---
title: "gaik-toolkit"
description: "Skills for building document pipelines with the gaik Python toolkit: choosing a document parser that preserves table structure, designing extraction schemas that stay inside provider limits, and building hybrid pgvector "
canonical: https://agentpluginsdirectory.com/plugins/gaik-toolkit--gaik-project
last-updated: 2026-10-01
---

# gaik-toolkit
Skills for building document pipelines with the gaik Python toolkit: choosing a document parser that preserves table structure, designing extraction schemas that stay inside provider limits, and building hybrid pgvector search whose failures are visible instead of silent.
- Slug: gaik-toolkit--gaik-project
- Publisher: GAIK project
- Repository: https://github.com/GAIK-project/gaik-toolkit
- Manifest: implementation_layer/no-code-assets/agent-plugin/plugin.json
- Version: 0.2.5
- License: MIT
- Category (editorial): other
- Skills: 3 (extracting-structured-data, parsing-documents, searching-documents)
- MCP servers: 0
- Stars: 99
- Repository created: 2025-10-10
- Repository last pushed: 2026-09-30
- Publisher type: Organization
- Listing: https://agentpluginsdirectory.com/plugins/gaik-toolkit--gaik-project
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What gaik-toolkit does, in the publisher's words

A portable Agent Plugins v1 package containing the skills an AI coding agent needs to build document pipelines with the gaik Python toolkit.

The skills carry decisions and failure modes that are expensive to rediscover, which parser preserves a table's structure, why an extraction request is refused, why a hybrid search quietly became vector-only, rather than restating the API reference, which the agent can read from the package itself.

Each skill is self-contained: SKILL.md holds the workflow, and references/ holds detail loaded only when the task needs it.

- Agent Plugins v1 clients (Codex, Copilot, VS Code, Cursor, Kiro) read plugin.json at this directory's root and discover skills in skills/.
- Claude Code does not implement Agent Plugins v1. It reads its own manifest,.claude-plugin/plugin.json, and discovers the same skills/.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/GAIK-project/gaik-toolkit/HEAD/implementation_layer/no-code-assets/agent-plugin/README.md

## Skills

- extracting-structured-data: Extracts structured data, fields, tables, line items, out of documents into a validated schema using the gaik toolkit, and designs schemas that stay inside provider limits and produce checkable evidence. Use when pulling fields from invoices, forms, contracts, reports, or scanned documents into JSO…
- parsing-documents: Converts PDFs, scans, and Word documents into text or markdown with the gaik toolkit's parsers, choosing the parser that will not silently destroy the structure the downstream task depends on. Use when reading a PDF or DOCX into text, pulling tables out of a document, running OCR on scans, feeding…
- searching-documents: Builds and debugs retrieval with the gaik toolkit, PgVectorStore, Ranker, FinnishTextProcessor, RelevanceGate, as hybrid search: pgvector similarity plus Postgres full-text, fused by rank, and the same design in plain SQL for a TypeScript app. Use whenever gaik is used for search or RAG retrieval,…

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.