Files
hyperguild/ingestion/cmd/server/main.go
Mathias a56a4db963
All checks were successful
CI / Lint / Test / Vet (push) Successful in 10s
CI / Mirror to GitHub (push) Successful in 3s
feat(brain_answer): Qwen3-Reranker cross-encoder filter (opt-in)
Adds an opt-in cross-encoder rerank step between BM25 retrieval and LLM
synthesis. With BRAIN_RERANKER_URL set, brain_answer retrieves BM25
top-20, scores each excerpt against the query via Qwen3-Reranker on
Ollama, drops the "no" answers, and forwards up to 5 surviving sources
to the LLM. Unset, behaviour is unchanged (BM25 top-10 → LLM).

The reranker is a *filter*, not a re-ranker: Qwen3-Reranker emits a
binary yes/no token under its native chat template, and ties within the
"yes" set are broken by BM25 rank — what got retrieved first stays
ahead.

New package ingestion/internal/reranker:
- Client with URL, Model, HTTP fields.
- New(url, model) returns nil on empty url so callers can treat
  "feature disabled" as a single nil check.
- Score(ctx, query, docs) issues one /api/generate call per doc using
  the Qwen3-Reranker yes/no chat template (verbatim, because the model
  was trained on this exact wording). Parses the first non-think token.

Wiring:
- mcp.Server gains a WithReranker fluent setter to keep NewServer
  signature stable.
- brain_answer's BM25 limit jumps to 20 only when a reranker is wired,
  to give the filter something to do.
- cmd/server/main.go reads BRAIN_RERANKER_URL (+ optional
  BRAIN_RERANKER_MODEL, default dengcao/Qwen3-Reranker-0.6B:F16).

Tests cover: nil-on-empty-url, ordered yes/no scoring, request shape
(model, prompt contents, yes/no template), ambiguous response → 0,
empty doc slice, upstream-error propagation, plus an end-to-end
brain_answer integration that proves only the relevant note reaches the
LLM when noise.md is rejected.

