feat: Add .env.example configuration file and integrate Redis service into Docker Compose for improved task management. Update desktop application to support document indexing and extraction workflows, enhancing user experience with a new extraction wizard and stepper components. Revise README and documentation for clarity on setup and usage.

2026-07-05 22:39:07 -05:00
parent 9aca926988
commit d95f8f6ad8
70 changed files with 9807 additions and 499 deletions
@@ -0,0 +1,105 @@
+package config
+
+import (
+	"os"
+	"strconv"
+	"time"
+)
+
+type Config struct {
+	Port              string
+	RedisURL          string
+	NATSURL           string
+	MinIOEndpoint     string
+	MinIOAccessKey    string
+	MinIOSecretKey    string
+	MinIOBucket       string
+	MinIOUseSSL       bool
+	ModelPath         string
+	InferencePath     string
+	OCRDPI            int
+	OCRLang           string
+	DBSCANEps         float64
+	DBSCANMinSamples  int
+	SyncMaxFiles      int
+	JobMaxFiles       int
+	QueueMaxPending   int
+	WorkerConcurrency int
+	MaxPDFSizeMB      int
+	PDFProcessTimeout time.Duration
+	JobResultTTL      time.Duration
+	StreamName        string
+	SubjectPrefix     string
+	OCRPoolSize            int
+	LogPipelineTiming      bool
+	NATSFetchMaxWait       time.Duration
+	JobInlineProcessing    bool
+	SyncProcessConcurrency int
+}
+
+func Load() Config {
+	return Config{
+		Port:              getenv("PORT", "8080"),
+		RedisURL:          getenv("REDIS_URL", "redis://redis:6379/0"),
+		NATSURL:           getenv("NATS_URL", "nats://nats:4222"),
+		MinIOEndpoint:     getenv("MINIO_ENDPOINT", "minio:9000"),
+		MinIOAccessKey:    getenv("MINIO_ACCESS_KEY", "minioadmin"),
+		MinIOSecretKey:    getenv("MINIO_SECRET_KEY", "minioadmin"),
+		MinIOBucket:       getenv("MINIO_BUCKET", "pdf-count"),
+		MinIOUseSSL:       getenvBool("MINIO_USE_SSL", false),
+		ModelPath:         getenv("MODEL_PATH", "/app/models/model.onnx"),
+		InferencePath:     getenv("INFERENCE_CONFIG", "/app/models/inference.json"),
+		OCRDPI:            getenvInt("OCR_DPI", 300),
+		OCRLang:           getenv("OCR_LANG", "spa"),
+		DBSCANEps:         getenvFloat("DBSCAN_EPS", 10),
+		DBSCANMinSamples:  getenvInt("DBSCAN_MIN_SAMPLES", 1),
+		SyncMaxFiles:      getenvInt("SYNC_MAX_FILES", 50),
+		JobMaxFiles:       getenvInt("JOB_MAX_FILES", 50000),
+		QueueMaxPending:   getenvInt("QUEUE_MAX_PENDING", 100000),
+		WorkerConcurrency: getenvInt("WORKER_CONCURRENCY", 4),
+		MaxPDFSizeMB:      getenvInt("MAX_PDF_SIZE_MB", 20),
+		PDFProcessTimeout: time.Duration(getenvInt("PDF_PROCESS_TIMEOUT_SEC", 120)) * time.Second,
+		JobResultTTL:      time.Duration(getenvInt("JOB_RESULT_TTL_HOURS", 72)) * time.Hour,
+		StreamName:        getenv("NATS_STREAM", "PDF_JOBS"),
+		SubjectPrefix:     getenv("NATS_SUBJECT_PREFIX", "pdf.process"),
+		OCRPoolSize:            getenvInt("OCR_POOL_SIZE", 0),
+		LogPipelineTiming:      getenvBool("LOG_PIPELINE_TIMING", false),
+		NATSFetchMaxWait:       time.Duration(getenvInt("NATS_FETCH_MAX_WAIT_MS", 300)) * time.Millisecond,
+		JobInlineProcessing:    getenvBool("JOB_INLINE_PROCESSING", false),
+		SyncProcessConcurrency: getenvInt("SYNC_PROCESS_CONCURRENCY", 0),
+	}
+}
+
+func getenv(key, fallback string) string {
+	if v := os.Getenv(key); v != "" {
+		return v
+	}
+	return fallback
+}
+
+func getenvInt(key string, fallback int) int {
+	if v := os.Getenv(key); v != "" {
+		if n, err := strconv.Atoi(v); err == nil {
+			return n
+		}
+	}
+	return fallback
+}
+
+func getenvFloat(key string, fallback float64) float64 {
+	if v := os.Getenv(key); v != "" {
+		if n, err := strconv.ParseFloat(v, 64); err == nil {
+			return n
+		}
+	}
+	return fallback
+}
+
+func getenvBool(key string, fallback bool) bool {
+	if v := os.Getenv(key); v != "" {
+		if b, err := strconv.ParseBool(v); err == nil {
+			return b
+		}
+	}
+	return fallback
+}