zzos/OpenViking
1
0
Fork 0
mirror of https://github.com/volcengine/OpenViking.git synced 2026-10-01 17:57:49 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
python-sdk@0.1.5
OpenViking/examples/ov.conf.example
T
MaojiaShengandqin-ctx 3c70f8d370 feat(parse): add large image processing for image parser (#3265) 
* feat(parse): add large image processing for image parser

- Add large_image_processor.py: detect large images (>10MB or >4096px),
  create low-res previews, split into grid tiles, and generate grid
  overlay images with tile labels
- Refactor ImageParser.parse() to integrate large image processing pipeline
- Enable SVG-to-PNG conversion in utils.py (cairosvg/wand)
- Rename ImageConfig.max_dimension to preview_max_dimension and add new
  config fields: max_file_size_mb, max_tile_size_mb, max_tile_dimension_px,
  tile_overlap_px, large_image_threshold_dimension
- Update ov.conf.example with new image config options

* fix(parse): correct tile dimension comment from 1024px to 2048px

* fix(parse): fix tile label path in grid overlay to include tiles/ directory

* fix(parse): register missing image extensions for ImageParser

TIFF, ICO, DIB, ICNS, SGI, JP2 were not in IMAGE_EXTENSIONS, causing
them to fallback to TextParser. All are supported by PIL.

* fix(parse): preserve PNG format for tiles instead of always converting to JPEG

* fix(parse): address review feedback for large image processing

- Wire config.image to ImageParser in ParserRegistry (was missing)
- Remove unnecessary preview creation for small images (broke LA mode PNG)
- Enforce max_tile_size_mb on tiles with quality reduction and resize fallback
- Remove 64-tile hard cap that conflicted with max_tile_dimension_px
- Add comment explaining why original file is not saved for large images

* refactor(parse): remove max_tile_size_mb as it is a soft suggestion

max_tile_size_mb was a soft constraint that was not enforced
consistently. Remove it from config, constants, and all enforcement
logic. Tile dimension (max_tile_dimension_px) remains the sole constraint.

* fix(parse): use CJK-capable font for grid overlay labels

The old font loading only tried macOS-specific paths and fell back to
PIL's default bitmap font, which cannot render CJK characters in
filenames. Add a cross-platform CJK font lookup that covers Linux
(Noto/Droid/WQY/DejaVu), macOS (PingFang), and Windows (MSYH/SimSun).

* fix(parse): convert non-VLM-supported image formats to PNG on save

Image formats like TIFF, ICO, DIB, ICNS, SGI, JP2 are not recognized
by VLM backends (OpenAI/LiteLLM/VolcEngine only support PNG/JPEG/GIF/
WebP/BMP) or by embedding_utils for image vectorization. When a file
with one of these extensions is parsed, convert it to PNG and use a
.png extension so that downstream pipelines see consistent data.

SVG files (already PNG-converted via cairosvg) also get the .png
extension for the same reason.

