2024-10-04 08:54:32 +00:00
# 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.
2025-08-17 16:23:57 +00:00
# category: ai
2024-10-04 08:54:32 +00:00
# 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 :
2025-08-10 08:10:22 +00:00
- SERVICE_URL_UNSTRUCTURED_8000
2024-10-04 08:54:32 +00:00
- "UNSTRUCTURED_API_KEY=${SERVICE_PASSWORD_APIKEY}"
healthcheck :
test :
- CMD
- wget
- "-qO-"
- "http://0.0.0.0:8000/healthcheck"
2024-10-07 09:54:54 +00:00
interval : 5s
timeout : 30s
retries : 10