[PR #687] [MERGED] feat(gemini): Update Gemini Models to support image multimodal output #1493

Closed
opened 2026-02-16 10:23:06 -05:00 by yindo · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/langgenius/dify-official-plugins/pull/687
Author: @QuantumGhost
Created: 4/10/2025
Status: Merged
Merged: 4/25/2025
Merged by: @crazywoola

Base: mainHead: feat/gemini-image-support-2


📝 Commits (4)

  • a6babcb types(gemini): Improve type hints for Google Gemini plugin
  • 35263e2 WIP: feat(gemini): Update Gemini Models to support image multimodal output
  • 998c669 fix(gemini): Restrict Image in response_modalities to gemini-2.0-flash-exp
  • 012d481 Merge remote-tracking branch 'upstream/main' into feat/gemini-image-support-2

📊 Changes

3 files changed (+305 additions, -91 deletions)

View changed files

📝 models/gemini/README.md (+19 -2)
📝 models/gemini/manifest.yaml (+1 -1)
📝 models/gemini/models/llm/llm.py (+285 -88)

📄 Description

Related Issue or Context

Documentation for Gemini: https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal-response-generation

Type of Change

  • Bug Fix (non-breaking change which fixes an Issue)
  • New Feature (non-breaking change which adds Functionality)
  • Breaking Change (fix or feature that may cause existing Functionality to not work as expected)
    • Input/Output Handling:
      • Multimodal Output Generation (Images, Audio, Video if applicable)
  • Documentation Update
  • Code Refactoring
  • Other

Version Control (if applicable)

  • Version bumped in Manifest.yaml (top-level Version field, not in Meta section)

Test Evidence (if applicable)

Important

Visual Proof is required for Bug Fixes, New Features, and Breaking Changes:

Screenshots or Video/GIF:

Now images generated by Google Gemini model can be viewed in the chat:

image

Environment Verification

Local Deployment Environment

Local Deployment Dify Version: v1.1.3+dev (a development version, see langgenius/dify#17372).

SaaS Environment

  • Testing performed on cloud.dify.ai
    Wait for the release of langgenius/dify#17372.
  • Changes tested in a Clean Environment that matches Production Configuration

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/langgenius/dify-official-plugins/pull/687 **Author:** [@QuantumGhost](https://github.com/QuantumGhost) **Created:** 4/10/2025 **Status:** ✅ Merged **Merged:** 4/25/2025 **Merged by:** [@crazywoola](https://github.com/crazywoola) **Base:** `main` ← **Head:** `feat/gemini-image-support-2` --- ### 📝 Commits (4) - [`a6babcb`](https://github.com/langgenius/dify-official-plugins/commit/a6babcba40fd2f880da2125971c5db267bca95c8) types(gemini): Improve type hints for Google Gemini plugin - [`35263e2`](https://github.com/langgenius/dify-official-plugins/commit/35263e20fafcaded4b831d972c6fbfed5b5ede6b) WIP: feat(gemini): Update Gemini Models to support image multimodal output - [`998c669`](https://github.com/langgenius/dify-official-plugins/commit/998c66918be03ef10872b3af5442c5bec55b4223) fix(gemini): Restrict `Image` in `response_modalities` to gemini-2.0-flash-exp - [`012d481`](https://github.com/langgenius/dify-official-plugins/commit/012d481b37b6e6286d8b38b3dbf7fd18853fdc7f) Merge remote-tracking branch 'upstream/main' into feat/gemini-image-support-2 ### 📊 Changes **3 files changed** (+305 additions, -91 deletions) <details> <summary>View changed files</summary> 📝 `models/gemini/README.md` (+19 -2) 📝 `models/gemini/manifest.yaml` (+1 -1) 📝 `models/gemini/models/llm/llm.py` (+285 -88) </details> ### 📄 Description ## Related Issue or Context Documentation for Gemini: https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal-response-generation ## Type of Change - [ ] Bug Fix (non-breaking change which fixes an Issue) - [x] New Feature (non-breaking change which adds Functionality) - [x] Breaking Change (fix or feature that may cause existing Functionality to not work as expected) - **Input/Output Handling**: - [x] Multimodal Output Generation (Images, Audio, Video if applicable) - [ ] Documentation Update - [ ] Code Refactoring - [ ] Other ## Version Control (if applicable) - [ ] Version bumped in Manifest.yaml (top-level `Version` field, not in Meta section) ## Test Evidence (if applicable) > [!IMPORTANT] > Visual Proof is required for Bug Fixes, New Features, and Breaking Changes: ### Screenshots or Video/GIF: Now images generated by Google Gemini model can be viewed in the chat: <img width="438" alt="image" src="https://github.com/user-attachments/assets/b6e2cab0-9a94-479e-ad3f-f57749223cee" /> ### Environment Verification #### Local Deployment Environment Local Deployment Dify Version: v1.1.3+dev (a development version, see langgenius/dify#17372). #### SaaS Environment - [ ] Testing performed on cloud.dify.ai Wait for the release of langgenius/dify#17372. - [ ] Changes tested in a Clean Environment that matches Production Configuration --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
yindo added the pull-request label 2026-02-16 10:23:06 -05:00
yindo closed this issue 2026-02-16 10:23:06 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify-official-plugins#1493