urieljareth/Estacion-de-Documentos
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

OCR Mistral: modelo mistral-ocr-4-0, batch + fallback con reintentos y errores etiquetados

Browse Source 
- Modelo por defecto mistral-ocr-4-0 (.env.example, config.py, docker-compose)
- MistralClient: OCR en lote via API Batch (/v1/ocr) subiendo JSONL, polling y descarga de resultados
- Reintentos con backoff exponencial en llamadas a Mistral (429/5xx/red); sin reintento en 401/400
- PdfProcessor: lote cuando >= umbral de paginas, fallback sincrono pagina a pagina, placeholder rastreable por pagina fallida
- Errores etiquetados ([AUTH_MISTRAL], [BATCH], [NETWORK], [OCR_EMPTY], [PDF_PARSE]...) en el mensaje del job
- Nuevas variables: MISTRAL_OCR_BATCH_THRESHOLD/POLL_SECONDS/TIMEOUT_SECONDS/RETRY_ATTEMPTS/RETRY_BACKOFF_BASE
This commit is contained in:
urieljareth
2026-07-26 19:58:38 -06:00
parent 379f563d04
commit 239a7510c6
7 changed files with 441 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.env.example
+6 -1
View File
@@ -2,5 +2,10 @@ APP_ENV=development
APP_DATA_DIR=./data
DATABASE_PATH=./data/app.db
MISTRAL_API_KEY=
MISTRAL_OCR_MODEL=mistral-ocr-latest
MISTRAL_OCR_MODEL=mistral-ocr-4-0
MISTRAL_OCR_BATCH_THRESHOLD=3
MISTRAL_OCR_BATCH_POLL_SECONDS=10
MISTRAL_OCR_BATCH_TIMEOUT_SECONDS=1800
MISTRAL_OCR_RETRY_ATTEMPTS=3
MISTRAL_OCR_RETRY_BACKOFF_BASE=2.0
DEEPGRAM_API_KEY=