⚠️ Breaking Change
Impact Score: 7/10
Dify: v0.3.32
Source available — automated, not human-reviewed
Component: dify · Channel: stable. Automated analysis, not a compatibility certification. How this works.
Analysis updated: 2026-11-01.
Breaking-change evidence from the source
⚠️ Breaking Change We've recently switched provider `ChatGLM` to the OpenAI API protocol, so from now on, we'll only be supporting `ChatGLM3` and `ChatGLM2`. Unfortunately, support for `ChatGLM1` has been deprecated.
⚡ Executive Summary (TL;DR)
Dify 0.3.32. Source highlight: Supported the `rerank` model of `xinference` for local deployment, such as: `bge-reranker-large`, `bge-reranker-base`.
Who Does This Impact? (Role-Based Analysis)
💻 Software Engineers & Devs
Check the source notes against the package and APIs you use before upgrading.
📊 Product & Engineering Leads
Use the documented changes to assess relevance to your product; release frequency alone is not a quality measure.
⚙️ DevOps & Security
Verify the target version, runtime requirements and rollback procedure in the official documentation.
⚠️ Breaking Changes & Deprecations (1)
- ⚠️ Breaking Change We've recently switched provider `ChatGLM` to the OpenAI API protocol, so from now on, we'll only be supporting `ChatGLM3` and `ChatGLM2`. Unfortunately, support for `ChatGLM1` has been deprecated.
✨ New Features & Capabilities (6)
- Supported the `rerank` model of `xinference` for local deployment, such as: `bge-reranker-large`, `bge-reranker-base`.
- feat: bump version to 0.3.31-fix1
- feat: add anthropic claude-2.1 support
- feat: bump version to 0.3.31-fix2
- feat: optimize db connections in thread
- feat: bump version to 0.3.31-fix3
🔧 Bug Fixes & Patches (6)
- fix: retrieval test page hide rerank model also hide retrieval config
- fix: chat on start bug
- fix: safari can not in
- fix sql transaction error in statistic API
- fix: chat token spent info style
- fix weaviate hybrid search issue
📄 View Raw Release Notes (Original Developer Log)
## New Features
- Supported the `rerank` model of `xinference` for local deployment, such as: `bge-reranker-large`, `bge-reranker-base`.
- ChatGLM2/3 support
## ⚠️ Breaking Change
We've recently switched provider `ChatGLM` to the OpenAI API protocol, so from now on, we'll only be supporting `ChatGLM3` and `ChatGLM2`. Unfortunately, support for `ChatGLM1` has been deprecated.
## What's Changed
* fix: retrieval test page hide rerank model also hide retrieval config by @iamjoel in https://github.com/langgenius/dify/pull/1585
* fix: chat on start bug by @iamjoel in https://github.com/langgenius/dify/pull/1588
* Update docker-compose.yaml by @JohnJyong in https://github.com/langgenius/dify/pull/1587
* feat: bump version to 0.3.31-fix1 by @takatost in https://github.com/langgenius/dify/pull/1589
* fix: safari can not in by @iamjoel in https://github.com/langgenius/dify/pull/1590
* feat: add anthropic claude-2.1 support by @takatost in https://github.com/langgenius/dify/pull/1591
* feat: bump version to 0.3.31-fix2 by @takatost in https://github.com/langgenius/dify/pull/1592
* fix sql transaction error in statistic API by @waltcow in https://github.com/langgenius/dify/pull/1586
* fix: chat token spent info style by @zxhlyh in https://github.com/langgenius/dify/pull/1597
* fix weaviate hybrid search issue by @JohnJyong in https://github.com/langgenius/dify/pull/1600
* feat: optimize db connections in thread by @takatost in https://github.com/langgenius/dify/pull/1601
* fix: hybrid search when document is none by @JohnJyong in https://github.com/langgenius/dify/pull/1603
* Fix/multi thread parameter by @JohnJyong in https://github.com/langgenius/dify/pull/1604
* feat: bump version to 0.3.31-fix3 by @takatost in https://github.com/langgenius/dify/pull/1606
* feat: xinference rerank model support by @takatost in https://github.com/langgenius/dify/pull/1615
* feat: chatglm3 support by @takatost in https://github.com/langgenius/dify/pull/1616
* fix: dataset tool missing in n-to-1 retrieve mode by @takatost in https://github.com/langgenius/dify/pull/1617
* fix: provider chatglm tests error by @takatost in https://github.com/langgenius/dify/pull/1618
* feat: add xinference rerank model by @zxhlyh in https://github.com/langgenius/dify/pull/1619
* feat: bump version to 0.3.32 by @takatost in https://github.com/langgenius/dify/pull/1620
## New Contributors
* @waltcow made their first contribution in https://github.com/langgenius/dify/pull/1586
**Full Changelog**: https://github.com/langgenius/dify/compare/0.3.31...0.3.32