An underrated alternative to Unstructured/Nougat for text extraction(blog.min.io)
blog.min.io
An underrated alternative to Unstructured/Nougat for text extraction
https://blog.min.io/minio-tika-text-extraction/
2 comments
Put together a document text extraction server using Apache Tika (with ~30 lines of code) that can be used to vectorize text for retrieval-augmented generation or to create LLM training datasets.
Much credit to the tika-python project for making the Python bindings!
Much credit to the tika-python project for making the Python bindings!
Furthermore, using a backing object store (i.e. MinIO) to hold the source documents is very useful (whether the extracted text is being used for RAG or an LLM training dataset).