* fix(parse): import io for SVG conversion

---------

Co-authored-by: qin-ctx <qinhaojie.exe@bytedance.com>
2026-07-16 17:37:05 +08:00

312 lines
11 KiB
Plaintext
Raw Permalink Blame History

{
"server": {
"host": "0.0.0.0",
"port": 1933,
"root_api_key": null,
"cors_origins": ["*"],
"observability": {
"metrics": {
"enabled": true,
"account_dimension": {
"enabled": true,
"max_active_accounts": 100,
"metric_allowlist": ["openviking_*"],
},
"exporters": {
"prometheus": {"enabled": true},
"otel": {
"enabled": false,
"protocol": "grpc",
"tls": {"insecure": false},
"endpoint": "localhost:4317",
"service_name": "openviking-server",
"export_interval_ms": 10000,
"headers": {},
},
},
},
"traces": {
"enabled": false,
"protocol": "grpc",
"tls": {"insecure": false},
"endpoint": "localhost:4317",
"service_name": "openviking-server",
"headers": {},
},
"logs": {
"enabled": false,
"protocol": "grpc",
"tls": {"insecure": false},
"endpoint": "localhost:4317",
"service_name": "openviking-server",
"headers": {},
},
},
},
"storage": {
"workspace": "./data",
"vectordb": {
"name": "context",
"backend": "local",
"project": "default",
"volcengine": {
"region": "cn-beijing",
"ak": null,
"sk": null,
"api_key": null,
"host": "api-vikingdb.vikingdb.cn-beijing.volces.com",
"session_token": null,
},
},
"agfs": {
"backend": "local",
"timeout": 10,
"s3": {
"bucket": null,
"region": null,
"access_key": null,
"secret_key": null,
"endpoint": null,
"prefix": "",
"use_ssl": true,
"auto_detect_content_type": false,
"disable_batch_delete": false,
},
},
},
"embedding": {
"dense": {
"model": "doubao-embedding-vision-251215",
"api_key": "{your-api-key}",
"api_base": "https://ark.cn-beijing.volces.com/api/v3",
"dimension": 1024,
"provider": "volcengine",
"input": "multimodal",
},
"text_source": "content_only",
"max_input_tokens": 4096,
"circuit_breaker": {"failure_threshold": 5, "reset_timeout": 60, "max_reset_timeout": 600},
},
"embedding_ollama_example": {
"_comment": "For local deployment with Ollama (no API key required):",
"dense": {
"provider": "ollama",
"model": "nomic-embed-text",
"api_base": "http://localhost:11434/v1",
"dimension": 768,
"input": "text",
},
},
"vlm": {
"model": "doubao-seed-2-0-lite-260428",
"api_key": "{your-api-key}",
"api_base": "https://ark.cn-beijing.volces.com/api/v3",
"temperature": 0.0,
"max_retries": 2,
"provider": "volcengine",
"thinking": false,
},
"vlm_codex_example": {
"_comment": "For Codex OAuth via subscription. Complete sign-in from `openviking-server init`. OV stores tokens in ~/.openviking/codex_auth.json and can bootstrap from an existing Codex CLI auth file if needed.",
"provider": "openai-codex",
"model": "gpt-5.3-codex",
"api_base": "https://chatgpt.com/backend-api/codex",
"temperature": 0.0,
"max_retries": 2,
},
"vlm_kimi_example": {
"_comment": "For Kimi Coding subscription. OpenViking applies the recommended provider defaults automatically.",
"provider": "kimi",
"model": "kimi-code",
"api_key": "{your-kimi-subscription-api-key}",
"api_base": "https://api.kimi.com/coding",
"temperature": 0.0,
"max_retries": 2,
},
"vlm_glm_example": {
"_comment": "For GLM Coding Plan via Z.AI subscription API key. Use a vision-capable model for multimodal parsing.",
"provider": "glm",
"model": "glm-4.6v",
"api_key": "{your-zai-api-key}",
"api_base": "https://api.z.ai/api/coding/paas/v4",
"temperature": 0.0,
"max_retries": 2,
},
"rerank": {
"provider": "vikingdb",
"ak": "{your-ak}",
"sk": "{your-sk}",
"host": "api-vikingdb.vikingdb.cn-beijing.volces.com",
"model_name": "doubao-seed-rerank",
"model_version": "251028",
"threshold": 0.1,
},
"rerank_openai_example": {
"_comment": "For OpenAI-compatible rerank providers (e.g. DashScope qwen3-rerank):",
"provider": "openai",
"api_key": "{your-api-key}",
"api_base": "https://dashscope.aliyuncs.com/compatible-api/v1/reranks",
"model": "qwen3-rerank",
"threshold": 0.1,
},
"retrieval": {"hotness_alpha": 0.0, "score_propagation_alpha": 1.0},
