Bugfix to #11, #12, #13

CatchTheTornado / pdf-extract-api

Document (PDF) extraction and parse API using state of the art modern OCRs + Ollama supported models. Anonymize documents. Remove PII. Convert any document or picture to structured JSON or Markdown

https://demo.doctractor.com

GNU General Public License v3.0

1.33k stars 86 forks source link

Bugfix to #11, #12, #13 #17

Closed pkarw closed 2 weeks ago

pkarw commented 2 weeks ago

README ocr command fix - setting data= instead of file= when uploading curl file
fixed env variable OLLAMA_HOST (there was just a typo in the docker-compose.yml)
changed the ollama image version to specific one instead of latest + healthcheck endpoint fixed