mirror of
https://github.com/mudler/LocalAI.git
synced 2026-07-08 07:18:31 -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>
143 lines
5.2 KiB
Go
143 lines
5.2 KiB
Go
package routes
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"net/http"
|
|
|
|
"github.com/google/uuid"
|
|
"github.com/labstack/echo/v4"
|
|
"github.com/mudler/LocalAI/core/application"
|
|
"github.com/mudler/LocalAI/core/config"
|
|
"github.com/mudler/LocalAI/core/http/endpoints/anthropic"
|
|
mcpTools "github.com/mudler/LocalAI/core/http/endpoints/mcp"
|
|
"github.com/mudler/LocalAI/core/http/middleware"
|
|
"github.com/mudler/LocalAI/core/schema"
|
|
"github.com/mudler/LocalAI/core/services/routing/pii"
|
|
"github.com/mudler/LocalAI/core/services/routing/piiadapter"
|
|
"github.com/mudler/LocalAI/core/services/routing/router"
|
|
"github.com/mudler/LocalAI/pkg/distributedhdr"
|
|
"github.com/mudler/xlog"
|
|
)
|
|
|
|
func RegisterAnthropicRoutes(app *echo.Echo,
|
|
re *middleware.RequestExtractor,
|
|
application *application.Application,
|
|
) {
|
|
// Anthropic Messages API endpoint
|
|
var natsClient mcpTools.MCPNATSClient
|
|
if d := application.Distributed(); d != nil {
|
|
natsClient = d.Nats
|
|
}
|
|
|
|
messagesHandler := anthropic.MessagesEndpoint(
|
|
application.ModelConfigLoader(),
|
|
application.ModelLoader(),
|
|
application.TemplatesEvaluator(),
|
|
application.ApplicationConfig(),
|
|
natsClient,
|
|
)
|
|
|
|
messagesMiddleware := []echo.MiddlewareFunc{
|
|
middleware.ExposeNodeHeader(application.ApplicationConfig()),
|
|
middleware.UsageMiddleware(application.StatsRecorder(), application.FallbackUser()),
|
|
middleware.TraceMiddleware(application),
|
|
re.BuildFilteredFirstAvailableDefaultModel(config.BuildUsecaseFilterFn(config.FLAG_CHAT)),
|
|
re.SetModelAndConfig(func() schema.LocalAIRequest { return new(schema.AnthropicRequest) }),
|
|
setAnthropicRequestContext(application.ApplicationConfig()),
|
|
// RouteModel runs after the request is parsed but before the
|
|
// PII filter — see the OpenAI route for why this order matters
|
|
// (per-model PII configs apply to the routed target).
|
|
middleware.RouteModel(
|
|
application.ModelConfigLoader(),
|
|
application.ApplicationConfig(),
|
|
application.RouterDecisions(),
|
|
application.FallbackUser(),
|
|
middleware.AnthropicProbe,
|
|
router.SourceAnthropic,
|
|
middleware.ClassifierDeps{
|
|
Scorer: application.Scorer,
|
|
TokenCounter: application.TokenCounter,
|
|
Embedder: application.Embedder,
|
|
VectorStore: application.VectorStore,
|
|
Reranker: application.Reranker,
|
|
ModelLookup: application.ModelConfigLookup(),
|
|
Registry: application.RouterClassifierRegistry(),
|
|
Evaluator: application.TemplatesEvaluator(),
|
|
},
|
|
),
|
|
middleware.AdmissionControl(application.AdmissionLimiter(), application.PIIEvents()),
|
|
pii.RequestMiddleware(application.PIIRedactor(), application.PIIEvents(), piiadapter.Anthropic(), application.FallbackUser(), pii.WithNERResolver(application.PIINERResolver()), pii.WithPolicyResolver(application.PIIPolicyResolver())),
|
|
}
|
|
|
|
// Main Anthropic endpoint
|
|
app.POST("/v1/messages", messagesHandler, messagesMiddleware...)
|
|
|
|
// Also support without version prefix for compatibility
|
|
app.POST("/messages", messagesHandler, messagesMiddleware...)
|
|
}
|
|
|
|
// setAnthropicRequestContext sets up the context and cancel function for Anthropic requests
|
|
func setAnthropicRequestContext(appConfig *config.ApplicationConfig) echo.MiddlewareFunc {
|
|
return func(next echo.HandlerFunc) echo.HandlerFunc {
|
|
return func(c echo.Context) error {
|
|
input, ok := c.Get(middleware.CONTEXT_LOCALS_KEY_LOCALAI_REQUEST).(*schema.AnthropicRequest)
|
|
if !ok || input.Model == "" {
|
|
return echo.NewHTTPError(http.StatusBadRequest, "model is required")
|
|
}
|
|
|
|
cfg, ok := c.Get(middleware.CONTEXT_LOCALS_KEY_MODEL_CONFIG).(*config.ModelConfig)
|
|
if !ok || cfg == nil {
|
|
return echo.NewHTTPError(http.StatusBadRequest, "model configuration not found")
|
|
}
|
|
|
|
// Extract or generate the correlation ID
|
|
// Anthropic uses x-request-id header
|
|
correlationID := c.Request().Header.Get("x-request-id")
|
|
if correlationID == "" {
|
|
correlationID = uuid.New().String()
|
|
}
|
|
c.Response().Header().Set("x-request-id", correlationID)
|
|
|
|
// Set up context with cancellation
|
|
reqCtx := c.Request().Context()
|
|
c1, cancel := context.WithCancel(appConfig.Context)
|
|
|
|
// Bridge request cancellation to c1 without spawning a goroutine.
|
|
stop := context.AfterFunc(reqCtx, cancel)
|
|
defer func() {
|
|
stop() // deregister callback if it hasn't fired
|
|
cancel() // release c1 resources (idempotent)
|
|
}()
|
|
|
|
// Add the correlation ID to the new context
|
|
ctxWithCorrelationID := context.WithValue(c1, middleware.CorrelationIDKey, correlationID)
|
|
ctxWithCorrelationID = distributedhdr.Inherit(ctxWithCorrelationID, reqCtx)
|
|
|
|
input.Context = ctxWithCorrelationID
|
|
input.Cancel = cancel
|
|
|
|
if cfg.Model == "" {
|
|
xlog.Debug("replacing empty cfg.Model with input value", "input.Model", input.Model)
|
|
cfg.Model = input.Model
|
|
}
|
|
|
|
c.Set(middleware.CONTEXT_LOCALS_KEY_LOCALAI_REQUEST, input)
|
|
c.Set(middleware.CONTEXT_LOCALS_KEY_MODEL_CONFIG, cfg)
|
|
|
|
// Log the Anthropic API version if provided
|
|
anthropicVersion := c.Request().Header.Get("anthropic-version")
|
|
if anthropicVersion != "" {
|
|
xlog.Debug("Anthropic API version", "version", anthropicVersion)
|
|
}
|
|
|
|
// Validate max_tokens is provided
|
|
if input.MaxTokens <= 0 {
|
|
return echo.NewHTTPError(http.StatusBadRequest, fmt.Sprintf("max_tokens is required and must be greater than 0"))
|
|
}
|
|
|
|
return next(c)
|
|
}
|
|
}
|
|
}
|