37a90b734d
Switch PDF layout parsing to use the PP-DocLayoutV3 ONNX model, replacing the previous Docling-based approach. Update all environment variables, model fetching, and manifest handling for the new model and its artifacts. Refactor block kind taxonomy throughout the codebase, tests, and UI to align with PP-DocLayoutV3 labels, including expanded and renamed block types. Revise document settings, block filtering, and stitching logic to support the new set of block kinds. Update documentation and environment variable references to reflect the model transition. BREAKING CHANGE: PDF parsing now requires PP-DocLayoutV3 ONNX model and updated environment variables; block kind names and settings have changed throughout the system.
111 lines
5.1 KiB
Text
111 lines
5.1 KiB
Text
|
|
# Local / OpenAI TTS API Configuration (default)
|
|
# Suggest using https://github.com/remsky/Kokoro-FastAPI
|
|
#
|
|
# NOTE: On first boot, the server auto-seeds these values into a "default-openai"
|
|
# admin-managed shared provider (DB-backed, encrypted at rest). After that, the
|
|
# admin UI is authoritative and changing these env vars has no effect. You may
|
|
# remove them once the seed has run. See Settings → Admin → Shared providers.
|
|
API_BASE=http://localhost:8880/v1
|
|
API_KEY=api_key_optional
|
|
|
|
# (Optional) TTS request/cache tuning (leave unset to use defaults)
|
|
# TTS_CACHE_MAX_SIZE_BYTES=268435456 # 256MB
|
|
# TTS_CACHE_TTL_MS=1800000 # 30 minutes
|
|
# TTS_MAX_RETRIES=2
|
|
# TTS_RETRY_INITIAL_MS=250
|
|
# TTS_RETRY_MAX_MS=2000
|
|
# TTS_RETRY_BACKOFF=2
|
|
# TTS_UPSTREAM_TIMEOUT_MS=285000 # 285 seconds
|
|
|
|
# (Optional) Enable TTS character rate limiting (default is `false`)
|
|
# TTS_ENABLE_RATE_LIMIT=true
|
|
# (Optional) TTS per-user daily limits (leave unset to use defaults)
|
|
# TTS_DAILY_LIMIT_ANONYMOUS=50000
|
|
# TTS_DAILY_LIMIT_AUTHENTICATED=500000
|
|
# (Optional) TTS IP backstop daily limits (leave unset to use defaults)
|
|
# TTS_IP_DAILY_LIMIT_ANONYMOUS=100000
|
|
# TTS_IP_DAILY_LIMIT_AUTHENTICATED=1000000
|
|
|
|
# Auth configuration (recommended for contributors and public instances)
|
|
# (Optional) Auth is only enabled when AUTH_SECRET and BASE_URL are set
|
|
BASE_URL=http://localhost:3003 # Externally facing URL for this app (set to LAN IP for access from other devices on the network)
|
|
AUTH_SECRET=some_random_secret_key # Generate with `openssl rand -hex 32`
|
|
AUTH_TRUSTED_ORIGINS=http://localhost:3003,http://127.0.0.1:3003 # Additional trusted origins (BASE_URL is always trusted)
