1,210 tools found
HWP Loader reads HWP files (South Korean official document format) into LlamaIndex, handling both compressed and uncompressed files for document processing.
Load JSON files into LlamaIndex with control over traversal depth and fragment collapsing.
LlamaIndex reader that preserves complex PDF layouts, tables, and multi-column structure.
LlamaIndex reader that pulls a cleaned Lilac dataset back into LlamaIndex documents.
A LlamaIndex reader that loads data from Macrometa GDN collections using federation URL and API key authentication.
MangoppsGuides Loader fetches text content from Mangopps Guides installations into LlamaIndex with configurable limits.
LlamaIndex reader that converts PDFs, Word docs, PowerPoint, HTML, CSV, XML, JSON, and ZIP files to Markdown using Microsoft's MarkItDown library.
Nougat OCR loader parses academic PDFs to extract equations, symbols, and tables with LaTeX math support for LlamaIndex document ingestion.
LlamaIndex reader that parses Obsidian vault markdown files into documents with metadata including wikilinks, backlinks, and optional task extraction.
Load files from S3, Azure Blob, GCS, or any Apache OpenDAL-supported storage into LlamaIndex.
Paddle OCR loader reads equations, symbols, and tables from PDFs for LlamaIndex document processing pipelines.
LlamaIndex loaders that pull scientific papers from Arxiv or PubMed by search query.
