Files
hyperguild/ingestion/cmd/server/main.go
Mathias Bergqvist 189ff89c34
All checks were successful
CI / Lint / Test / Vet (push) Successful in 11s
CI / Mirror to GitHub (push) Successful in 3s
feat(brain): add brain_answer and brain_classify MCP tools
Adds two new LLM-backed MCP tools to the ingestion service:

- brain_answer(query): BM25 retrieval + LLM synthesis → answer + sources
- brain_classify(text): classifies doc into type/title/tags via LLM

Adds llm.Router for primary→fallback routing (berget.ai → iguana).
Wired via BRAIN_LLM_PRIMARY_URL/BRAIN_LLM_FALLBACK_URL env vars;
no-op when unset so existing deployments are unaffected.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-12 11:06:17 +02:00

141 lines
4.1 KiB
Go

// ingestion/cmd/server/main.go
package main
import (
"context"
"fmt"
"log/slog"
"net/http"
"os"
"strconv"
"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/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)
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 /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)
}
mux.Handle("/mcp", mcp.BearerAuth(mcpToken, jwtValidator, mcpSrv))
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, os.Getenv("DEX_ISSUER_URL")))
}
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)
}
}