mirror of
https://github.com/mudler/LocalAI.git
synced 2026-06-18 21:58:58 -04:00
Squashed feat/pii-ner-tier-engine rebased onto master (was 45 commits; see backup/pii-ner-tier-engine-prerebase). Net change: - privacy-filter.cpp: standalone GGML engine for the openai-privacy-filter PII/NER token classifier, wired as a LocalAI gRPC backend (CPU/CUDA/Vulkan). TokenClassify moves off the patched llama.cpp path onto this backend. - PII filter reworked to be NER-centric (encoder/NER detection tier scanning whole conversations as one document), with a recreated bounded restricted- regex secret-matching pattern detector tier alongside it (per-model pii_detection.builtins / .patterns + core/services/routing/piipattern). - Detection labelled by source (ner vs pattern); backend trace / confidence / debug observability; analyze/redact exposed as a synchronous API. - Instance-wide default detector policy + per-usecase default-on; request filtering extended to completions, embeddings, edits & Ollama. - React UI: NER-centric PII editor, detector-models table, pattern/builtins editor, middleware default-policy UI. - Gallery: privacy-filter-multilingual token-classify model + NER install filter; token_classify known_usecase; batch sized to context for NER models. privacy-filter backend registered in the backend gallery (cpu/vulkan/cuda-13 meta + image entries with a capabilities map) matching its CI matrix jobs, and an /import-model auto-detect importer (PrivacyFilterImporter, narrow privacy-filter GGUF detection) replacing the prior pref-only registration. Reconciled against master's independent evolution: - Dropped master's PIIPatternOverrides feature (global-pattern runtime overrides + /api/pii/patterns API + runtime_settings.json persistence). The per-model NER + pattern-detector design supersedes it; it was built on the global redactor pattern set this branch replaced. - Reverted the llama.cpp Score carry-patch (0006-server-task-type-score): removed the patch and restored master's grpc-server.cpp Score RPC (direct llama_decode, slot-loop bypass) and LLAMA_VERSION pin, plus master's model_config validation forbidding score + chat/completion/embeddings on llama-cpp. token_classify is unaffected (it runs on the privacy-filter backend, not llama-cpp). Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Richard Palethorpe <io@richiejp.com>
153 lines
6.0 KiB
YAML
153 lines
6.0 KiB
YAML
name: Bump Backend dependencies
|
|
on:
|
|
schedule:
|
|
- cron: 0 20 * * *
|
|
workflow_dispatch:
|
|
jobs:
|
|
bump-backends:
|
|
if: github.repository == 'mudler/LocalAI'
|
|
strategy:
|
|
fail-fast: false
|
|
matrix:
|
|
include:
|
|
- repository: "ggml-org/llama.cpp"
|
|
variable: "LLAMA_VERSION"
|
|
branch: "master"
|
|
file: "backend/cpp/llama-cpp/Makefile"
|
|
- repository: "ikawrakow/ik_llama.cpp"
|
|
variable: "IK_LLAMA_VERSION"
|
|
branch: "main"
|
|
file: "backend/cpp/ik-llama-cpp/Makefile"
|
|
- repository: "TheTom/llama-cpp-turboquant"
|
|
variable: "TURBOQUANT_VERSION"
|
|
branch: "feature/turboquant-kv-cache"
|
|
file: "backend/cpp/turboquant/Makefile"
|
|
- repository: "antirez/ds4"
|
|
variable: "DS4_VERSION"
|
|
branch: "main"
|
|
file: "backend/cpp/ds4/Makefile"
|
|
- repository: "localai-org/privacy-filter.cpp"
|
|
variable: "PRIVACY_FILTER_VERSION"
|
|
branch: "master"
|
|
file: "backend/cpp/privacy-filter/Makefile"
|
|
- repository: "ggml-org/whisper.cpp"
|
|
variable: "WHISPER_CPP_VERSION"
|
|
branch: "master"
|
|
file: "backend/go/whisper/Makefile"
|
|
- repository: "CrispStrobe/CrispASR"
|
|
variable: "CRISPASR_VERSION"
|
|
branch: "main"
|
|
file: "backend/go/crispasr/Makefile"
|
|
- repository: "mudler/parakeet.cpp"
|
|
variable: "PARAKEET_VERSION"
|
|
branch: "master"
|
|
file: "backend/go/parakeet-cpp/Makefile"
|
|
- repository: "mudler/depth-anything.cpp"
|
|
variable: "DEPTHANYTHING_VERSION"
