v4.17.1 v4.17.2
labring/FastGPTSep 30, 2026 → Oct 9, 20269 days between releases
What's New
Refactors knowledge base training pipeline and migrates core pages to client-side rendering.
Breaking Changes
- Manual database migration scripts required: 20261008_migrate_chunk_training and 20261009_migrate_dataset_rebuild_status
New Features
- Knowledge base data pre-storage and training pipeline refactoring with a three-state index lifecycle.
- Search scope limitation to current directory and sub-tree.
- Training progress dashboard with refined progress tracking per processing mode.
- Client-side rendering (CSR) for admin and workspace pages with shallow routing.
- BullMQ failure retention optimization changed to count-based (10,000 jobs).
Improvements
- Core management pages migrated to client-side rendering (CSR) with shallow routing.
- i18n resources optimized for faster loading.
- Knowledge base search capabilities improved by limiting scopes.
- Knowledge base model switching and synonym rebuild optimized to only trigger on indexed data.
- BullMQ failure retention strategy optimized to count-based.
Bug Fixes
- Fixed workflow condition logic (If/Else, Regex) for non-string values.
- Fixed admin menu visibility issues when a valid license is not present.
Upgrade Notes
Requires manual execution of two migration scripts (20261008_migrate_chunk_training and 20261009_migrate_dataset_rebuild_status) in the admin panel. Ensure old versions are stopped before running the chunk training migration.
The Two Releases
v4.17.1
Sep 30, 2026· 22 days ago
FastGPT v4.17.1 focuses on system stability and user experience, merging commercial admin features into the main app, introducing file-level knowledge base permissions, and adding comprehensive model health monitoring. It includes automated migration scripts for data updates and a wide array of bug fixes for workflows, tools, and document parsing.
Full release notesv4.17.2
Oct 9, 2026· 13 days ago
This release updates FastGPT images and introduces a major refactoring of the knowledge base training pipeline, including data pre-storage and index lifecycle management. It also optimizes system performance by migrating core pages to client-side rendering and improves search capabilities by limiting scopes. Several critical bug fixes were made to workflow logic, admin permissions, and Markdown parsing.
Full release notes