docs: Add troubleshooting guide for embedding models (#9064)
- Add section on using gallery models for embeddings
- Document common issues with embedding model configuration
- Add troubleshooting guide for Qwen3 embedding models
- Include correct configuration examples for Qwen3-Embedding-4B
- Document context size limits and dimension parameters
- Add table of Qwen3 embedding model specifications
Fixes#9064
Signed-off-by: localai-bot <localai-bot@localai.io>
Co-authored-by: localai-bot <localai-bot@localai.io>
* feat(ui, gallery): Display and filter by the backend models use
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* feat(ui): Add searchable model backend/model selector and prevent delete models being selected
Signed-off-by: Richard Palethorpe <io@richiejp.com>
---------
Signed-off-by: Richard Palethorpe <io@richiejp.com>
- Add 'agent' subcommand with 'run' and 'list' sub-commands
- Support running agents by name from pool.json registry
- Support running agents from JSON config files
- Implement foreground mode with --prompt flag for single-turn interactions
- Reuse AgentPoolService for consistent agent initialization
- Add comprehensive unit tests for config loading and overrides
Fixes#8960
Signed-off-by: localai-bot <localai-bot@users.noreply.github.com>
Co-authored-by: localai-bot <localai-bot@noreply.github.com>
* fix(openresponses): do not omit required fields summary and id
* fix(openresponses): ensure ORItemParam.Summary is never null
Normalize Summary to an empty slice at serialization chokepoints
(sendSSEEvent, bufferEvent, buildORResponse) so it always serializes
as [] instead of null.
Closes#9047
* feat(gallery): Switch to expandable box instead of pop-over and display model files
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* feat(ui, backends): Add individual backend logging
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* fix(ui): Set the context settings from the model config
Signed-off-by: Richard Palethorpe <io@richiejp.com>
---------
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* fix: Automatically disable mmap for Intel SYCL backends
Fixes issue #9012 where Qwen3.5 models fail to load on Intel Arc GPU
with RPC EOF error.
The Intel SYCL backend has a known issue where mmap enabled causes
the backend to hang. This change automatically disables mmap when
detecting Intel or SYCL backends.
References:
- https://github.com/mudler/LocalAI/issues/9012
- Documentation mentions: SYCL hangs when mmap: true is set
* feat: Add logging for mmap auto-disable on Intel SYCL backends
As requested in PR review, add xlog.Info call to log when mmap
is automatically disabled for Intel SYCL backends. This helps
with debugging and confirms the auto-disable logic is working.
---------
Co-authored-by: localai-bot <localai-bot@users.noreply.github.com>
AIO images are behind, and takes effort to maintain these. Wizard and
installation of models have been semplified massively, so AIO images
lost their purpose.
This allows us to be more laser focused on main images and reliefes
stress from CI.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(acestep-cpp): resolve relative model paths in options
The acestep-cpp backend was failing to load models because the model
paths in options (text_encoder_model, dit_model, vae_model) were being
passed to the C++ code without resolving their relative paths.
When a user configures acestep-cpp-turbo-4b, the model paths are specified
as relative paths like 'acestep-cpp/acestep-v15-turbo-Q8_0.gguf'. The
backend was passing these paths directly to the C++ code without joining
them with the model directory.
This fix:
1. Gets the base directory from the ModelFile path
2. Resolves all relative paths in options to be absolute paths
3. Adds debug logging to show resolved paths for troubleshooting
Fixes#8991
Signed-off-by: localai-bot <localai-bot@users.noreply.github.com>
* Apply suggestion from @mudler
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* test: fix acestep tests to not join modeldir in options
According to code review feedback, the Options array in TestLoadModel
and TestSoundGeneration should contain just the model filenames without
filepath.Join with modelDir. The model paths are handled internally by
the backend.
* fix: change bpm parameter type to float32 to match C++ API signature
* test: fix TestLoadModel and TestSoundGeneration to use baseDir for model paths
- Modified TestLoadModel to compute baseDir from main model path and use it for relative model paths
- Modified TestSoundGeneration similarly to use baseDir for model paths
- Changed bpm parameter type from int32 to float32 to match C++ API
* Apply suggestions from code review
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* Apply suggestions from code review
Co-authored-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@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>
Also test for regressions in HTTP GET API key exempted endpoints because
this list can get out of sync with the UI routes.
Also fix support for proxying on a different prefix both server and
client side.
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* feat(realtime): WebRTC support
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* fix(tracing): Show full LLM opts and deltas
Signed-off-by: Richard Palethorpe <io@richiejp.com>
---------
Signed-off-by: Richard Palethorpe <io@richiejp.com>
