From 845425af62f9de08093d2c2a6a6fe7ef1533c712 Mon Sep 17 00:00:00 2001 From: Pier-Jean Malandrino Date: Mon, 13 Apr 2026 13:23:27 +0200 Subject: [PATCH] chore: add Coming soon to batch chunking notice, set BATCH_PAGE_SIZE default to 10 --- README.md | 2 +- docker-compose.dev.yml | 2 +- docker-compose.yml | 2 +- docs/getting-started.md | 2 +- document-parser/infra/settings.py | 2 +- frontend/src/shared/i18n.ts | 4 ++-- 6 files changed, 7 insertions(+), 7 deletions(-) diff --git a/README.md b/README.md index 9f76066..eff9564 100644 --- a/README.md +++ b/README.md @@ -206,7 +206,7 @@ All configuration is done via environment variables. See [`.env.example`](.env.e | `UPLOAD_DIR` | `./uploads` | File storage directory | | `DB_PATH` | `./data/docling_studio.db` | SQLite database path | | `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_PAGE_COUNT` | `0` | Maximum number of pages per document (`0` = unlimited) | | `RATE_LIMIT_RPM` | `100` | Max requests per minute per IP (`0` = disabled) | diff --git a/docker-compose.dev.yml b/docker-compose.dev.yml index afd24ac..9255c3b 100644 --- a/docker-compose.dev.yml +++ b/docker-compose.dev.yml @@ -74,7 +74,7 @@ services: DOCLING_SERVE_API_KEY: ${DOCLING_SERVE_API_KEY:-} RATE_LIMIT_RPM: ${RATE_LIMIT_RPM:-100} 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 EMBEDDING_URL: http://embedding:8001 command: ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000", "--reload"] diff --git a/docker-compose.yml b/docker-compose.yml index bde9a9d..918bfb9 100644 --- a/docker-compose.yml +++ b/docker-compose.yml @@ -50,7 +50,7 @@ services: DOCLING_SERVE_API_KEY: ${DOCLING_SERVE_API_KEY:-} RATE_LIMIT_RPM: ${RATE_LIMIT_RPM:-100} 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:-} EMBEDDING_URL: ${EMBEDDING_URL:-} deploy: diff --git a/docs/getting-started.md b/docs/getting-started.md index 6b273ff..c187e72 100644 --- a/docs/getting-started.md +++ b/docs/getting-started.md @@ -141,7 +141,7 @@ All configuration is done via environment variables: | `UPLOAD_DIR` | `./uploads` | File storage directory | | `DB_PATH` | `./data/docling_studio.db` | SQLite database path | | `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 | | `DEPLOYMENT_MODE` | `self-hosted` | `self-hosted` or `huggingface` (shows disclaimer banner) | | `MAX_FILE_SIZE_MB` | `50` | Maximum upload file size in MB (`0` = unlimited) | diff --git a/document-parser/infra/settings.py b/document-parser/infra/settings.py index 0d2cec0..50e465d 100644 --- a/document-parser/infra/settings.py +++ b/document-parser/infra/settings.py @@ -94,7 +94,7 @@ class Settings: max_file_size=int(os.environ.get("MAX_FILE_SIZE", "0")), max_file_size_mb=int(os.environ.get("MAX_FILE_SIZE_MB", "50")), 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", ""), embedding_url=os.environ.get("EMBEDDING_URL", ""), embedding_dimension=int(os.environ.get("EMBEDDING_DIMENSION", "384")), diff --git a/frontend/src/shared/i18n.ts b/frontend/src/shared/i18n.ts index 2c7ff81..e6ee3fd 100644 --- a/frontend/src/shared/i18n.ts +++ b/frontend/src/shared/i18n.ts @@ -130,7 +130,7 @@ const messages: Messages = { 'chunking.deleteConfirm': 'Supprimer ce chunk ? Il sera marqué comme supprimé jusqu\u2019à la prochaine synchronisation.', '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 'nav.search': 'Recherche', @@ -299,7 +299,7 @@ const messages: Messages = { 'chunking.deleteConfirm': 'Delete this chunk? It will be marked as deleted until the next sync.', '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', 'search.hint': 'Enter a term to search through indexed chunks.',