* docs: add comprehensive development setup instructions to CONTRIBUTING.md
- Expand prerequisites with Go version requirements and installation links
- Add system dependencies for Ubuntu/Debian, CentOS/RHEL/Fedora, macOS, and Windows
- Document build commands with explanations and key build variables
- Add environment variables section with useful development env vars
- Include development workflow guidelines (branch naming, commit format, PR process)
- Enhance testing section with per-package and focused test instructions
* Apply suggestions from code review
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
---------
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Co-authored-by: localai-bot <localai-bot@noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* feat: add documentation for undocumented API endpoints
Creates comprehensive documentation for 8 previously undocumented endpoints:
- Voice Activity Detection (/v1/vad)
- Video Generation (/video)
- Sound Generation (/v1/sound-generation)
- Backend Monitor (/backend/monitor, /backend/shutdown)
- Token Metrics (/tokenMetrics)
- P2P endpoints (/api/p2p/* - 5 sub-endpoints)
- System Info (/system, /version)
Each documentation file includes HTTP method, request/response schemas,
curl examples, sample JSON responses, and error codes.
* docs: remove token-metrics endpoint documentation per review feedback
The token-metrics endpoint is not wired into the HTTP router and
should not be documented per reviewer request.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* docs: move system-info documentation to reference section
Per review feedback, system-info endpoint docs are better suited
for the reference section rather than features.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: localai-bot <localai-bot@noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* docs: clarify SECURITY.md version support table with specific ranges and EOL dates
- Add detailed version support table with 3.x (actively supported), 2.x (security fixes until Dec 31, 2026), and 1.x (EOL since Jan 1, 2024)
- Define what each support level means for users
- Add migration guidance for users on older versions
- Replace vague version ranges with specific, actionable information
Signed-off-by: localai-bot <localai-bot@noreply.github.com>
* Apply suggestions from code review
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
---------
Signed-off-by: localai-bot <localai-bot@noreply.github.com>
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Co-authored-by: localai-bot <localai-bot@noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* chore: ⬆️ update stable-diffusion.cpp to `c8fb3d245858d495be1f140efdcfaa0d49de41e5`
Update stablediffusion-ggml to include fix for SD1 Pix2Pix issue
(leejet/stable-diffusion.cpp#1329).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Signed-off-by: localai-bot <localai-bot@noreply.github.com>
* fix: address CI failures in stablediffusion update
Signed-off-by: localai-bot <localai-bot@noreply.github.com>
* fix: resolve remaining CI failures in stablediffusion update
- Move flow_shift to global scope so gen_image() can access the value
set during load_model() (was causing compilation error)
- Fix sd_type_str array: TQ1_0 should be at index 34, TQ2_0 at index 35
to match upstream SD_TYPE_TQ1_0=34, SD_TYPE_TQ2_0=35 enum values
Signed-off-by: localai-bot <localai-bot@noreply.github.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Signed-off-by: localai-bot <localai-bot@noreply.github.com>
Co-authored-by: localai-bot <localai-bot@noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
- Added HF_MIRROR env var to configure HuggingFace mirror URLs
- HF_MIRROR takes precedence over HF_ENDPOINT for simpler mirror config
- Supports both full URLs (https://hf-mirror.com) and simple hostnames (hf-mirror.com)
- Auto-adds https:// if no scheme is provided
- Also supports HF env var as an alias for HF_MIRROR
Closes#8414
Signed-off-by: localai-bot <localai-bot@users.noreply.github.com>
Co-authored-by: localai-bot <localai-bot@users.noreply.github.com>
feat: add shell completion support for bash, zsh, and fish
- Add core/cli/completion.go with dynamic completion script generation
- Add core/cli/completion_test.go with unit tests
- Modify cmd/local-ai/main.go to support completion command
- Modify core/cli/cli.go to add Completion subcommand
- Add docs/content/features/shell-completion.md with installation instructions
The completion scripts are generated dynamically from the Kong CLI model,
so they automatically include all commands, subcommands, and flags.