|
|
branch: "master"
|
|
file: "backend/go/depth-anything-cpp/Makefile"
|
|
- repository: "leejet/stable-diffusion.cpp"
|
|
variable: "STABLEDIFFUSION_GGML_VERSION"
|
|
branch: "master"
|
|
file: "backend/go/stablediffusion-ggml/Makefile"
|
|
- repository: "mudler/go-piper"
|
|
variable: "PIPER_VERSION"
|
|
branch: "master"
|
|
file: "backend/go/piper/Makefile"
|
|
- repository: "antirez/voxtral.c"
|
|
variable: "VOXTRAL_VERSION"
|
|
branch: "main"
|
|
file: "backend/go/voxtral/Makefile"
|
|
- repository: "ace-step/acestep.cpp"
|
|
variable: "ACESTEP_CPP_VERSION"
|
|
branch: "master"
|
|
file: "backend/go/acestep-cpp/Makefile"
|
|
- repository: "PABannier/sam3.cpp"
|
|
variable: "SAM3_VERSION"
|
|
branch: "main"
|
|
file: "backend/go/sam3-cpp/Makefile"
|
|
- repository: "mudler/rf-detr.cpp"
|
|
variable: "RFDETR_VERSION"
|
|
branch: "main"
|
|
file: "backend/go/rfdetr-cpp/Makefile"
|
|
- repository: "mudler/locate-anything.cpp"
|
|
variable: "LOCATEANYTHING_VERSION"
|
|
branch: "master"
|
|
file: "backend/go/locate-anything-cpp/Makefile"
|
|
- repository: "ServeurpersoCom/qwentts.cpp"
|
|
variable: "QWEN3TTS_CPP_VERSION"
|
|
branch: "master"
|
|
file: "backend/go/qwen3-tts-cpp/Makefile"
|
|
- repository: "ServeurpersoCom/omnivoice.cpp"
|
|
variable: "OMNIVOICE_VERSION"
|
|
branch: "master"
|
|
file: "backend/go/omnivoice-cpp/Makefile"
|
|
- repository: "localai-org/vibevoice.cpp"
|
|
variable: "VIBEVOICE_CPP_VERSION"
|
|
branch: "master"
|
|
file: "backend/go/vibevoice-cpp/Makefile"
|
|
runs-on: ubuntu-latest
|
|
steps:
|
|
- uses: actions/checkout@v6
|
|
- name: Bump dependencies 🔧
|
|
id: bump
|
|
run: |
|
|
bash .github/bump_deps.sh ${{ matrix.repository }} ${{ matrix.branch }} ${{ matrix.variable }} ${{ matrix.file }}
|
|
{
|
|
echo 'message<<EOF'
|
|
cat "${{ matrix.variable }}_message.txt"
|
|
echo EOF
|
|
} >> "$GITHUB_OUTPUT"
|
|
{
|
|
echo 'commit<<EOF'
|
|
cat "${{ matrix.variable }}_commit.txt"
|
|
echo EOF
|
|
} >> "$GITHUB_OUTPUT"
|
|
rm -rfv ${{ matrix.variable }}_message.txt
|
|
rm -rfv ${{ matrix.variable }}_commit.txt
|
|
- name: Create Pull Request
|
|
uses: peter-evans/create-pull-request@v8
|
|
with:
|
|
token: ${{ secrets.UPDATE_BOT_TOKEN }}
|
|
push-to-fork: ci-forks/LocalAI
|
|
commit-message: ':arrow_up: Update ${{ matrix.repository }}'
|
|
title: 'chore: :arrow_up: Update ${{ matrix.repository }} to `${{ steps.bump.outputs.commit }}`'
|
|
branch: "update/${{ matrix.variable }}"
|
|
body: ${{ steps.bump.outputs.message }}
|
|
signoff: true
|
|
|
|
bump-vllm-wheel:
|
|
# vLLM's cu130 wheel comes from a per-tag index URL (no /latest/ alias),
|
|
# so the cublas13 requirements file pins both a URL segment and a version
|
|
# constraint. bump_deps.sh handles git-sha-in-Makefile only — this job
|
|
# rewrites both values atomically when a new vLLM stable tag ships.
|
|
if: github.repository == 'mudler/LocalAI'
|
|
runs-on: ubuntu-latest
|
|
steps:
|
|
- uses: actions/checkout@v6
|
|
- name: Bump vLLM cu130 wheel pin 🔧
|
|
id: bump
|
|
run: |
|
|
bash .github/bump_vllm_wheel.sh vllm-project/vllm backend/python/vllm/requirements-cublas13-after.txt VLLM_VERSION
|
|
{
|
|
echo 'message<<EOF'
|
|
cat "VLLM_VERSION_message.txt"
|
|
echo EOF
|
|
} >> "$GITHUB_OUTPUT"
|
|
{
|
|
echo 'commit<<EOF'
|
|
cat "VLLM_VERSION_commit.txt"
|
|
echo EOF
|
|
} >> "$GITHUB_OUTPUT"
|
|
rm -rfv VLLM_VERSION_message.txt VLLM_VERSION_commit.txt
|
|
- name: Create Pull Request
|
|
uses: peter-evans/create-pull-request@v8
|
|
with:
|
|
token: ${{ secrets.UPDATE_BOT_TOKEN }}
|
|
push-to-fork: ci-forks/LocalAI
|
|
commit-message: ':arrow_up: Update vllm-project/vllm cu130 wheel'
|
|
title: 'chore: :arrow_up: Update vllm-project/vllm cu130 wheel to `${{ steps.bump.outputs.commit }}`'
|
|
branch: "update/VLLM_VERSION"
|
|
body: ${{ steps.bump.outputs.message }}
|
|
signoff: true
|