Skill rating

Extract text, tables, metadata, and images from 107 document formats (PDF, Office, images, HTML, email, archives, academic) using Xberg. Use when writing code that calls Xberg APIs in Python, Node.js/

Use when extracting tabular data from PDFs, spreadsheets, or images. Covers layout-aware table detection, table model selection, output formats (markdown / JSON cells), and known limits.

Use when extracting from many files at once with shared config, bounded parallelism, per-file overrides, and error recovery. Covers the `batch` command, `--file-configs`, `--max-concurrent`, and outpu

Use when extracting keywords (YAKE/RAKE) from documents — and, secondarily, when detecting document language or generating embeddings for RAG and search. Covers the keyword config (and its feature gat

Use when extracting text from scanned PDFs, photographed pages, or images that have no embedded text layer. Covers OCR backends, language packs, force-OCR, and performance tuning.

Use when choosing an output format for extracted documents — plain text, markdown, djot, HTML, JSON, or DocTags. Maps consumer (LLM, parser, archive) to the right `--format` / `--content-format` pair.

Use when splitting extracted text into chunks for LLM context windows or RAG ingestion. Covers chunk size, overlap, markdown/yaml/semantic chunkers, tokenizer-based sizing, and the standalone `chunk`

Per-format Xberg extractors (Office XML, PDF, archives, ...): parsers, security budgets, metadata helpers. Use when changing or adding one.

Xberg plugin traits, typed registries, priority collisions, lifecycle and Alef Python plugin bridges. Use for plugin-system work, not parsing.

How Xberg resolves config: CLI and server/MCP precedence, file walk-up, inline JSON, overrides. Use when adding a setting or one does not take effect.

Xberg OCR backends, preprocessing, caching, page acceptance, hOCR, tables, cross-backend quality. Use for OCR behavior or A/B quality work.

Xberg MIME detection and extractor routing (core/mime.rs, FORMATS registry). Use when a file routes to the wrong extractor or a format is added.

Xberg text chunking (ChunkerType, ChunkingConfig wire names), embeddings and RAG. Use when changing chunking or embeddings code or config.

Xberg core extraction orchestration: cache, extractor fallback, post-processing, concurrency, quality invariants. Use for pipeline changes.

Xberg on top of the shared Alef workflow: output locations, alef.toml sections, regen-breaking core edits, FFI JSON bridge. Use when editing bindings.

Which xberg-io repo owns a cross-repo fix or API, and coordinating compatible sibling changes. Use when work spans sibling repositories.

Xberg extraction benchmarks: running, quality scoring, fixtures, ground truth. Use for the Benchmarks workflow or benchmark-harness work.

crates/xberg-wasm build constraints: wasm-target features, sync-only APIs, SyncExtractor, size limits. Use for wasm32 build or runtime failures.

Xberg workspace layout: version source, members and excluded crates, packages/, tools/, ignore allowlists. Use when placing code or adding a crate.

Xberg REST API server (axum routes, middleware, cache endpoints) and MCP surface. Use when changing an endpoint, server startup or MCP tools.

Xberg PDF extraction: native/Pdfium backend selection, rendering, encryption, OCR fallback, capability gaps. Use for PDF engine work.

The test_documents corpus (submodule, bucket-fetched): read_test_fixture, missing fixtures, A/B controls. Use on a fresh clone or a missing fixture.

Cargo features: shared otel/mcp/allocator contract, then Xberg's ORT-free targets, aggregates, PDF backend, parity guard. Use when editing [features].

Xberg TS/JS tooling: pnpm vs npm lockfiles, Vitest, napi-rs, wasm-pack, integration packages. Use for TS/JS package or tooling changes.

xberg's e2e fixture schema: fields, categories, calls, inputs, mock responses, assertions. Use when adding or editing an xberg e2e fixture.

Xberg release on top of the shared release-workflow: task version:sync to bindings and chart, CI/Publish/Benchmarks readiness. Use before a release.