danvics/docling-studio
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

chore: add Coming soon to batch chunking notice, set BATCH_PAGE_SIZE default to 10

Browse source
This commit is contained in:
Pier-Jean Malandrino 2026-04-13 13:23:27 +02:00
parent 5f8b3559e3
commit 845425af62
6 changed files with 7 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
README.md
View file

@ -206,7 +206,7 @@ All configuration is done via environment variables. See [`.env.example`](.env.e
| `UPLOAD_DIR` | `./uploads` | File storage directory | | `UPLOAD_DIR` | `./uploads` | File storage directory |
| `DB_PATH` | `./data/docling_studio.db` | SQLite database path | | `DB_PATH` | `./data/docling_studio.db` | SQLite database path |
| `CONVERSION_TIMEOUT` | `600` | Max seconds for a single Docling conversion | | `CONVERSION_TIMEOUT` | `600` | Max seconds for a single Docling conversion |
| `BATCH_PAGE_SIZE` | `5` | Pages per batch (`0` = process all at once) | | `BATCH_PAGE_SIZE` | `10` | Pages per batch (`0` = process all at once) |
| `MAX_FILE_SIZE_MB` | `50` | Maximum upload file size in MB (`0` = unlimited) | | `MAX_FILE_SIZE_MB` | `50` | Maximum upload file size in MB (`0` = unlimited) |
| `MAX_PAGE_COUNT` | `0` | Maximum number of pages per document (`0` = unlimited) | | `MAX_PAGE_COUNT` | `0` | Maximum number of pages per document (`0` = unlimited) |
| `RATE_LIMIT_RPM` | `100` | Max requests per minute per IP (`0` = disabled) | | `RATE_LIMIT_RPM` | `100` | Max requests per minute per IP (`0` = disabled) |

2
docker-compose.dev.yml
View file

@ -74,7 +74,7 @@ services:
DOCLING_SERVE_API_KEY: ${DOCLING_SERVE_API_KEY:-} DOCLING_SERVE_API_KEY: ${DOCLING_SERVE_API_KEY:-}
RATE_LIMIT_RPM: ${RATE_LIMIT_RPM:-100} RATE_LIMIT_RPM: ${RATE_LIMIT_RPM:-100}
MAX_FILE_SIZE_MB: ${MAX_FILE_SIZE_MB:-50} MAX_FILE_SIZE_MB: ${MAX_FILE_SIZE_MB:-50}
BATCH_PAGE_SIZE: ${BATCH_PAGE_SIZE:-5} BATCH_PAGE_SIZE: ${BATCH_PAGE_SIZE:-10}
OPENSEARCH_URL: http://opensearch:9200 OPENSEARCH_URL: http://opensearch:9200
EMBEDDING_URL: http://embedding:8001 EMBEDDING_URL: http://embedding:8001
command: ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000", "--reload"] command: ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000", "--reload"]

2
docker-compose.yml
View file

@ -50,7 +50,7 @@ services:
DOCLING_SERVE_API_KEY: ${DOCLING_SERVE_API_KEY:-} DOCLING_SERVE_API_KEY: ${DOCLING_SERVE_API_KEY:-}
RATE_LIMIT_RPM: ${RATE_LIMIT_RPM:-100} RATE_LIMIT_RPM: ${RATE_LIMIT_RPM:-100}
MAX_FILE_SIZE_MB: ${MAX_FILE_SIZE_MB:-50} MAX_FILE_SIZE_MB: ${MAX_FILE_SIZE_MB:-50}
BATCH_PAGE_SIZE: ${BATCH_PAGE_SIZE:-5} BATCH_PAGE_SIZE: ${BATCH_PAGE_SIZE:-10}
OPENSEARCH_URL: ${OPENSEARCH_URL:-} OPENSEARCH_URL: ${OPENSEARCH_URL:-}
EMBEDDING_URL: ${EMBEDDING_URL:-} EMBEDDING_URL: ${EMBEDDING_URL:-}
deploy: deploy:

