Home / AI / Dify / 0.4.4
Dify 0.4.4stable Released Jan 05, 2024
Impact Score: 5/10

Dify: v0.4.4

Source available — automated, not human-reviewed

Component: dify · Channel: stable. Automated analysis, not a compatibility certification. How this works.

Analysis updated: 2026-11-01.

Compatibility not verified — check source notes
📄 .MD
✨ Features 5 🔧 Bug Fixes 6
⚡ Executive Summary (TL;DR)

Dify 0.4.4. Source highlight: Add Together.ai model provider and fix some bugs.

Visit Dify Official Site ↗ Official Release Source ↗ All Dify Releases 📡 Dify RSS
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.

✨ New Features & Capabilities (5)

  • feat: optimize memory & invoke error output
  • Feat/optimize entity construct
  • feat: reuse decoding_rsa_key & decoding_cipher_rsa & optimize construct
  • Add Together.ai's OpenAI API-compatible inference endpoints
  • feat: reorder togetherai

🔧 Bug Fixes & Patches (6)

  • fix: vision fail in complete app
  • fix: llm result usage none
  • fix: gpt-4-32k model name empty in OpenAI response
  • fix: arg user required and must not be null in service generate api
  • fix: text completion app cannot get data.
  • fix: text-generation run batch
📄 View Raw Release Notes (Original Developer Log)
Add Together.ai model provider and fix some bugs. ## What's Changed * feat: optimize memory & invoke error output by @takatost in https://github.com/langgenius/dify/pull/1931 * fix: vision fail in complete app by @takatost in https://github.com/langgenius/dify/pull/1933 * Feat/optimize entity construct by @takatost in https://github.com/langgenius/dify/pull/1935 * feat: reuse decoding_rsa_key & decoding_cipher_rsa & optimize construct by @takatost in https://github.com/langgenius/dify/pull/1937 * fix: llm result usage none by @takatost in https://github.com/langgenius/dify/pull/1940 * fix: gpt-4-32k model name empty in OpenAI response by @takatost in https://github.com/langgenius/dify/pull/1941 * fix: arg user required and must not be null in service generate api by @takatost in https://github.com/langgenius/dify/pull/1943 * fix: text completion app cannot get data. by @GarfieldDai in https://github.com/langgenius/dify/pull/1942 * fix: text-generation run batch by @zxhlyh in https://github.com/langgenius/dify/pull/1945 * fix streaming by @guchenhe in https://github.com/langgenius/dify/pull/1944 * Add Together.ai's OpenAI API-compatible inference endpoints by @guchenhe in https://github.com/langgenius/dify/pull/1947 * feat: reorder togetherai by @takatost in https://github.com/langgenius/dify/pull/1951 * change API key field to 'required' by @guchenhe in https://github.com/langgenius/dify/pull/1953 * optimize qa prompt by @JohnJyong in https://github.com/langgenius/dify/pull/1957 * prohibit enable and disable function when segment is not completed by @JohnJyong in https://github.com/langgenius/dify/pull/1954 * delete remnant 'required': false by @guchenhe in https://github.com/langgenius/dify/pull/1955 * fix: check result should be string. by @GarfieldDai in https://github.com/langgenius/dify/pull/1959 * fix: generate not stop when pressing stop link by @takatost in https://github.com/langgenius/dify/pull/1961 * bump version to 0.4.4 by @takatost in https://github.com/langgenius/dify/pull/1962 **Full Changelog**: https://github.com/langgenius/dify/compare/0.4.3...0.4.4
← Older Version Dify 0.4.3