anydoc is a pure Rust document parser from Firecrawl that turns Word, Excel, PowerPoint, PDF, and ten other formats into consistent GitHub-Flavored Markdown. Median conversion is 4.4ms, MIT licensed, with Rust, Node, Python, WASM, and CLI bindings built for agent pipelines.
A 3B MoE model with Reference Sliding Window Attention parses long PDFs in a single forward pass. Here is when it beats page-by-page OCR pipelines for RAG and document automation.
Datalab's lift is a 9B open-weights vision model that decodes directly against your JSON Schema. Schema-constrained generation guarantees valid structure, trained abstention returns null instead of hallucinating fields, and self-hosted runs hit 90.2% field accuracy.
Vision-language agents score under 1% on end-to-end PDF forms until FieldFinder helps them find input fields. Two models, one task, 54-point gains.