Closes hyperguild#7.
2026-05-18 22:55:46 +02:00

185 lines
6.0 KiB
Go

// ingestion/cmd/server/main.go
package main
import (
"context"
"fmt"
"log/slog"
"net/http"
"os"
"strconv"
"strings"
"time"
"github.com/mathiasbq/hyperguild/ingestion/internal/api"
"github.com/mathiasbq/hyperguild/ingestion/internal/auth"
"github.com/mathiasbq/hyperguild/ingestion/internal/llm"
"github.com/mathiasbq/hyperguild/ingestion/internal/mcp"
"github.com/mathiasbq/hyperguild/ingestion/internal/oauth"
"github.com/mathiasbq/hyperguild/ingestion/internal/reranker"
"github.com/mathiasbq/hyperguild/ingestion/internal/pipeline"
"github.com/mathiasbq/hyperguild/ingestion/internal/watcher"
)
func envOr(key, fallback string) string {
if v := os.Getenv(key); v != "" {
return v
}
return fallback
}
func envInt(key string, fallback int) int {
if v := os.Getenv(key); v != "" {
if n, err := strconv.Atoi(v); err == nil {
return n
}
}
return fallback
}
func main() {
logger := slog.New(slog.NewJSONHandler(os.Stdout, nil))
brainDir := envOr("INGEST_BRAIN_DIR", "../brain")
port := envOr("INGEST_PORT", "3300")
llmURL := envOr("INGEST_LLM_URL", "http://iguana:4000/v1")
llmKey := os.Getenv("INGEST_LLM_KEY")
llmModel := envOr("INGEST_LLM_MODEL", "koala/qwen35-9b-fast")
llmTimeoutMins := envInt("INGEST_LLM_TIMEOUT", 15)
chunkSize := envInt("INGEST_CHUNK_SIZE", 6000)
watchInterval := envInt("INGEST_WATCH_INTERVAL", 30)
llmClient := llm.New(llmURL, llmKey, llmModel, time.Duration(llmTimeoutMins)*time.Minute)
pipelineCfg := pipeline.Config{
Complete: llmClient.Complete,
ChunkSize: chunkSize,
}
h := api.NewHandler(brainDir, logger, pipelineCfg)
var answerComplete pipeline.CompleteFunc
if primaryURL := os.Getenv("BRAIN_LLM_PRIMARY_URL"); primaryURL != "" {
primaryModel := envOr("BRAIN_LLM_PRIMARY_MODEL", "gemma4:31b")
primaryKey := os.Getenv("BERGET_API_KEY")
timeoutMS := envInt("BRAIN_LLM_TIMEOUT_MS", 10000)
timeout := time.Duration(timeoutMS) * time.Millisecond
primary := llm.New(primaryURL, primaryKey, primaryModel, timeout)
router := &llm.Router{Primary: primary}
if fallbackURL := os.Getenv("BRAIN_LLM_FALLBACK_URL"); fallbackURL != "" {
fallbackModel := envOr("BRAIN_LLM_FALLBACK_MODEL", "gemma4:31b")
router.Fallback = llm.New(fallbackURL, "", fallbackModel, timeout)
}
answerComplete = router.Complete
logger.Info("brain answer LLM configured", "primary", primaryURL, "model", primaryModel)
}
mcpSrv := mcp.NewServer(brainDir, &pipelineCfg, llmClient.Complete, answerComplete)
if rerankURL := os.Getenv("BRAIN_RERANKER_URL"); rerankURL != "" {
rerankModel := envOr("BRAIN_RERANKER_MODEL", "dengcao/Qwen3-Reranker-0.6B:F16")
mcpSrv = mcpSrv.WithReranker(reranker.New(rerankURL, rerankModel))
logger.Info("brain reranker configured", "url", rerankURL, "model", rerankModel)
}
mcpToken := os.Getenv("BRAIN_MCP_TOKEN")
if mcpToken == "" {
logger.Error("BRAIN_MCP_TOKEN not set")
os.Exit(1)
}
ctx := context.Background()
if watchInterval > 0 {
watcher.Start(ctx, watcher.Config{
BrainDir: brainDir,
Interval: time.Duration(watchInterval) * time.Second,
Pipeline: pipelineCfg,
})
}
mux := http.NewServeMux()
mux.HandleFunc("POST /query", h.Query)
mux.HandleFunc("POST /write", h.Write)
mux.HandleFunc("POST /index", h.Index)
mux.HandleFunc("POST /ingest", h.Ingest)
mux.HandleFunc("POST /ingest-path", h.IngestPath)
mux.HandleFunc("POST /ingest-raw", h.IngestRaw)
mux.HandleFunc("POST /backfill-refs", h.BackfillRefs)
mux.HandleFunc("GET /pass-rate", h.PassRate)
var jwtValidator *auth.Validator
if dexURL := os.Getenv("DEX_ISSUER_URL"); dexURL != "" {
audience := os.Getenv("MCP_AUDIENCE")
v, err := auth.NewValidator(dexURL, audience)
if err != nil {
logger.Error("build jwt validator", "err", err)
os.Exit(1)
}
jwtValidator = v
logger.Info("jwt auth enabled", "issuer", dexURL)
}
// Resource-metadata URL is only emitted on 401 when Dex OAuth is
// configured. Static-Bearer-only deployments leave this empty so
// clients never see an OAuth challenge.
var resourceMetadataURL string
if dexURL := os.Getenv("DEX_ISSUER_URL"); dexURL != "" {
resourceURL := os.Getenv("MCP_RESOURCE_URL")
mux.HandleFunc("GET /.well-known/oauth-protected-resource",
auth.ProtectedResourceHandler(resourceURL, dexURL))
if resourceURL != "" {
resourceMetadataURL = strings.TrimRight(resourceURL, "/") + "/.well-known/oauth-protected-resource"
}
}
mux.Handle("/mcp", mcp.BearerAuth(mcpToken, jwtValidator, resourceMetadataURL, mcpSrv))
// Opt-in OAuth 2.0 client_credentials flow for claude.ai's custom-MCP
// integration UI, which has no static-Bearer field. Setting both
// OAUTH_CLIENT_ID and OAUTH_CLIENT_SECRET enables the token exchange;
// setting only one is misconfiguration → fail fast.
oauthID := os.Getenv("OAUTH_CLIENT_ID")
oauthSecret := os.Getenv("OAUTH_CLIENT_SECRET")
switch {
case oauthID != "" && oauthSecret != "":
issuer := os.Getenv("MCP_RESOURCE_URL")
if issuer == "" {
logger.Error("OAUTH_CLIENT_ID/SECRET set but MCP_RESOURCE_URL is empty; cannot derive issuer")
os.Exit(1)
}
mux.HandleFunc("GET /.well-known/oauth-authorization-server",
oauth.MetadataHandler(issuer))
mux.HandleFunc("POST /oauth/token", oauth.TokenHandler(oauth.TokenConfig{
ClientID: oauthID,
ClientSecret: oauthSecret,
AccessToken: mcpToken,
}))
logger.Info("oauth client_credentials enabled", "issuer", strings.TrimRight(issuer, "/"))
case oauthID == "" && oauthSecret == "":
// disabled — that's fine
default:
logger.Error("OAUTH_CLIENT_ID and OAUTH_CLIENT_SECRET must be set together")
os.Exit(1)
}
addr := ":" + port
watchIntervalLog := "disabled"
if watchInterval > 0 {
watchIntervalLog = fmt.Sprintf("%ds", watchInterval)
}
logger.Info("ingestion server starting",
"addr", addr,
"brain_dir", brainDir,
"llm_url", llmURL,
"llm_model", llmModel,
"chunk_size", chunkSize,
"watch_interval", watchIntervalLog,
"mcp_enabled", true,
)
if err := http.ListenAndServe(addr, mux); err != nil {
logger.Error("server stopped", "err", err)
os.Exit(1)
}
}