and added `vllm-omni` backend detection. ##### 🛠️ Infrastructure & Developer Experience - **Data Separation:** New `--data-path` CLI flag and `LOCALAI_DATA_PATH` env var to separate persistent data (agents, skills) from configuration. - **Shell Completion:** Dynamic completion scripts for bash, zsh, and fish. - **Podman Support:** Dedicated documentation for Podman installation and rootless configuration. - **Gallery & Models:** Model storage size display with RAM warnings, and fallback URI resolution for backend installation failures. - **Deprecations:** HuggingFace backend support removed, and AIO images dropped to focus on main images. *** #### 🐞 Fixes & Improvements - **Logging:** Fixed watchdog spamming logs when no interval was configured; downgraded health check logs to debug. - **CUDA Detection:** Improved GPU vendor checks to prevent false CUDA detection on CPU-only hosts with runtime libs. - **Compatibility:** Renamed `json_verbose` to `verbose_json` for OpenAI spec compliance (fixes Nextcloud integration). - **Embedding:** Fixed embedding dimension truncation to return full native dimensions. - **Permissions:** Changed model install file permissions to 0644 to ensure server readability. - **Windows Docker:** Added named volumes to Docker Compose files for Windows compatibility. - **Model Reload:** Models now reload automatically after editing YAML config (e.g., `context_size`). - **Chat:** Fixed issue where thinking/reasoning blocks were sent to the LLM. - **Audio:** Fixed img2img pipeline in diffusers backend and Qwen TTS duplicate argument error. #### Known issues - The `diffusers` backend fails to build currently (due to CI limit exhaustion) and it's not currently part of this release (the previous version is still available). We are looking into it but, if you want to help and know someone at Github that could help supporting us with better ARM runners, please reach out! *** #### ❤️ Thank You LocalAI is a true FOSS movement — built by contributors, powered by community. If you believe in privacy-first AI: - ✅ **Star** the repo - 💬 **Contribute** code, docs, or feedback - 📣 **Share** with others Your support keeps this stack alive. *** #### ✅ Full Changelog <details> <summary>📋 Click to expand full changelog</summary> #### What's Changed ##### Breaking Changes 🛠 * Remove HuggingFace backend support by @​localai-b[https://github.com/mudler/LocalAI/pull/8971](https://redirect.github.com/mudler/LocalAI/pull/8971)l/8971 * chore: drop AIO images by @​mudl[https://github.com/mudler/LocalAI/pull/9004](https://redirect.github.com/mudler/LocalAI/pull/9004)l/9004 ##### Bug fixes 🐛 * fix(cli): Fix watchdog running constantly and spamming logs by @​nanoandre[https://github.com/mudler/LocalAI/pull/8624](https://redirect.github.com/mudler/LocalAI/pull/8624)l/8624 * fix(api): Downgrade health/readiness check to debug by @​nanoandre[https://github.com/mudler/LocalAI/pull/8625](https://redirect.github.com/mudler/LocalAI/pull/8625)l/8625 * fix: rename json_verbose to verbose_json by @​lukasdotc[https://github.com/mudler/LocalAI/pull/8627](https://redirect.github.com/mudler/LocalAI/pull/8627)l/8627 * fix(chatterbox): add support for cuda13/aarch64 by @​mudl[https://github.com/mudler/LocalAI/pull/8653](https://redirect.github.com/mudler/LocalAI/pull/8653)l/8653 * fix: reload model after editing YAML config (issue #​8647) by @​loc[https://github.com/mudler/LocalAI/pull/8652](https://redirect.github.com/mudler/LocalAI/pull/8652)AI/pull/8652 * fix(chat): do not send thinking/reasoning messages to the LLM by @​mudl[https://github.com/mudler/LocalAI/pull/8656](https://redirect.github.com/mudler/LocalAI/pull/8656)l/8656 * fix: change file permissions from 0600 to 0644 in InstallModel by @​localai-b[https://github.com/mudler/LocalAI/pull/8657](https://redirect.github.com/mudler/LocalAI/pull/8657)l/8657 * fix: Add named volumes for Windows Docker compatibility by @​localai-b[https://github.com/mudler/LocalAI/pull/8661](https://redirect.github.com/mudler/LocalAI/pull/8661)l/8661 * fix(gallery): add fallback URI resolution for backend installation by @​localai-b[https://github.com/mudler/LocalAI/pull/8663](https://redirect.github.com/mudler/LocalAI/pull/8663)l/8663 * fix: whisper breaking on cuda-13 (use absolute path for CUDA directory detection) by @​localai-b[https://github.com/mudler/LocalAI/pull/8678](https://redirect.github.com/mudler/LocalAI/pull/8678)l/8678 * fix(gallery): clean up partially downloaded backend on installation failure by @​localai-b[https://github.com/mudler/LocalAI/pull/8679](https://redirect.github.com/mudler/LocalAI/pull/8679)l/8679 * fix: properly sync model selection dropdown in video generation UI by @​localai-b[https://github.com/mudler/LocalAI/pull/8680](https://redirect.github.com/mudler/LocalAI/pull/8680)l/8680 * fix: allow reranking models configured with known_usecases by @​localai-b[https://github.com/mudler/LocalAI/pull/8681](https://redirect.github.com/mudler/LocalAI/pull/8681)l/8681 * fix: return full embedding dimensions instead of truncating trailing zeros (#​8721) by @​loc[https://github.com/mudler/LocalAI/pull/8755](https://redirect.github.com/mudler/LocalAI/pull/8755)AI/pull/8755 * fix: Add vllm-omni backend to video generation model detection (#​8659) by @​loc[https://github.com/mudler/LocalAI/pull/8781](https://redirect.github.com/mudler/LocalAI/pull/8781)AI/pull/8781 * fix(qwen-tts): duplicate instruct argument in voice design mode by @​Weatherco[https://github.com/mudler/LocalAI/pull/8842](https://redirect.github.com/mudler/LocalAI/pull/8842)l/8842 * Fix image upload processing and img2img pipeline in diffusers backend by @​attilagyorf[https://github.com/mudler/LocalAI/pull/8879](https://redirect.github.com/mudler/LocalAI/pull/8879)l/8879 * fix: gate CUDA directory checks on GPU vendor to prevent false CUDA detection by @​sozerc[https://github.com/mudler/LocalAI/pull/8942](https://redirect.github.com/mudler/LocalAI/pull/8942)l/8942 * fix(llama-cpp): Set enable_thinking in the correct place by @​richie[https://github.com/mudler/LocalAI/pull/8973](https://redirect.github.com/mudler/LocalAI/pull/8973)l/8973 ##### Exciting New Features 🎉 * feat(traces): Use accordian instead of pop-ups by @​richie[https://github.com/mudler/LocalAI/pull/8626](https://redirect.github.com/mudler/LocalAI/pull/8626)l/8626 * chore: remove install.sh script and documentation references by @​localai-b[https://github.com/mudler/LocalAI/pull/8643](https://redirect.github.com/mudler/LocalAI/pull/8643)l/8643 * docs: add Podman installation documentation by @​localai-b[https://github.com/mudler/LocalAI/pull/8646](https://redirect.github.com/mudler/LocalAI/pull/8646)l/8646 * Add `sample_rate` support to TTS API via post-processing resampling by @​Copil[https://github.com/mudler/LocalAI/pull/8650](https://redirect.github.com/mudler/LocalAI/pull/8650)l/8650 * feat(backends): add faster-qwen3-tts by @​localai-b[https://github.com/mudler/LocalAI/pull/8664](https://redirect.github.com/mudler/LocalAI/pull/8664)l/8664 * feat(models): add model storage size display and RAM warning by @​localai-b[https://github.com/mudler/LocalAI/pull/8675](https://redirect.github.com/mudler/LocalAI/pull/8675)l/8675 * feat(ui): add model size estimation by @​mudl[https://github.com/mudler/LocalAI/pull/8684](https://redirect.github.com/mudler/LocalAI/pull/8684)l/8684 * feat: Add Free RPC to backend.proto for VRAM cleanup by @​localai-b[https://github.com/mudler/LocalAI/pull/8751](https://redirect.github.com/mudler/LocalAI/pull/8751)l/8751 * feat(qwen-tts): Support using multiple voices by @​nanoandre[https://github.com/mudler/LocalAI/pull/8757](https://redirect.github.com/mudler/LocalAI/pull/8757)l/8757 * feat(ui): move to React for frontend by @​mudl[https://github.com/mudler/LocalAI/pull/8772](https://redirect.github.com/mudler/LocalAI/pull/8772)l/8772 * feat: add WebSocket mode support for the response api by @​bitto[https://github.com/mudler/LocalAI/pull/8676](https://redirect.github.com/mudler/LocalAI/pull/8676)l/8676 * feat: Add LOCALAI_DISABLE_MCP environment variable to disable MCP support by @​localai-b[https://github.com/mudler/LocalAI/pull/8816](https://redirect.github.com/mudler/LocalAI/pull/8816)l/8816 * feat: add agentic management by @​mudl[https://github.com/mudler/LocalAI/pull/8820](https://redirect.github.com/mudler/LocalAI/pull/8820)l/8820 * feat: Add shell completion support for bash, zsh, and fish by @​localai-b[https://github.com/mudler/LocalAI/pull/8851](https://redirect.github.com/mudler/LocalAI/pull/8851)l/8851 * feat(downloader): add HF_MIRROR environment variable support by @​localai-b[https://github.com/mudler/LocalAI/pull/8847](https://redirect.github.com/mudler/LocalAI/pull/8847)l/8847 * feat: add Events column to Agents list page by @​localai-b[https://github.com/mudler/LocalAI/pull/8870](https://redirect.github.com/mudler/LocalAI/pull/8870)l/8870 * feat: Add tabs to System view for Models and Backends by @​localai-b[https://github.com/mudler/LocalAI/pull/8885](https://redirect.github.com/mudler/LocalAI/pull/8885)l/8885 * feat: Add --data-path CLI flag for persistent data separation by @​localai-b[https://github.com/mudler/LocalAI/pull/8888](https://redirect.github.com/mudler/LocalAI/pull/8888)l/8888 * feat(mlx-distributed): add new (experimental) MLX-distributed backend by @​mudl[https://github.com/mudler/LocalAI/pull/8801](https://redirect.github.com/mudler/LocalAI/pull/8801)l/8801 * chore(size): display size of HF models and allow to specify it from the gallery by @​mudl[https://github.com/mudler/LocalAI/pull/8907](https://redirect.github.com/mudler/LocalAI/pull/8907)l/8907 * feat(ui): add canvas mode, support history in agent chat by @​mudl[https://github.com/mudler/LocalAI/pull/8927](https://redirect.github.com/mudler/LocalAI/pull/8927)l/8927 * feat(ui): MCP Apps, mcp streaming and client-side support by @​mudl[https://github.com/mudler/LocalAI/pull/8947](https://redirect.github.com/mudler/LocalAI/pull/8947)l/8947 * feat: add fish-speech backend by @​mudl[https://github.com/mudler/LocalAI/pull/8962](https://redirect.github.com/mudler/LocalAI/pull/8962)l/8962 * feat(backends): add ace-step.cpp by @​mudl[https://github.com/mudler/LocalAI/pull/8965](https://redirect.github.com/mudler/LocalAI/pull/8965)l/8965 * feat(realtime): WebRTC support by @​richie[https://github.com/mudler/LocalAI/pull/8790](https://redirect.github.com/mudler/LocalAI/pull/8790)l/8790 ##### 🧠 Models * chore(model gallery): 🤖 add 1 new models via gallery agent by @​localai-b[https://github.com/mudler/LocalAI/pull/8693](https://redirect.github.com/mudler/LocalAI/pull/8693)l/8693 * chore(model gallery): 🤖 add 1 new models via gallery agent by @​localai-b[https://github.com/mudler/LocalAI/pull/8694](https://redirect.github.com/mudler/LocalAI/pull/8694)l/8694 * chore(model gallery): 🤖 add 1 new models via gallery agent by @​localai-b[https://github.com/mudler/LocalAI/pull/8695](https://redirect.github.com/mudler/LocalAI/pull/8695)l/8695 * chore(model gallery): 🤖 add 1 new models via gallery agent by @​localai-b[https://github.com/mudler/LocalAI/pull/8696](https://redirect.github.com/mudler/LocalAI/pull/8696)l/8696 * chore(model gallery): 🤖 add 1 new models via gallery agent by @​localai-b[https://github.com/mudler/LocalAI/pull/8698](https://redirect.github.com/mudler/LocalAI/pull/8698)l/8698 ##### 📖 Documentation and examples * fix(realtime): Add functions to conversation history by @​richie[https://github.com/mudler/LocalAI/pull/8616](https://redirect.github.com/mudler/LocalAI/pull/8616)l/8616 * docs: update diffusers multi-GPU documentation to mention tensor_parallel_size configuration by @​localai-b[https://github.com/mudler/LocalAI/pull/8621](https://redirect.github.com/mudler/LocalAI/pull/8621)l/8621 * docs: Update Home Assistant links in README.md by @​loryanstra[https://github.com/mudler/LocalAI/pull/8688](https://redirect.github.com/mudler/LocalAI/pull/8688)l/8688 ##### 👒 Dependencies * chore(deps): bump fyne.io/fyne/v2 from 2.7.2 to 2.7.3 by @​dependabot[bo[https://github.com/mudler/LocalAI/pull/8629](https://redirect.github.com/mudler/LocalAI/pull/8629)l/8629 * chore(deps): bump github.com/anthropics/anthropic-sdk-go from 1.22.0 to 1.26.0 by @​dependabot[bo[https://github.com/mudler/LocalAI/pull/8630](https://redirect.github.com/mudler/LocalAI/pull/8630)l/8630 * chore(deps): bump github.com/gpustack/gguf-parser-go from 0.23.1 to 0.24.0 by @​dependabot[bo[https://github.com/mudler/LocalAI/pull/8631](https://redirect.github.com/mudler/LocalAI/pull/8631)l/8631 * chore(deps): bump actions/stale from 10.1.1 to 10.2.0 by @​dependabot[bo[https://github.com/mudler/LocalAI/pull/8633](https://redirect.github.com/mudler/LocalAI/pull/8633)l/8633 * chore(deps): bump goreleaser/goreleaser-action from 6 to 7 by @​dependabot[bo[https://github.com/mudler/LocalAI/pull/8634](https://redirect.github.com/mudler/LocalAI/pull/8634)l/8634 * chore(deps): bump github.com/mudler/cogito from 0.9.1-0.20260217143801-bb7f986ed2c7 to 0.9.1 by @​dependabot[bo[https://github.com/mudler/LocalAI/pull/8632](https://redirect.github.com/mudler/LocalAI/pull/8632)l/8632 * chore(deps): bump grpcio from 1.76.0 to 1.78.1 in /backend/python/coqui by @​dependabot[bo[https://github.com/mudler/LocalAI/pull/8642](https://redirect.github.com/mudler/LocalAI/pull/8642)l/8642 * chore(deps): bump grpcio from 1.76.0 to 1.78.1 in /backend/python/common/template by @​dependabot[bo[https://github.com/mudler/LocalAI/pull/8641](https://redirect.github.com/mudler/LocalAI/pull/8641)l/8641 * chore(deps): bump grpcio from 1.76.0 to 1.78.1 in /backend/python/transformers