mirror of
https://github.com/mudler/LocalAI.git
synced 2026-06-18 21:58:58 -04:00
3fa7b2955c
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>
45 lines
1.9 KiB
Go
45 lines
1.9 KiB
Go
package localaitools
|
|
|
|
// Tool names exposed by the LocalAI Assistant MCP server. Use these
|
|
// constants — never bare strings — when registering tools, asserting the
|
|
// catalog in tests, or referencing tool names from other packages. The
|
|
// embedded skill prompts under prompts/ keep the bare strings because
|
|
// go:embed-ed markdown can't reference Go constants; TestPromptsContain
|
|
// SafetyAnchors guards that those strings stay aligned.
|
|
const (
|
|
// Read-only tools.
|
|
ToolGallerySearch = "gallery_search"
|
|
ToolListInstalledModels = "list_installed_models"
|
|
ToolListGalleries = "list_galleries"
|
|
ToolGetJobStatus = "get_job_status"
|
|
ToolGetModelConfig = "get_model_config"
|
|
ToolListBackends = "list_backends"
|
|
ToolListKnownBackends = "list_known_backends"
|
|
ToolSystemInfo = "system_info"
|
|
ToolListNodes = "list_nodes"
|
|
ToolVRAMEstimate = "vram_estimate"
|
|
ToolGetBranding = "get_branding"
|
|
ToolGetUsageStats = "get_usage_stats"
|
|
ToolGetPIIEvents = "get_pii_events"
|
|
ToolGetMiddlewareStatus = "get_middleware_status"
|
|
ToolGetRouterDecisions = "get_router_decisions"
|
|
|
|
// Mutating tools — guarded by Options.DisableMutating and the
|
|
// LLM-side safety prompt (see prompts/10_safety.md).
|
|
ToolInstallModel = "install_model"
|
|
ToolImportModelURI = "import_model_uri"
|
|
ToolDeleteModel = "delete_model"
|
|
ToolEditModelConfig = "edit_model_config"
|
|
ToolReloadModels = "reload_models"
|
|
ToolInstallBackend = "install_backend"
|
|
ToolUpgradeBackend = "upgrade_backend"
|
|
ToolToggleModelState = "toggle_model_state"
|
|
ToolToggleModelPinned = "toggle_model_pinned"
|
|
ToolSetBranding = "set_branding"
|
|
)
|
|
|
|
// DefaultServerName is the MCP Implementation.Name surfaced when
|
|
// Options.ServerName is empty. Use the constant when you want a stable
|
|
// reference across packages (e.g. test fixtures, CLI defaults).
|
|
const DefaultServerName = "localai-admin"
|