mirror of
https://github.com/mudler/LocalAI.git
synced 2026-06-02 13:22:34 -04:00
6a80e23733
Add a routing middleware stack and a cloud-proxy backend. * cloud-proxy: a Go gRPC backend that forwards OpenAI- and Anthropic-shaped chat requests to upstream providers, with an optional translate mode (OpenAI request -> Anthropic /v1/messages -> OpenAI response) and full tool-calling support. * routing: admission control, content-aware model routing (embedding cache + classifier + rerank + Arch-Router score), PII detection/redaction (regex + NER) with streaming filter and OpenAI/Anthropic adapters, and a per-user/per-key billing recorder backed by GORM or in-memory storage. * middleware: UsageMiddleware records usage via the billing recorder, plus admission, route-model, usage-stamp and trace middlewares. * observability: BackendTrace ring buffer stores full request bodies (capped), MITM proxy emits structured trace events, and router classifier decisions surface at /api/router/decide. * gallery: Arch-Router-1.5B (Q4_K_M and Q8_0). * UI: cloud-proxy model-editor fields, classifier system-prompt and score-normalization config, and a Traces page rendering request bodies. Assisted-by: claude-code:claude-opus-4-7 [Read] [Edit] [Bash] Signed-off-by: Richard Palethorpe <io@richiejp.com>
47 lines
1.2 KiB
Go
47 lines
1.2 KiB
Go
package store
|
|
|
|
// pb⇄[][]float32/[][]byte translation helpers shared by the gRPC
|
|
// client (this file's package) and the local-store gRPC server in
|
|
// backend/go/local-store. Same shape on both sides of the wire so a
|
|
// schema bug only needs fixing once.
|
|
|
|
import (
|
|
"github.com/mudler/LocalAI/pkg/grpc/proto"
|
|
)
|
|
|
|
// WrapKeys wraps each plain []float32 in a *proto.StoresKey.
|
|
func WrapKeys(in [][]float32) []*proto.StoresKey {
|
|
out := make([]*proto.StoresKey, len(in))
|
|
for i, k := range in {
|
|
out[i] = &proto.StoresKey{Floats: k}
|
|
}
|
|
return out
|
|
}
|
|
|
|
// WrapValues wraps each []byte in a *proto.StoresValue.
|
|
func WrapValues(in [][]byte) []*proto.StoresValue {
|
|
out := make([]*proto.StoresValue, len(in))
|
|
for i, v := range in {
|
|
out[i] = &proto.StoresValue{Bytes: v}
|
|
}
|
|
return out
|
|
}
|
|
|
|
// UnwrapKeys extracts the inner Floats from a slice of *proto.StoresKey.
|
|
func UnwrapKeys(in []*proto.StoresKey) [][]float32 {
|
|
out := make([][]float32, len(in))
|
|
for i, k := range in {
|
|
out[i] = k.Floats
|
|
}
|
|
return out
|
|
}
|
|
|
|
// UnwrapValues extracts the inner Bytes from a slice of *proto.StoresValue.
|
|
func UnwrapValues(in []*proto.StoresValue) [][]byte {
|
|
out := make([][]byte, len(in))
|
|
for i, v := range in {
|
|
out[i] = v.Bytes
|
|
}
|
|
return out
|
|
}
|