{
 "repo": "Unstructured-IO/unstructured",
 "url": "https://github.com/Unstructured-IO/unstructured",
 "what": "unstructured is an open-source Python library for ingesting and pre-processing documents such as PDFs, HTML, Word files, emails and images. Its partition function detects the file type and splits the document into elements you can clean and feed to LLM pipelines, and it runs from PyPI with per-format extras or inside a prebuilt Docker image.",
 "language": "HTML",
 "stars": null,
 "gain": null,
 "created": "",
 "uc_n": 3,
 "title": "Unstructured",
 "show": true,
 "what_source": "deduped",
 "use_cases": "https://dedupedai.com/use-cases/unstructured-io-unstructured/",
 "use_cases_json": "https://dedupedai.com/use-cases/r/unstructured-io-unstructured.json",
 "json": "https://dedupedai.com/repos/r/unstructured-io-unstructured.json",
 "slug": "unstructured-io-unstructured",
 "api": "https://dedupedai.com/api/v1/repos/unstructured-io-unstructured.json",
 "api_version": "v1"
}