"grep": {"engine": "auto", "switch_to_remote_threshold": 10000},
"auto_generate_l0": true,
"auto_generate_l1": true,
"default_search_mode": "thinking",
"default_search_limit": 3,
"enable_memory_decay": true,
"memory_decay_check_interval": 3600,
"memory": {
"version": "v2",
"extraction_enabled": true,
"session_skill_extraction_enabled": false,
},
"ingest": {
"enabled": false,
"server_url": "$OPENVIKING_URL",
"api_key": "$OPENVIKING_API_KEY",
"account": "default",
"user": "default",
"harnesses": {
"claude_code": {"enabled": false, "mode": "both"},
"codex": {"enabled": false, "mode": "backfill"},
"opencode": {"enabled": false, "mode": "watch", "experimental": true},
"hermes": {"enabled": false, "mode": "both", "user_field": "sender"},
"openclaw": {"enabled": false, "mode": "both", "user_field": "sender"},
},
},
"bot": {
"gateway": {
"host": "127.0.0.1",
"port": 18790,
"token": null,
},
"ov_server": {
"server_url": null,
"api_key_type": "user",
"api_key": null,
},
},
"log": {
"level": "INFO",
"format": "%(asctime)s - %(name)s - %(levelname)s - %(message)s",
"output": "stdout",
"rotation": true,
"rotation_days": 3,
"rotation_interval": "midnight",
},
"parsers": {
"pdf": {
"strategy": "auto",
"max_content_length": 100000,
"max_section_size": 4000,
"section_size_flexibility": 0.3,
"max_section_chars": 6000,
"mineru_endpoint": "https://mineru.example.com/api/v1",
"mineru_api_key": "{your-mineru-api-key}",
"mineru_timeout": 300.0,
},
"code": {
"code_summary_mode": "ast",
"extract_functions": true,
"extract_classes": true,
"extract_imports": true,
"include_comments": true,
"max_line_length": 1000,
"max_token_limit": 50000,
"truncation_strategy": "head",
"warn_on_truncation": true,
"github_raw_domain": "raw.githubusercontent.com",
"code_hosting_domains": ["github.com", "gitlab.com"],
"github_domains": ["github.com", "www.github.com"],
"gitlab_domains": ["gitlab.com", "www.gitlab.com"],
},
"image": {
"enable_ocr": false,
"enable_vlm": true,
"ocr_lang": "eng",
"vlm_model": "gpt-4-vision",
"preview_max_dimension": 2048,
"max_file_size_mb": 10.0,
"max_tile_dimension_px": 2048,
"tile_overlap_px": 2,
"large_image_threshold_dimension": 4096
},
"audio": {
"enable_transcription": true,
"transcription_model": "whisper-large-v3",
"language": null,
"extract_metadata": true,
},
"video": {
"extract_frames": true,
"frame_interval": 10.0,
"enable_transcription": true,
"enable_vlm_description": false,
"max_duration": 3600.0,
},
"markdown": {
"preserve_links": true,
"extract_frontmatter": true,
"include_metadata": true,
"max_heading_depth": 3,
},
"html": {
"extract_text_only": false,
"preserve_structure": true,
"clean_html": true,
"extract_metadata": true,
},
"text": {
"detect_language": true,
"split_by_paragraphs": true,
"max_paragraph_length": 1000,
"preserve_line_breaks": false,
},
"webfeed": {
"max_pages": 200,
"max_concurrency": 5,
"request_timeout": 30.0,
"politeness_delay": 0.2,
"same_host_only": true,
"respect_robots": true,
"max_depth": 2,
"suggest_feed": true,
},
},
"encryption": {
"enabled": true,
"provider": "local",
"local": {"key_file": "~/.openviking/master.key"},
"api_key_hashing": {"enabled": false},
},
"encryption_vault_example": {
"_comment": "For HashiCorp Vault integration:",
"enabled": true,
"provider": "vault",
"vault": {
"address": "http://127.0.0.1:8200",
"token": "hvs.your-vault-token",
"mount_point": "transit",
"kv_mount_point": "secret",
"kv_version": 1,
"root_key_name": "openviking-root-key",
"encrypted_root_key_key": "openviking-encrypted-root-key",
},
},
"encryption_volcengine_kms_example": {
"_comment": "For Volcengine KMS integration:",
"enabled": true,
"provider": "volcengine_kms",
"volcengine_kms": {
"region": "cn-beijing",
"access_key": "AKLTyour-access-key",
"secret_key": "your-secret-key",
"key_id": "your-kms-key-id",
"endpoint": null,
"key_file": "~/.openviking/openviking-volcengine-root-key.enc",
},
},
}
Reference in New Issue View Git Blame Copy Permalink