|
|
# (Optional) Allow anonymous auth sessions when auth is enabled (default: `false`)
|
|
USE_ANONYMOUS_AUTH_SESSIONS=
|
|
# (Optional) Sign in w/ GitHub Configuration
|
|
GITHUB_CLIENT_ID=
|
|
GITHUB_CLIENT_SECRET=
|
|
# (Optional) Disable Better Auth built-in rate limiting (useful for testing)
|
|
DISABLE_AUTH_RATE_LIMIT=
|
|
|
|
# (Optional) Comma-separated list of emails that are auto-promoted to admin.
|
|
# Admins see the "Admin" tab in Settings (TTS shared providers + site features).
|
|
# Demotion is automatic: removing an email here demotes the user on next login.
|
|
# Requires auth to be enabled (AUTH_SECRET + BASE_URL).
|
|
ADMIN_EMAILS=
|
|
|
|
# (Optional) Backend DB used for server-side metadata (documents/audiobooks) and, when auth is enabled, auth tables.
|
|
# Defaults to SQLite at docstore/sqlite3.db when not set.
|
|
POSTGRES_URL=
|
|
|
|
# Embedded SeaweedFS weed mini config
|
|
# (Optional) Enable embedded weed mini for local S3-compatible storage (default: `true`)
|
|
USE_EMBEDDED_WEED_MINI=
|
|
WEED_MINI_DIR=
|
|
WEED_MINI_WAIT_SEC=
|
|
|
|
# S3 storage config (use with embedded weed mini or external S3-compatible storage)
|
|
# (Optional) For embedded weed mini, set explicit keys if you want stable credentials across restarts.
|
|
S3_ACCESS_KEY_ID=
|
|
S3_SECRET_ACCESS_KEY=
|
|
S3_BUCKET=
|
|
S3_REGION=
|
|
# (Optional) If empty in embedded mode, OpenReader uses BASE_URL host (when set) or detected LAN host.
|
|
S3_ENDPOINT=
|
|
S3_FORCE_PATH_STYLE=
|
|
S3_PREFIX=
|
|
|
|
# Migrations configuration
|
|
# (Optional) Skip automatic startup migrations when set to `false` (default: `true`)
|
|
RUN_DRIZZLE_MIGRATIONS=
|
|
# (Optional) Skip automatic filesystem->S3/DB migration pass when set to `false` (default: `true`)
|
|
RUN_FS_MIGRATIONS=
|
|
|
|
# (Optional) Server library import roots (uses /docstore/library by default)
|
|
IMPORT_LIBRARY_DIR=
|
|
IMPORT_LIBRARY_DIRS=
|
|
|
|
# (Required without Docker) Path to your local whisper.cpp CLI binary for STT timestamp generation
|
|
WHISPER_CPP_BIN=/whisper.cpp/build/bin/whisper-cli
|
|
|
|
# Heavy compute backend mode for whisper alignment + PDF layout parsing.
|
|
# local = run compute in-process (default)
|
|
# none = disable both capabilities (good for preview/serverless)
|
|
# worker = reserved for future external worker mode (not implemented in v1)
|
|
OPENREADER_COMPUTE_MODE=local
|
|
# OPENREADER_COMPUTE_WORKER_URL=
|
|
# OPENREADER_COMPUTE_WORKER_TOKEN=
|
|
|
|
# Optional overrides for PDF layout model artifacts
|
|
# OPENREADER_PDF_LAYOUT_MODEL_URL=https://huggingface.co/Bei0001/PP-DocLayoutV3-ONNX/resolve/main/PP-DocLayoutV3.onnx
|
|
# OPENREADER_PDF_LAYOUT_MODEL_DATA_URL=https://huggingface.co/Bei0001/PP-DocLayoutV3-ONNX/resolve/main/PP-DocLayoutV3.onnx.data
|
|
# OPENREADER_PDF_LAYOUT_CONFIG_URL=https://huggingface.co/Bei0001/PP-DocLayoutV3-ONNX/resolve/main/config.json
|
|
# OPENREADER_PDF_LAYOUT_PREPROCESSOR_URL=https://huggingface.co/Bei0001/PP-DocLayoutV3-ONNX/resolve/main/preprocessor_config.json
|
|
|
|
# (Optional) Override ffmpeg binary path used for audiobook processing
|
|
FFMPEG_BIN=
|
|
|
|
# (Optional) Client feature flags — seeded into the admin-managed runtime
|
|
# config on first boot, then ignored. Edit values from Settings → Admin →
|
|
# Site features instead of redeploying. SSR-injected so they take effect
|
|
# without rebuilding (unlike the old NEXT_PUBLIC_* build-time pattern).
|
|
# NEXT_PUBLIC_ENABLE_DOCX_CONVERSION=true
|
|
# NEXT_PUBLIC_ENABLE_DESTRUCTIVE_DELETE_ACTIONS=true
|
|
# NEXT_PUBLIC_ENABLE_TTS_PROVIDERS_TAB=true
|
|
# NEXT_PUBLIC_ENABLE_USER_SIGNUPS=true
|
|
# NEXT_PUBLIC_RESTRICT_USER_API_KEYS=true
|
|
# NEXT_PUBLIC_DEFAULT_TTS_PROVIDER=custom-openai
|
|
# NEXT_PUBLIC_CHANGELOG_FEED_URL=https://docs.openreader.richardr.dev/changelog/manifest.json
|
|
# NEXT_PUBLIC_ENABLE_AUDIOBOOK_EXPORT=true
|