chore: pin document recognition engine
This commit is contained in:
@@ -22,8 +22,8 @@ FastAPI /search ◀── BGE Reranker ◀── RRF merge ◀──────
|
||||
|
||||
| Component | Tech |
|
||||
|------------------|------------------------------------------|
|
||||
| OCR | OCRmyPDF + Tesseract (rus + eng) |
|
||||
| Extraction | Docling (layout, tables, figures) |
|
||||
| OCR | `teamhub-document-recognition-engine` over OCRmyPDF + Tesseract (rus + eng) |
|
||||
| Extraction | `teamhub-document-recognition-engine` over Docling (layout, tables, figures) |
|
||||
| Object storage | MinIO (S3-compatible) |
|
||||
| Relational store | PostgreSQL 16 |
|
||||
| Lexical search | OpenSearch 2.x (BM25 + ru/en analyzers) |
|
||||
@@ -196,7 +196,7 @@ docker compose exec postgres psql -U legacyhub -d legacyhub \
|
||||
|
||||
See [`.env.example`](.env.example) for the full list. Key ones:
|
||||
|
||||
- `OCR_LANGUAGES` - Tesseract language packs (default `rus+eng`).
|
||||
- `OCR_LANGUAGES` - Tesseract language packs passed to the shared recognition engine (default `rus+eng`).
|
||||
- `OCR_ENABLED` - set `false` to skip OCR completely.
|
||||
- `DOCLING_OCR_ENABLED` - prefer OCRmyPDF; only enable if you do not run OCRmyPDF.
|
||||
- `EMBEDDING_DEVICE` / `RERANKER_DEVICE` - `cpu`, `cuda`, or `mps`.
|
||||
|
||||
Reference in New Issue
Block a user