# 3.10.4 - Release Notes Squirro 3.10.4 was released June 20, 2024. Learn more about the [Squirro Release Process](../../squirro-release-process.md#getting-squirro-process). ## What’s New - Upgraded the platform to Python 3.11. All Python-based microservices now run on Python 3.11, and all Squirro-related Python dependencies are located in the `/opt/squirro/virtualenv311/` virtual environment (can be activated using `squirro_activate` as before). Please note that Python 3.11 support applies to RHEL 8 (and derivatives) deployments. - Added support for agent-driven LLM endpoints. - Added a Redo OCR configuration option to the PDF OCR pipeline step. ## Improvements - Changed the default value for boosting popular items from the top 100 to the top 30. - Enabled lazy loading for “Show all labels” mode for `LabelsWidget`. - Added an option to hide empty placeholder images in non-grid modes for `ItemWidget`. - Upgraded many Python dependencies to newer or the latest versions. - Limited the Crawler plugin to load 1,000 pages from a website to prevent overloading while indexing large sites. This limit can be adjusted in the data source configuration. - Added a new `response_format` option to the API for running ML workflows. This option allows changing the response format. Supported formats include `standard` (current format with values wrapped in a list) and `plain` (response without wrapping). ## Bug Fixes - Fixed an issue where older strategies were not being parsed by our Pydantic models. - Added the ability to handle missing `abstract` fields when querying items to generate starter questions. - Correctly cast the `distinct-sub-items` flag as a boolean in the reindex script. - Fixed an issue where numbers were being removed when tokenizing a query, e.g., `401k` became `k`. - Fixed mapping for custom summaries in PDFs. - Added custom date formatting inside item details. - Return an error status when the PDF OCR pipeline step raises an exception. - Fixed a 404 error in reference screen inline search when dashboard filters and similar items are mutually exclusive. - Renamed the `dashboards.communityWizard` column to `dashboards.community_wizard` to support PostgreSQL. ## Breaking Changes - As part of the Python 3.11 upgrade , the `autogluon` packages were upgraded from `v0.7.0` to `v1.1.0` because support for Python 3.11 was added in `v1.0.0` of the library. AutoGluon does not support loading models trained on older versions of the library. Therefore, re-training any AI Studio models that were trained with AutoGluon is necessary to use those models again. - Removed the `cache_document` and `document_cache_expiration` configurations from the NLP steps; they no longer have any effect. - Changed the response shape of the `/parse` endpoint so that it no longer wraps values in a list. This affects the usage of Query Contexts in dashboard queries. A migration script is provided to update the most common pattern used in Hybrid Search dashboards (`queryContext?.parse?.type?.length > 0 && queryContext?.parse?.type[0]`) to the new format (`queryContext?.parse?.type`). Other uses of the Query Context in dashboard/widget queries must be manually migrated. ## Installation and Upgrade For new installations, find step-by-step instructions in [Install and Manage Squirro with Ansible](../../../install/ansible/index.md#ansible) (recommended) or [Installing Squirro on Linux](../../../install/linux.md#install-linux). To upgrade an existing installation, see [Upgrading Squirro](../../../install/upgrade.md#install-upgrade).