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>
62 lines
2.1 KiB
Go
62 lines
2.1 KiB
Go
package backend
|
|
|
|
import (
|
|
"errors"
|
|
"time"
|
|
|
|
"github.com/mudler/LocalAI/core/config"
|
|
"github.com/mudler/LocalAI/core/trace"
|
|
pb "github.com/mudler/LocalAI/pkg/grpc/proto"
|
|
|
|
. "github.com/onsi/ginkgo/v2"
|
|
. "github.com/onsi/gomega"
|
|
)
|
|
|
|
var _ = Describe("tokenClassifyResponseToEntities", func() {
|
|
It("returns nil for a nil response", func() {
|
|
Expect(tokenClassifyResponseToEntities(nil)).To(BeNil())
|
|
})
|
|
|
|
It("maps proto entities to TokenEntity, skipping nil rows", func() {
|
|
resp := &pb.TokenClassifyResponse{
|
|
Entities: []*pb.TokenClassifyEntity{
|
|
{EntityGroup: "private_person", Start: 3, End: 8, Score: 0.97, Text: "Alice"},
|
|
nil,
|
|
{EntityGroup: "EMAIL", Start: 20, End: 40, Score: 0.5, Text: "a@b.com"},
|
|
},
|
|
}
|
|
Expect(tokenClassifyResponseToEntities(resp)).To(Equal([]TokenEntity{
|
|
{Group: "private_person", Start: 3, End: 8, Score: 0.97, Text: "Alice"},
|
|
{Group: "EMAIL", Start: 20, End: 40, Score: 0.5, Text: "a@b.com"},
|
|
}))
|
|
})
|
|
|
|
It("returns an empty (non-nil) slice for a response with no entities", func() {
|
|
out := tokenClassifyResponseToEntities(&pb.TokenClassifyResponse{})
|
|
Expect(out).NotTo(BeNil())
|
|
Expect(out).To(BeEmpty())
|
|
})
|
|
})
|
|
|
|
var _ = Describe("tokenClassifyTrace", func() {
|
|
cfg := config.ModelConfig{Name: "privacy-filter", Backend: "privacy-filter"}
|
|
ents := []TokenEntity{{Group: "SSN", Start: 5, End: 16, Score: 0.62, Text: "123-45-6789"}}
|
|
|
|
It("captures model, input preview, threshold and per-entity detail", func() {
|
|
tr := tokenClassifyTrace(cfg, "ssn is 123-45-6789", 0.5, ents, time.Now(), nil)
|
|
Expect(tr.Type).To(Equal(trace.BackendTraceTokenClassify))
|
|
Expect(tr.ModelName).To(Equal("privacy-filter"))
|
|
Expect(tr.Backend).To(Equal("privacy-filter"))
|
|
Expect(tr.Summary).To(ContainSubstring("ssn is"))
|
|
Expect(tr.Error).To(BeEmpty())
|
|
Expect(tr.Data["input_chars"]).To(Equal(len("ssn is 123-45-6789")))
|
|
Expect(tr.Data["threshold"]).To(BeEquivalentTo(float32(0.5)))
|
|
Expect(tr.Data["entities"]).To(Equal(ents))
|
|
})
|
|
|
|
It("records the backend error string when the call failed", func() {
|
|
tr := tokenClassifyTrace(cfg, "x", 0, nil, time.Now(), errors.New("boom"))
|
|
Expect(tr.Error).To(Equal("boom"))
|
|
})
|
|
})
|