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>
97 lines
4.5 KiB
Go
97 lines
4.5 KiB
Go
package localaitools
|
|
|
|
import (
|
|
"context"
|
|
|
|
"github.com/mudler/LocalAI/core/config"
|
|
"github.com/mudler/LocalAI/core/gallery"
|
|
"github.com/mudler/LocalAI/core/schema"
|
|
"github.com/mudler/LocalAI/core/services/modeladmin"
|
|
"github.com/mudler/LocalAI/pkg/vram"
|
|
)
|
|
|
|
// LocalAIClient is the surface tools depend on. It has two implementations:
|
|
//
|
|
// - inproc.Client (in-process; calls LocalAI services directly)
|
|
// - httpapi.Client (out-of-process; calls the LocalAI REST API)
|
|
//
|
|
// Tool handlers and the embedded skill prompts are agnostic to which
|
|
// implementation backs the client.
|
|
//
|
|
// Where the same shape already exists elsewhere in the codebase
|
|
// (config.Gallery, gallery.Metadata, schema.KnownBackend, vram.EstimateResult,
|
|
// modeladmin.Action/Capability) we surface it directly rather than maintain
|
|
// a parallel DTO — keeping the LLM-visible wire format aligned with the
|
|
// rest of LocalAI by construction.
|
|
type LocalAIClient interface {
|
|
// ---- Models / gallery (read) ----
|
|
GallerySearch(ctx context.Context, q GallerySearchQuery) ([]gallery.Metadata, error)
|
|
ListInstalledModels(ctx context.Context, capability Capability) ([]InstalledModel, error)
|
|
ListGalleries(ctx context.Context) ([]config.Gallery, error)
|
|
GetJobStatus(ctx context.Context, jobID string) (*JobStatus, error)
|
|
GetModelConfig(ctx context.Context, name string) (*ModelConfigView, error)
|
|
|
|
// ---- Models / gallery (write) ----
|
|
InstallModel(ctx context.Context, req InstallModelRequest) (jobID string, err error)
|
|
DeleteModel(ctx context.Context, name string) error
|
|
EditModelConfig(ctx context.Context, name string, patch map[string]any) error
|
|
ReloadModels(ctx context.Context) error
|
|
ImportModelURI(ctx context.Context, req ImportModelURIRequest) (*ImportModelURIResponse, error)
|
|
|
|
// ---- Backends ----
|
|
// ListBackends returns installed backends. The shape stays a thin
|
|
// localaitools.Backend rather than gallery.SystemBackend because the
|
|
// latter carries filesystem paths (RunFile, Metadata) the LLM
|
|
// shouldn't see.
|
|
ListBackends(ctx context.Context) ([]Backend, error)
|
|
// ListKnownBackends returns the same shape as REST /backends/known.
|
|
ListKnownBackends(ctx context.Context) ([]schema.KnownBackend, error)
|
|
InstallBackend(ctx context.Context, req InstallBackendRequest) (jobID string, err error)
|
|
UpgradeBackend(ctx context.Context, name string) (jobID string, err error)
|
|
|
|
// ---- System ----
|
|
SystemInfo(ctx context.Context) (*SystemInfo, error)
|
|
ListNodes(ctx context.Context) ([]Node, error)
|
|
VRAMEstimate(ctx context.Context, req VRAMEstimateRequest) (*vram.EstimateResult, error)
|
|
|
|
// ---- State ----
|
|
// ToggleModelState accepts modeladmin.ActionEnable / ActionDisable.
|
|
ToggleModelState(ctx context.Context, name string, action modeladmin.Action) error
|
|
// ToggleModelPinned accepts modeladmin.ActionPin / ActionUnpin.
|
|
ToggleModelPinned(ctx context.Context, name string, action modeladmin.Action) error
|
|
|
|
// ---- Branding / whitelabeling ----
|
|
// GetBranding returns the configured instance branding (name, tagline,
|
|
// asset URLs).
|
|
GetBranding(ctx context.Context) (*Branding, error)
|
|
// SetBranding updates the text branding fields. Asset uploads are not
|
|
// exposed over MCP — admins use the Settings UI for binary files.
|
|
SetBranding(ctx context.Context, req SetBrandingRequest) (*Branding, error)
|
|
|
|
// ---- Usage / billing ----
|
|
|
|
// GetUsageStats returns aggregated token usage. In single-user
|
|
// no-auth mode this reports the synthetic local user's usage. The
|
|
// implementation enforces "admin required to query other users".
|
|
GetUsageStats(ctx context.Context, q UsageStatsQuery) (*UsageStats, error)
|
|
|
|
// ---- PII filter ----
|
|
// GetPIIEvents returns recent redaction events. Implementation
|
|
// enforces "admin required" when auth is on. The regex pattern tools
|
|
// were removed — detection policy lives on each detector model's
|
|
// pii_detection block, managed via the model-config tools.
|
|
GetPIIEvents(ctx context.Context, q PIIEventsQuery) ([]PIIEvent, error)
|
|
|
|
// ---- Middleware admin ----
|
|
// GetMiddlewareStatus returns the aggregated state surfaced on the
|
|
// /app/middleware page: active PII patterns, per-model resolved
|
|
// enabled state, recent event count, router placeholder.
|
|
GetMiddlewareStatus(ctx context.Context) (*MiddlewareStatus, error)
|
|
|
|
// ---- Router (intelligent routing) ----
|
|
// GetRouterDecisions returns recent routing decisions for the
|
|
// /app/middleware Routing tab and for agent-driven introspection.
|
|
// Admin-required when auth is on.
|
|
GetRouterDecisions(ctx context.Context, q RouterDecisionsQuery) ([]RouterDecision, error)
|
|
}
|