mirror of
https://github.com/mudler/LocalAI.git
synced 2026-06-19 06:09:07 -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>
89 lines
2.5 KiB
Go
89 lines
2.5 KiB
Go
// Package cloudproxy stitches the cloud-proxy gRPC backend to the
|
|
// HTTP edge: model rewrite and body shaping. The outbound HTTP request
|
|
// itself lives inside the cloud-proxy backend binary
|
|
// (backend/go/cloud-proxy), not here — this package is the core-side
|
|
// glue. PII redaction runs request-side (the NER middleware + MITM
|
|
// input path); response/output is forwarded unmodified.
|
|
package cloudproxy
|
|
|
|
import (
|
|
"encoding/json"
|
|
"fmt"
|
|
"io"
|
|
"net/http"
|
|
|
|
"github.com/labstack/echo/v4"
|
|
"github.com/mudler/xlog"
|
|
)
|
|
|
|
func rewriteModel(body []byte, upstreamModel string) ([]byte, error) {
|
|
if upstreamModel == "" {
|
|
return body, nil
|
|
}
|
|
var m map[string]any
|
|
if err := json.Unmarshal(body, &m); err != nil {
|
|
return nil, fmt.Errorf("cloudproxy: parse request body: %w", err)
|
|
}
|
|
m["model"] = upstreamModel
|
|
return json.Marshal(m)
|
|
}
|
|
|
|
func streaming(body []byte) bool {
|
|
var probe struct {
|
|
Stream bool `json:"stream"`
|
|
}
|
|
if err := json.Unmarshal(body, &probe); err != nil {
|
|
return false
|
|
}
|
|
return probe.Stream
|
|
}
|
|
|
|
// passthroughError emits the upstream's error response unchanged.
|
|
func passthroughError(c echo.Context, statusCode int, contentType string, body io.Reader) error {
|
|
const maxErrBody = 1 << 20
|
|
buf, _ := io.ReadAll(io.LimitReader(body, maxErrBody))
|
|
if contentType != "" {
|
|
c.Response().Header().Set("Content-Type", contentType)
|
|
}
|
|
c.Response().WriteHeader(statusCode)
|
|
_, _ = c.Response().Writer.Write(buf)
|
|
return nil
|
|
}
|
|
|
|
func forwardBuffered(c echo.Context, statusCode int, contentType string, body io.Reader) error {
|
|
if contentType != "" {
|
|
c.Response().Header().Set("Content-Type", contentType)
|
|
}
|
|
c.Response().WriteHeader(statusCode)
|
|
_, err := io.Copy(c.Response().Writer, body)
|
|
return err
|
|
}
|
|
|
|
// forwardStream relays the upstream SSE response to the client,
|
|
// flushing per read so events arrive in real time. Response/output PII
|
|
// redaction is out of scope for now, so the stream is forwarded
|
|
// unmodified.
|
|
func forwardStream(c echo.Context, body io.Reader) error {
|
|
c.Response().Header().Set("Content-Type", "text/event-stream")
|
|
c.Response().Header().Set("Cache-Control", "no-cache")
|
|
c.Response().Header().Set("Connection", "keep-alive")
|
|
c.Response().WriteHeader(http.StatusOK)
|
|
|
|
buf := make([]byte, 32*1024)
|
|
for {
|
|
n, rErr := body.Read(buf)
|
|
if n > 0 {
|
|
if _, wErr := c.Response().Writer.Write(buf[:n]); wErr != nil {
|
|
return nil
|
|
}
|
|
c.Response().Flush()
|
|
}
|
|
if rErr != nil {
|
|
if rErr != io.EOF {
|
|
xlog.Debug("cloudproxy: stream read error", "error", rErr)
|
|
}
|
|
return nil
|
|
}
|
|
}
|
|
}
|