Co-authored-by: localai-bot <localai-bot@noreply.github.com>
docs: add Table of Contents to README.md for easier navigation
- Add collapsible TOC with anchor links to all major sections
- Include H2 sections and important H3 subsections
- Place TOC after main description, before Local Stack Family
- Use proper markdown anchor link format
Signed-off-by: localai-bot <localai-bot@noreply.github.com>
Co-authored-by: localai-bot <localai-bot@noreply.github.com>
docs: add comprehensive API error reference documentation
Document all error response formats (OpenAI, Anthropic, Open Responses),
HTTP status codes, per-endpoint error scenarios, and client error handling
examples based on actual error handling code in the codebase.
Signed-off-by: localai-bot <localai-bot@noreply.github.com>
Co-authored-by: localai-bot <localai-bot@noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Don't pass instruct because it is added to kwargs
Fixes the error `qwen_tts.inference.qwen3_tts_model.Qwen3TTSModel.generate_voice_design() got multiple values for keyword argument 'instruct'`
Signed-off-by: Weathercold <weathercold.scr@proton.me>
feat: update descriptions for first 9 models in gallery/index.yaml from HuggingFace model cards
- Updated qwen3.5-27b-claude-4.6-opus-reasoning-distilled-i1 with reasoning capabilities
- Updated qwen3.5-4b-claude-4.6-opus-reasoning-distilled with reasoning capabilities
- Updated q3.5-bluestar-27b with fine-tuned variant description
- Updated qwen3.5-9b with multimodal capabilities
- Updated qwen3.5-397b-a17b with large-scale model description
- Updated qwen3.5-27b with performance-efficiency balance
- Updated qwen3.5-122b-a10b with MoE architecture description
- Updated qwen3.5-35b-a3b with MoE architecture description
- Updated qwen3-next-80b-a3b-thinking with next-gen model description
Descriptions sourced from HuggingFace model API metadata.
Co-authored-by: localai-bot <localai-bot@users.noreply.github.com>
* feat: add standalone and agentic functionalities
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* expose agents via responses api
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat: Add LOCALAI_DISABLE_MCP environment variable to disable MCP support
- Added DisableMCP field to RunCMD struct in core/cli/run.go
- Added LOCALAI_DISABLE_MCP environment variable support
- Added DisableMCP field to ApplicationConfig struct
- Added DisableMCP AppOption function
- Updated MCP endpoint routing to check appConfig.DisableMCP
- When LOCALAI_DISABLE_MCP is set to true/1/yes, MCP endpoints are not registered
When set, all MCP functionality is disabled and appropriate error messages
are returned to users.
Use Cases:
- Security-conscious deployments where MCP is not needed
- Reducing attack surface
- Compliance requirements that prohibit certain protocol support
Environment variable: LOCALAI_DISABLE_MCP=true
Signed-off-by: localai-bot <localai-bot@users.noreply.github.com>
* docs: Add documentation for LOCALAI_DISABLE_MCP environment variable
- Add section explaining how to disable MCP support using environment variable
- Document use cases for disabling MCP
- Provide examples for CLI and Docker usage
Signed-off-by: localai-bot <localai-bot@users.noreply.github.com>
---------
Signed-off-by: localai-bot <localai-bot@users.noreply.github.com>
Co-authored-by: localai-bot <localai-bot@users.noreply.github.com>
* fix: Add timeout-based wait for model deletion completion
- Replace simple polling loop with context-based timeout (5 minutes)
- Use select statement for cleaner timeout handling
- Added proper logging for timeout case
- This addresses the code review comment about using context with timeout instead of dangerous polling approach
* Apply suggestion from @mudler
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* fix: replace goto statements with break in model deletion loop (fixes CI compilation error)
Signed-off-by: LocalAI [bot] <localai-bot@noreply.github.com>
* Apply suggestion from @mudler
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
---------
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Signed-off-by: LocalAI [bot] <localai-bot@noreply.github.com>
Co-authored-by: localai-bot <localai-bot@users.noreply.github.com>
Co-authored-by: LocalAI [bot] <localai-bot@noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* feat: Rename 'Whisper' model type to 'STT' in UI
- Updated models.html: Changed 'Whisper' filter button to 'STT'
- Updated talk.html: Changed 'Whisper Model' to 'STT Model'
- Updated backends.html: Changed 'Whisper' to 'STT'
- Updated talk.js: Renamed getWhisperModel() to getSTTModel(),
sendAudioToWhisper() to sendAudioToSTT(), and whisperModelSelect to sttModelSelect
This change makes the UI more consistent with the model category naming,
where all speech-to-text models (including Whisper, Parakeet, Moonshine,
WhisperX, etc.) are grouped under the 'STT' (Speech-to-Text) category.
