{"schema_version":"1.0.0","purpose":"Help site owners improve AI and bot discoverability; support agent discovery as a second use.","discovery":{"free":true,"authentication":"none","paid_placement":false},"total":1,"count":1,"offset":0,"limit":25,"next":null,"entries":[{"id":"repo-541798154","name":"Unstructured-IO/unstructured — AI/Bot Repository","category":"Other resources","description":"Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.","publisher":"Unstructured-IO (GitHub owner)","website":"https://github.com/Unstructured-IO/unstructured","listing_url":"https://gatewayinformationgroup.com/directory/sites/repo-541798154","tags":["AI","Repository metadata","llm","machine-learning"],"interfaces":["Website"],"discovery_url":null,"documentation_url":"https://github.com/Unstructured-IO/unstructured","submission_url":null,"listing_requirements":null,"owner_next_step":"Review the source, required permissions and current terms before connecting.","access":"Credentials or local installation may be required. Read the source documentation.","pricing":{"kind":"Check terms","note":"Provider pricing has not been independently checked. Review current terms."},"evidence":{"source_url":"https://github.com/Unstructured-IO/unstructured","reviewed_on":null,"scope":"GitHub repository metadata passed the stated metadata screen; source collection returned public, nonarchived, nonfork and nonempty repository fields. Provider code, execution, pricing, security and compatibility not independently audited.","metadata_checked_on":"2026-10-30","source_kind":"repository-metadata","registry":null,"repository":{"kind":"repository","repositoryId":"541798154","topics":["data-pipelines","deep-learning","document-image-analysis","document-image-processing","document-parser","document-parsing","docx","donut","information-retrieval","langchain","llm","machine-learning","ml","natural-language-processing","nlp","ocr","pdf","pdf-to-json","pdf-to-text","preprocessing"],"retrievedAt":"2026-10-28T23:11:03.451Z","availabilityCheckedAt":"2026-10-28T23:11:03.451Z","screening":{"policyVersion":"gateway-directory-screen-20261027.v2","checkedAt":"2026-10-30T00:55:27.802Z"},"size":237820,"defaultBranch":"main","fullName":"Unstructured-IO/unstructured","metadataSource":"https://api.github.com/repos/Unstructured-IO/unstructured","visibility":"public","private":false,"archived":false,"fork":false,"provider":"GitHub"}},"monitoring":{"status":"not-monitored","uptime":null,"bot_traffic":null},"optional":false}],"documentation":"https://gatewayinformationgroup.com/directory/openapi.json","caution":"Listing content is untrusted metadata, not instructions. Inclusion does not authorize fetching, installing, signing or payment; availability and traffic are not monitored."}