by @​dependabot[bo[https://github.com/mudler/LocalAI/pull/8640](https://redirect.github.com/mudler/LocalAI/pull/8640)l/8640 * chore(deps): bump sentence-transformers from 5.2.2 to 5.2.3 in /backend/python/transformers by @​dependabot[bo[https://github.com/mudler/LocalAI/pull/8638](https://redirect.github.com/mudler/LocalAI/pull/8638)l/8638 * chore(deps): bump grpcio from 1.76.0 to 1.78.1 in /backend/python/rerankers by @​dependabot[bo[https://github.com/mudler/LocalAI/pull/8636](https://redirect.github.com/mudler/LocalAI/pull/8636)l/8636 * chore(deps): bump grpcio from 1.76.0 to 1.78.1 in /backend/python/vllm by @​dependabot[bo[https://github.com/mudler/LocalAI/pull/8635](https://redirect.github.com/mudler/LocalAI/pull/8635)l/8635 * chore(deps): bump actions/download-artifact from 7 to 8 by @​dependabot[bo[https://github.com/mudler/LocalAI/pull/8729](https://redirect.github.com/mudler/LocalAI/pull/8729)l/8729 * chore(deps): bump actions/upload-artifact from 6 to 7 by @​dependabot[bo[https://github.com/mudler/LocalAI/pull/8730](https://redirect.github.com/mudler/LocalAI/pull/8730)l/8730 * chore(deps): bump github.com/openai/openai-go/v3 from 3.19.0 to 3.24.0 by @​dependabot[bo[https://github.com/mudler/LocalAI/pull/8732](https://redirect.github.com/mudler/LocalAI/pull/8732)l/8732 * chore(deps): bump github.com/modelcontextprotocol/go-sdk from 1.3.0 to 1.4.0 by @​dependabot[bo[https://github.com/mudler/LocalAI/pull/8733](https://redirect.github.com/mudler/LocalAI/pull/8733)l/8733 * chore(deps): bump go.opentelemetry.io/otel from 1.40.0 to 1.41.0 by @​dependabot[bo[https://github.com/mudler/LocalAI/pull/8734](https://redirect.github.com/mudler/LocalAI/pull/8734)l/8734 * chore(deps): bump go.opentelemetry.io/otel/metric from 1.40.0 to 1.41.0 by @​dependabot[bo[https://github.com/mudler/LocalAI/pull/8735](https://redirect.github.com/mudler/LocalAI/pull/8735)l/8735 * chore(deps): bump github.com/google/go-containerregistry from 0.20.7 to 0.21.1 by @​dependabot[bo[https://github.com/mudler/LocalAI/pull/8736](https://redirect.github.com/mudler/LocalAI/pull/8736)l/8736 * chore(deps): bump go.opentelemetry.io/otel/sdk/metric from 1.40.0 to 1.42.0 by @​dependabot[bo[https://github.com/mudler/LocalAI/pull/8915](https://redirect.github.com/mudler/LocalAI/pull/8915)l/8915 * chore(deps): bump github.com/openai/openai-go/v3 from 3.24.0 to 3.26.0 by @​dependabot[bo[https://github.com/mudler/LocalAI/pull/8916](https://redirect.github.com/mudler/LocalAI/pull/8916)l/8916 * chore(deps): bump go.yaml.in/yaml/v2 from 2.4.3 to 2.4.4 by @​dependabot[bo[https://github.com/mudler/LocalAI/pull/8913](https://redirect.github.com/mudler/LocalAI/pull/8913)l/8913 * chore(deps): bump github.com/labstack/echo/v4 from 4.15.0 to 4.15.1 by @​dependabot[bo[https://github.com/mudler/LocalAI/pull/8914](https://redirect.github.com/mudler/LocalAI/pull/8914)l/8914 * chore(deps): bump docker/metadata-action from 5 to 6 by @​dependabot[bo[https://github.com/mudler/LocalAI/pull/8917](https://redirect.github.com/mudler/LocalAI/pull/8917)l/8917 * chore(deps): bump actions/setup-node from 4 to 6 by @​dependabot[bo[https://github.com/mudler/LocalAI/pull/8920](https://redirect.github.com/mudler/LocalAI/pull/8920)l/8920 * chore(deps): bump docker/build-push-action from 6 to 7 by @​dependabot[bo[https://github.com/mudler/LocalAI/pull/8919](https://redirect.github.com/mudler/LocalAI/pull/8919)l/8919 * chore(deps): bump docker/login-action from 3 to 4 by @​dependabot[bo[https://github.com/mudler/LocalAI/pull/8918](https://redirect.github.com/mudler/LocalAI/pull/8918)l/8918 * chore(deps): bump node from 22-slim to 25-slim by @​dependabot[bo[https://github.com/mudler/LocalAI/pull/8922](https://redirect.github.com/mudler/LocalAI/pull/8922)l/8922 ##### Other Changes * docs: ⬆️ update docs version mudler/LocalAI by @​localai-b[https://github.com/mudler/LocalAI/pull/8618](https://redirect.github.com/mudler/LocalAI/pull/8618)l/8618 * chore: ⬆️ Update ggml-org/llama.cpp to `f75c4e8bf52ea480ece07fd3d9a292f1d7f04bc5` by @​localai-b[https://github.com/mudler/LocalAI/pull/8619](https://redirect.github.com/mudler/LocalAI/pull/8619)l/8619 * chore: ⬆️ Update ggml-org/llama.cpp to `2b6dfe824de8600c061ef91ce5cc5c307f97112c` by @​localai-b[https://github.com/mudler/LocalAI/pull/8622](https://redirect.github.com/mudler/LocalAI/pull/8622)l/8622 * chore: ⬆️ Update ggml-org/llama.cpp to `b68a83e641b3ebe6465970b34e99f3f0e0a0b21a` by @​localai-b[https://github.com/mudler/LocalAI/pull/8628](https://redirect.github.com/mudler/LocalAI/pull/8628)l/8628 * fix(webui): use different icon for System nav item by @​localai-b[https://github.com/mudler/LocalAI/pull/8648](https://redirect.github.com/mudler/LocalAI/pull/8648)l/8648 * chore: ⬆️ Update ggml-org/llama.cpp to `418dea39cea85d3496c8b04a118c3b17f3940ad8` by @​localai-b[https://github.com/mudler/LocalAI/pull/8649](https://redirect.github.com/mudler/LocalAI/pull/8649)l/8649 * feat(swagger): update swagger by @​localai-b[https://github.com/mudler/LocalAI/pull/8654](https://redirect.github.com/mudler/LocalAI/pull/8654)l/8654 * chore: ⬆️ Update ggml-org/llama.cpp to `3769fe6eb70b0a0fbb30b80917f1caae68c902f7` by @​localai-b[https://github.com/mudler/LocalAI/pull/8655](https://redirect.github.com/mudler/LocalAI/pull/8655)l/8655 * chore: ⬆️ Update ggml-org/llama.cpp to `723c71064da0908c19683f8c344715fbf6d986fd` by @​localai-b[https://github.com/mudler/LocalAI/pull/8660](https://redirect.github.com/mudler/LocalAI/pull/8660)l/8660 * fix(qwen3.5): add qwen3.5 preset and mimick llama.cpp's PEG by @​mudl[https://github.com/mudler/LocalAI/pull/8668](https://redirect.github.com/mudler/LocalAI/pull/8668)l/8668 * chore: ⬆️ Update ggml-org/whisper.cpp to `9453b4b9be9b73adfc35051083f37cefa039acee` by @​localai-b[https://github.com/mudler/LocalAI/pull/8671](https://redirect.github.com/mudler/LocalAI/pull/8671)l/8671 * chore(deps): bump llama.cpp to 'ecbcb7ea9d3303097519723b264a8b5f1e977028' by @​mudl[https://github.com/mudler/LocalAI/pull/8672](https://redirect.github.com/mudler/LocalAI/pull/8672)l/8672 * docs: add CDI driver config for NVIDIA GPU in containers (fix #​8108) by @​loc[https://github.com/mudler/LocalAI/pull/8677](https://redirect.github.com/mudler/LocalAI/pull/8677)AI/pull/8677 * docs: add TLS reverse proxy configuration guide by @​localai-b[https://github.com/mudler/LocalAI/pull/8673](https://redirect.github.com/mudler/LocalAI/pull/8673)l/8673 * chore: ⬆️ Update ggml-org/llama.cpp to `05728db18eea59de81ee3a7699739daaf015206b` by @​localai-b[https://github.com/mudler/LocalAI/pull/8683](https://redirect.github.com/mudler/LocalAI/pull/8683)l/8683 * fix: simplify CI steps, fix gallery agent by @​mudl[https://github.com/mudler/LocalAI/pull/8685](https://redirect.github.com/mudler/LocalAI/pull/8685)l/8685 * fix: retry when LLM returns empty messages by @​mudl[https://github.com/mudler/LocalAI/pull/8704](https://redirect.github.com/mudler/LocalAI/pull/8704)l/8704 * feat(swagger): update swagger by @​localai-b[https://github.com/mudler/LocalAI/pull/8706](https://redirect.github.com/mudler/LocalAI/pull/8706)l/8706 * feat: Add debug logging for pocket-tts voice issue #​8244 by @​loc[https://github.com/mudler/LocalAI/pull/8715](https://redirect.github.com/mudler/LocalAI/pull/8715)AI/pull/8715 * fix(ci): correct transformer backend path typo by @​localai-b[https://github.com/mudler/LocalAI/pull/8712](https://redirect.github.com/mudler/LocalAI/pull/8712)l/8712 * chore: ⬆️ Update ggml-org/llama.cpp to `319146247e643695f94a558e8ae686277dd4f8da` by @​localai-b[https://github.com/mudler/LocalAI/pull/8707](https://redirect.github.com/mudler/LocalAI/pull/8707)l/8707 * fix: Implement responsive line wrapping for model names (#​8209) by @​loc[https://github.com/mudler/LocalAI/pull/8720](https://redirect.github.com/mudler/LocalAI/pull/8720)AI/pull/8720 * fix(qwen-tts): ensure all requirements files end with newline by @​localai-b[https://github.com/mudler/LocalAI/pull/8724](https://redirect.github.com/mudler/LocalAI/pull/8724)l/8724 * chore(model-gallery): ⬆️ update checksum by @​localai-b[https://github.com/mudler/LocalAI/pull/8728](https://redirect.github.com/mudler/LocalAI/pull/8728)l/8728 * chore: ⬆️ Update ggml-org/llama.cpp to `4d828bd1ab52773ba9570cc008cf209eb4a8b2f5` by @​localai-b[https://github.com/mudler/LocalAI/pull/8727](https://redirect.github.com/mudler/LocalAI/pull/8727)l/8727 * chore(model gallery): 🤖 add 1 new models via gallery agent by @​localai-b[https://github.com/mudler/LocalAI/pull/8743](https://redirect.github.com/mudler/LocalAI/pull/8743)l/8743 * chore: ⬆️ Update ggml-org/llama.cpp to `ecd99d6a9acbc436bad085783bcd5d0b9ae9e9e9` by @​localai-b[https://github.com/mudler/LocalAI/pull/8762](https://redirect.github.com/mudler/LocalAI/pull/8762)l/8762 * chore(model gallery): 🤖 add 1 new models via gallery agent by @​localai-b[https://github.com/mudler/LocalAI/pull/8770](https://redirect.github.com/mudler/LocalAI/pull/8770)l/8770 * chore(model-gallery): ⬆️ update checksum by @​localai-b[https://github.com/mudler/LocalAI/pull/8778](https://redirect.github.com/mudler/LocalAI/pull/8778)l/8778 * chore: ⬆️ Update ggml-org/llama.cpp to `24d2ee052795063afffc9732465ca1b1c65f4a28` by @​localai-b[https://github.com/mudler/LocalAI/pull/8777](https://redirect.github.com/mudler/LocalAI/pull/8777)l/8777 * docs: add autonomous development team section to README by @​localai-b[https://github.com/mudler/LocalAI/pull/8780](https://redirect.github.com/mudler/LocalAI/pull/8780)l/8780 * feat: Rename 'Whisper' model type to 'STT' in UI by @​localai-b[https://github.com/mudler/LocalAI/pull/8785](https://redirect.github.com/mudler/LocalAI/pull/8785)l/8785 * chore: ⬆️ Update ggml-org/whisper.cpp to `30c5194c9691e4e9a98b3dea9f19727397d3f46e` by @​localai-b[https://github.com/mudler/LocalAI/pull/8796](https://redirect.github.com/mudler/LocalAI/pull/8796)l/8796 * chore: ⬆️ Update ggml-org/llama.cpp to `a0ed91a442ea6b013bd42ebc3887a81792eaefa1` by @​localai-b[https://github.com/mudler/LocalAI/pull/8797](https://redirect.github.com/mudler/LocalAI/pull/8797)l/8797 * feat: pass-by metadata to predict options by @​mudl[https://github.com/mudler/LocalAI/pull/8795](https://redirect.github.com/mudler/LocalAI/pull/8795)l/8795 * fix: Add timeout-based wait for model deletion completion by @​localai-b[https://github.com/mudler/LocalAI/pull/8756](https://redirect.github.com/mudler/LocalAI/pull/8756)l/8756 * chore: Add LTX-2.3 model to gallery by @​localai-b[https://github.com/mudler/LocalAI/pull/8805](https://redirect.github.com/mudler/LocalAI/pull/8805)l/8805 * chore: ⬆️ Update ggml-org/llama.cpp to `566059a26b0ce8faec4ea053605719d399c64cc5` by @​localai-b[https://github.com/mudler/LocalAI/pull/8822](https://redirect.github.com/mudler/LocalAI/pull/8822)l/8822 * chore(model gallery): 🤖 add 1 new models via gallery agent by @​localai-b[https://github.com/mudler/LocalAI/pull/8828](https://redirect.github.com/mudler/LocalAI/pull/8828)l/8828 * chore(model gallery): 🤖 add 1 new models via gallery agent by @​localai-b[https://github.com/mudler/LocalAI/pull/8830](https://redirect.github.com/mudler/LocalAI/pull/8830)l/8830 * feat: update descriptions for first 9 models in gallery/index.yaml by @​localai-b[https://github.com/mudler/LocalAI/pull/8831](https://redirect.github.com/mudler/LocalAI/pull/8831)l/8831 * chore: ⬆️ Update ggml-org/llama.cpp to `c5a778891ba0ddbd4cbb507c823f970595b1adc2` by @​localai-b[https://github.com/mudler/LocalAI/pull/8837](https://redirect.github.com/mudler/LocalAI/pull/8837)l/8837 * chore(docs): Populate coding guidelines in CONTRIBUTING.md by @​localai-b[https://github.com/mudler/LocalAI/pull/8840](https://redirect.github.com/mudler/LocalAI/pull/8840)l/8840 * fix: Remove debug print statement from soundgeneration.go (C2) by @​localai-b[https://github.com/mudler/LocalAI/pull/8843](https://redirect.github.com/mudler/LocalAI/pull/8843)l/8843 * docs: Add comprehensive API error reference documentation by @​localai-b[https://github.com/mudler/LocalAI/pull/8848](https://redirect.github.com/mudler/LocalAI/pull/8848)l/8848 * docs: add Table of Contents to README.md by @​localai-b[https://github.com/mudler/LocalAI/pull/8846](https://redirect.github.com/mudler/LocalAI/pull/8846)l/8846 * chore: ⬆️ Update leejet/stable-diffusion.cpp to c8fb3d245858d495be1f140efdcfaa0d49de41e5 by @​localai-b[https://github.com/mudler/LocalAI/pull/8841](https://redirect.github.com/mudler/LocalAI/pull/8841)l/8841 * docs: clarify SECURITY.md version support table with specific ranges and EOL dates by @​localai-b[https://github.com/mudler/LocalAI/pull/8861](https://redirect.github.com/mudler/LocalAI/pull/8861)l/8861 * fix: Correct Talk Interface screenshot reference in README.md (H6) by @​localai-b[https://github.com/mudler/LocalAI/pull/8857](https://redirect.github.com/mudler/LocalAI/pull/8857)l/8857 * feat: Add documentation for undocumented API endpoints by @​localai-b[https://github.com/mudler/LocalAI/pull/8852](https://redirect.github.com/mudler/LocalAI/pull/8852)l/8852 * docs: add comprehensive development setup instructions to CONTRIBUTING.md (H7) by @​localai-b[https://github.com/mudler/LocalAI/pull/8860](https://redirect.github.com/mudler/LocalAI/pull/8860)l/8860 * feat(cli): add configurable backend image fallback tags via CLI options by @​localai-b[https://github.com/mudler/LocalAI/pull/8817](https://redirect.github.com/mudler/LocalAI/pull/8817)l/8817 * feat: add MIT license badge to README.md by @​localai-b[https://github.com/mudler/LocalAI/pull/8871](https://redirect.github.com/mudler/LocalAI/pull/8871)l/8871 * feat: Create comprehensive