2
docs/getting-started.md
View file

@ -141,7 +141,7 @@ All configuration is done via environment variables:
| `UPLOAD_DIR` | `./uploads` | File storage directory | | `UPLOAD_DIR` | `./uploads` | File storage directory |
| `DB_PATH` | `./data/docling_studio.db` | SQLite database path | | `DB_PATH` | `./data/docling_studio.db` | SQLite database path |
| `CONVERSION_TIMEOUT` | `600` | Max seconds per Docling conversion | | `CONVERSION_TIMEOUT` | `600` | Max seconds per Docling conversion |
| `BATCH_PAGE_SIZE` | `5` | Pages per batch (`0` = process all at once) | | `BATCH_PAGE_SIZE` | `10` | Pages per batch (`0` = process all at once) |
| `MAX_CONCURRENT_ANALYSES` | `3` | Maximum parallel analysis jobs | | `MAX_CONCURRENT_ANALYSES` | `3` | Maximum parallel analysis jobs |
| `DEPLOYMENT_MODE` | `self-hosted` | `self-hosted` or `huggingface` (shows disclaimer banner) | | `DEPLOYMENT_MODE` | `self-hosted` | `self-hosted` or `huggingface` (shows disclaimer banner) |
| `MAX_FILE_SIZE_MB` | `50` | Maximum upload file size in MB (`0` = unlimited) | | `MAX_FILE_SIZE_MB` | `50` | Maximum upload file size in MB (`0` = unlimited) |

2
document-parser/infra/settings.py
View file

@ -94,7 +94,7 @@ class Settings:
max_file_size=int(os.environ.get("MAX_FILE_SIZE", "0")), max_file_size=int(os.environ.get("MAX_FILE_SIZE", "0")),
max_file_size_mb=int(os.environ.get("MAX_FILE_SIZE_MB", "50")), max_file_size_mb=int(os.environ.get("MAX_FILE_SIZE_MB", "50")),
rate_limit_rpm=int(os.environ.get("RATE_LIMIT_RPM", "100")), rate_limit_rpm=int(os.environ.get("RATE_LIMIT_RPM", "100")),
batch_page_size=int(os.environ.get("BATCH_PAGE_SIZE", "5")), batch_page_size=int(os.environ.get("BATCH_PAGE_SIZE", "10")),
opensearch_url=os.environ.get("OPENSEARCH_URL", ""), opensearch_url=os.environ.get("OPENSEARCH_URL", ""),
embedding_url=os.environ.get("EMBEDDING_URL", ""), embedding_url=os.environ.get("EMBEDDING_URL", ""),
embedding_dimension=int(os.environ.get("EMBEDDING_DIMENSION", "384")), embedding_dimension=int(os.environ.get("EMBEDDING_DIMENSION", "384")),

4
frontend/src/shared/i18n.ts
View file

@ -130,7 +130,7 @@ const messages: Messages = {
'chunking.deleteConfirm': 'chunking.deleteConfirm':
'Supprimer ce chunk ? Il sera marqué comme supprimé jusqu\u2019à la prochaine synchronisation.', 'Supprimer ce chunk ? Il sera marqué comme supprimé jusqu\u2019à la prochaine synchronisation.',
'chunking.batchNotice': 'chunking.batchNotice':
'Le chunking n\u2019est pas disponible pour cette analyse. Les documents volumineux trait\u00e9s par batch ne g\u00e9n\u00e8rent pas la structure interne n\u00e9cessaire au d\u00e9coupage.', 'Le chunking n\u2019est pas disponible pour cette analyse. Les documents volumineux trait\u00e9s par batch ne g\u00e9n\u00e8rent pas la structure interne n\u00e9cessaire au d\u00e9coupage. Coming soon !',
// Search // Search
'nav.search': 'Recherche', 'nav.search': 'Recherche',
@ -299,7 +299,7 @@ const messages: Messages = {
'chunking.deleteConfirm': 'chunking.deleteConfirm':
'Delete this chunk? It will be marked as deleted until the next sync.', 'Delete this chunk? It will be marked as deleted until the next sync.',
'chunking.batchNotice': 'chunking.batchNotice':
'Chunking is not available for this analysis. Large documents processed in batch mode do not generate the internal structure required for chunking.', 'Chunking is not available for this analysis. Large documents processed in batch mode do not generate the internal structure required for chunking. Coming soon!',
'nav.search': 'Search', 'nav.search': 'Search',
'search.hint': 'Enter a term to search through indexed chunks.', 'search.hint': 'Enter a term to search through indexed chunks.',