# documentation: https://github.com/Unstructured-IO/unstructured-api?tab=readme-ov-file#--general-pre-processing-pipeline-for-documents
# slogan: Unstructured provides a platform and tools to ingest and process unstructured documents for Retrieval Augmented Generation (RAG) and model fine-tuning.
# tags: workflow, orchestration, data-pipeline, python, data, machine-learning, data-science, nlp, unstructured, ocr, data-extraction
# logo: svgs/unstructured.png
# port: 8000

services:
  unstructured:
    image: "downloads.unstructured.io/unstructured-io/unstructured-api:latest"
    environment:
      - SERVICE_FQDN_UNSTRUCTURED_8000
      - "UNSTRUCTURED_API_KEY=${SERVICE_PASSWORD_APIKEY}"
    healthcheck:
      test:
        - CMD
        - wget
        - "-qO-"
        - "http://0.0.0.0:8000/healthcheck"
      interval: 5s
      timeout: 30s
      retries: 10