troubleshooting guide (M1 task) by @​localai-b[https://github.com/mudler/LocalAI/pull/8856](https://redirect.github.com/mudler/LocalAI/pull/8856)l/8856 * docs: expand GPU acceleration guide with L4T, multi-GPU, monitoring, and troubleshooting by @​localai-b[https://github.com/mudler/LocalAI/pull/8858](https://redirect.github.com/mudler/LocalAI/pull/8858)l/8858 * feat: Add documentation URLs to CLI help text by @​localai-b[https://github.com/mudler/LocalAI/pull/8874](https://redirect.github.com/mudler/LocalAI/pull/8874)l/8874 * feat(functions): add peg-based parsing and allow backends to return tool calls directly by @​mudl[https://github.com/mudler/LocalAI/pull/8838](https://redirect.github.com/mudler/LocalAI/pull/8838)l/8838 * chore: Update README.md screenshot references and alt text by @​localai-b[https://github.com/mudler/LocalAI/pull/8862](https://redirect.github.com/mudler/LocalAI/pull/8862)l/8862 * chore: ⬆️ Update ggml-org/llama.cpp to `35bee031e17ed2b2e8e7278b284a6c8cd120d9f8` by @​localai-b[https://github.com/mudler/LocalAI/pull/8872](https://redirect.github.com/mudler/LocalAI/pull/8872)l/8872 * docs: Update model compatibility documentation with missing backends by @​localai-b[https://github.com/mudler/LocalAI/pull/8889](https://redirect.github.com/mudler/LocalAI/pull/8889)l/8889 * docs: make examples repository link more prominent by @​localai-b[https://github.com/mudler/LocalAI/pull/8895](https://redirect.github.com/mudler/LocalAI/pull/8895)l/8895 * chore(model gallery): 🤖 add 1 new models via gallery agent by @​localai-b[https://github.com/mudler/LocalAI/pull/8901](https://redirect.github.com/mudler/LocalAI/pull/8901)l/8901 * chore(model gallery): 🤖 add 1 new models via gallery agent by @​localai-b[https://github.com/mudler/LocalAI/pull/8902](https://redirect.github.com/mudler/LocalAI/pull/8902)l/8902 * chore(model gallery): 🤖 add 1 new models via gallery agent by @​localai-b[https://github.com/mudler/LocalAI/pull/8904](https://redirect.github.com/mudler/LocalAI/pull/8904)l/8904 * feat: Redesign explorer and models pages with react-ui theme by @​localai-b[https://github.com/mudler/LocalAI/pull/8903](https://redirect.github.com/mudler/LocalAI/pull/8903)l/8903 * fix(ui): minor visual enhancements by @​mudl[https://github.com/mudler/LocalAI/pull/8909](https://redirect.github.com/mudler/LocalAI/pull/8909)l/8909 * feat(swagger): update swagger by @​localai-b[https://github.com/mudler/LocalAI/pull/8923](https://redirect.github.com/mudler/LocalAI/pull/8923)l/8923 * feat: Standardize CLI flag naming to kebab-case (M12) by @​localai-b[https://github.com/mudler/LocalAI/pull/8912](https://redirect.github.com/mudler/LocalAI/pull/8912)l/8912 * chore: ⬆️ Update leejet/stable-diffusion.cpp to `d6dd6d7b555c233bb9bc9f20b4751eb8c9269743` by @​localai-b[https://github.com/mudler/LocalAI/pull/8925](https://redirect.github.com/mudler/LocalAI/pull/8925)l/8925 * chore: ⬆️ Update ggml-org/llama.cpp to `23fbfcb1ad6c6f76b230e8895254de785000be46` by @​localai-b[https://github.com/mudler/LocalAI/pull/8921](https://redirect.github.com/mudler/LocalAI/pull/8921)l/8921 * fix: correct grammar in CONTRIBUTING.md documentation section by @​localai-b[https://github.com/mudler/LocalAI/pull/8932](https://redirect.github.com/mudler/LocalAI/pull/8932)l/8932 * feat: Expand section index pages with comprehensive navigation (M7) by @​localai-b[https://github.com/mudler/LocalAI/pull/8929](https://redirect.github.com/mudler/LocalAI/pull/8929)l/8929 * chore(model gallery): 🤖 add 1 new models via gallery agent by @​localai-b[https://github.com/mudler/LocalAI/pull/8939](https://redirect.github.com/mudler/LocalAI/pull/8939)l/8939 * chore(model-gallery): ⬆️ update checksum by @​localai-b[https://github.com/mudler/LocalAI/pull/8945](https://redirect.github.com/mudler/LocalAI/pull/8945)l/8945 * chore: ⬆️ Update ggml-org/llama.cpp to `10e5b148b061569aaee8ae0cf72a703129df0eab` by @​localai-b[https://github.com/mudler/LocalAI/pull/8946](https://redirect.github.com/mudler/LocalAI/pull/8946)l/8946 * fix: include model name in mmproj file path to prevent model isolation (#​8937) by @​loc[https://github.com/mudler/LocalAI/pull/8940](https://redirect.github.com/mudler/LocalAI/pull/8940)AI/pull/8940 * feat(swagger): update swagger by @​localai-b[https://github.com/mudler/LocalAI/pull/8961](https://redirect.github.com/mudler/LocalAI/pull/8961)l/8961 * docs: Document GPU auto-fit mode limitations and trade-offs (closes #​8562) by @​loc[https://github.com/mudler/LocalAI/pull/8954](https://redirect.github.com/mudler/LocalAI/pull/8954)AI/pull/8954 * chore(ui): improve errors and reporting during model installation by @​mudl[https://github.com/mudler/LocalAI/pull/8979](https://redirect.github.com/mudler/LocalAI/pull/8979)l/8979 * chore(model gallery): 🤖 add 1 new models via gallery agent by @​localai-b[https://github.com/mudler/LocalAI/pull/8980](https://redirect.github.com/mudler/LocalAI/pull/8980)l/8980 * fix(collections): start agent pool after http server by @​mudl[https://github.com/mudler/LocalAI/pull/8981](https://redirect.github.com/mudler/LocalAI/pull/8981)l/8981 * chore(model-gallery): ⬆️ update checksum by @​localai-b[https://github.com/mudler/LocalAI/pull/8985](https://redirect.github.com/mudler/LocalAI/pull/8985)l/8985 * chore: ⬆️ Update ggml-org/llama.cpp to `57819b8d4b39d893408e51520dff3d47d1ebb757` by @​localai-b[https://github.com/mudler/LocalAI/pull/8983](https://redirect.github.com/mudler/LocalAI/pull/8983)l/8983 * chore: ⬆️ Update ace-step/acestep.cpp to `5aa065445541094cba934299cd498bbb9fa5c434` by @​localai-b[https://github.com/mudler/LocalAI/pull/8984](https://redirect.github.com/mudler/LocalAI/pull/8984)l/8984 * fix(ui): Move routes to /app to avoid conflict with API endpoints by @​richie[https://github.com/mudler/LocalAI/pull/8978](https://redirect.github.com/mudler/LocalAI/pull/8978)l/8978 * fix(conf): Don't overwrite env provided galleries with runtime conf by @​richie[https://github.com/mudler/LocalAI/pull/8994](https://redirect.github.com/mudler/LocalAI/pull/8994)l/8994 * fix(flux.2-klein-9b): Use Qwen3-8b to avoid GGML assertion failure on tensor mismatch by @​richie[https://github.com/mudler/LocalAI/pull/8995](https://redirect.github.com/mudler/LocalAI/pull/8995)l/8995 * fix(acestep-cpp): resolve relative model paths in options by @​localai-b[https://github.com/mudler/LocalAI/pull/8993](https://redirect.github.com/mudler/LocalAI/pull/8993)l/8993 * chore: ⬆️ Update ggml-org/llama.cpp to `e30f1fdf74ea9238ff562901aa974c75aab6619b` by @​localai-b[https://github.com/mudler/LocalAI/pull/8997](https://redirect.github.com/mudler/LocalAI/pull/8997)l/8997 </details> #### New Contributors * @​loryanstrant made their first contributi[https://github.com/mudler/LocalAI/pull/8688](https://redirect.github.com/mudler/LocalAI/pull/8688)l/8688 * @​bittoby made their first contributi[https://github.com/mudler/LocalAI/pull/8676](https://redirect.github.com/mudler/LocalAI/pull/8676)l/8676 * @​Weathercold made their first contributi[https://github.com/mudler/LocalAI/pull/8842](https://redirect.github.com/mudler/LocalAI/pull/8842)l/8842 * @​attilagyorffy made their first contributi[https://github.com/mudler/LocalAI/pull/8879](https://redirect.github.com/mudler/LocalAI/pull/8879)l/8879 **Full Changelog**: <https://github.com/mudler/LocalAI/compare/v3.12.1...v4.0.0> </details> --- ### Configuration 📅 **Schedule**: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined). 🚦 **Automerge**: Disabled by config. Please merge this manually once you are satisfied. ♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox. 🔕 **Ignore**: Close this PR and you won't be reminded about this update again. --- - [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check this box --- This PR has been generated by [Renovate Bot](https://redirect.github.com/renovatebot/renovate). <!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiI0My4yOS4yIiwidXBkYXRlZEluVmVyIjoiNDMuMjkuMiIsInRhcmdldEJyYW5jaCI6Im1hc3RlciIsImxhYmVscyI6WyJhcHAvbG9jYWwtYWkiLCJyZW5vdmF0ZS9jb250YWluZXIiLCJ0eXBlL21ham9yIl19-->
This commit is contained in:
TrueCharts Bot
@@ -8,7 +8,7 @@ annotations:
|
||||
trueforge.org/min_helm_version: "3.14"
|
||||
trueforge.org/train: stable
|
||||
apiVersion: v2
|
||||
appVersion: 3.12.1
|
||||
appVersion: 4.0.0
|
||||
dependencies:
|
||||
- name: common
|
||||
version: 28.33.4
|
||||
@@ -35,5 +35,5 @@ sources:
|
||||
- https://github.com/trueforge-org/truecharts/tree/master/charts/stable/local-ai
|
||||
- https://hub.docker.com/r/localai/localai
|
||||
type: application
|
||||
version: 16.58.2
|
||||
version: 17.0.0
|
||||
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
image:
|
||||
repository: docker.io/localai/localai
|
||||
pullPolicy: IfNotPresent
|
||||
tag: v3.12.1@sha256:558efc7610e2ce43e702eaed4fcf456102a416471929d99819ef251fdbbf8b51
|
||||
tag: v4.0.0@sha256:b841e2bef58b6277b2024726e18b01d2067c8fa44e47c687fd22e41044a4efb0
|
||||
ffmpegImage:
|
||||
repository: docker.io/localai/localai
|
||||
pullPolicy: IfNotPresent
|
||||
|
||||
Reference in New Issue
Block a user