Intel® AI for Enterprise RAG Text Extractor Service
8.4K
Part of the Intel® AI for Enterprise RAG (ERAG) ecosystem.
The Text Extractor microservice is designed to extract text from data sent for processing. That data can be sent in form of files and/or links for scraping and further extraction. Result of this microservice can then be passed to text_splitter microservice for splitting into chunks and, later, to embedding microservice in order to ultimately persist in the system.
| File Extension | Loader Class |
|---|---|
| AsciiDoc | LoadWithMarkitdown |
| doc, docx | LoadDoc |
| txt | LoadWithMarkitdown |
| json, jsonl | LoadWithMarkitdown |
| csv | LoadWithMarkitdown |
| xlsx, xls | LoadWithMarkitdown |
| LoadPdf | |
| html | LoadWithMarkitdown |
| md | LoadWithMarkitdown |
| xml | LoadWithMarkitdown |
| yaml | LoadWithMarkitdown |
| ppt, pptx | LoadPpt |
| tiff, jpg, jpeg, png, svg | LoadImage |
This service integrates with other OPEA ERAG components:
OPEA ERAG is licensed under the Apache License, Version 2.0.
Copyright © 2024–2026 Intel Corporation. All rights reserved.
Content type
Image
Digest
sha256:b20a41467…
Size
1.4 GB
Last updated
5 months ago
docker pull opea/erag-text-extractor