Fixes#8776
Signed-off-by: team-coding-agent-1 <team-coding-agent-1@localai.dev>
* Rename whisperModelSelect to sttModelSelect in talk.html
As requested by maintainer mudler in PR review, replacing all
whisperModelSelect occurrences with sttModelSelect since the
model type was renamed from Whisper to STT.
Signed-off-by: LocalAI [bot] <localai-bot@users.noreply.github.com>
---------
Signed-off-by: team-coding-agent-1 <team-coding-agent-1@localai.dev>
Signed-off-by: LocalAI [bot] <localai-bot@users.noreply.github.com>
Co-authored-by: team-coding-agent-1 <team-coding-agent-1@localai.dev>
Co-authored-by: LocalAI [bot] <localai-bot@users.noreply.github.com>
fix: Add vllm-omni backend to video generation model detection
- Include vllm-omni in the list of backends that support FLAG_VIDEO
- This allows models like vllm-omni-wan2.2-t2v to appear in the video model selector UI
- Fixes issue #8659 where video generation models using vllm-omni backend were not showing in the dropdown
Co-authored-by: team-coding-agent-1 <team-coding-agent-1@localai.dev>
* docs: add autonomous development team section to README
- Add blog post link to Media, Blogs, Social section
- Add new section about autonomous AI agent maintenance team
- Include links to reports.localai.io and project board
- Reference the experiment blog post
* Apply suggestion from @mudler
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
---------
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Co-authored-by: team-coding-agent-1 <team-coding-agent-1@localai.dev>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* Add support for multiple voice clones in Qwen TTS
Signed-off-by: Andres Smith <andressmithdev@pm.me>
* Add voice prompt caching and generation logs to see generation time
---------
Signed-off-by: Andres Smith <andressmithdev@pm.me>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
fix: return full embedding dimensions instead of truncating trailing zeros
- Remove the logic that strips trailing zeros from embeddings
- Trailing zeros may be valid values in some embedding models
- This fixes the issue where embeddings like jina-v3 returned
only 1/4 of their native dimensions (256 instead of 1024)
- The truncation was causing vector database dimension mismatch errors
- Fixes issue #8721
Signed-off-by: localai-bot <localai-bot@users.noreply.github.com>
Co-authored-by: localai-bot <localai-bot@users.noreply.github.com>
* fix: Add VRAM cleanup when stopping models
- Add Free() method to AIModel interface for proper GPU resource cleanup
- Implement Free() in llama backend to release llama.cpp model resources
- Add Free() stub implementations in base and SingleThread backends
- Modify deleteProcess() to call Free() before stopping the process
to ensure VRAM is properly released when models are unloaded
Fixes issue where VRAM was not freed when stopping models, which
could lead to memory exhaustion when running multiple models
sequentially.
* feat: Add Free RPC to backend.proto for VRAM cleanup\n\n- Add rpc Free(HealthMessage) returns (Result) {} to backend.proto\n- This RPC is required to properly expose the Free() method\n through the gRPC interface for VRAM resource cleanup\n\nRefs: PR #8739
* Apply suggestion from @mudler
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
---------
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Co-authored-by: localai-bot <localai-bot@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
