[PR #201] [MERGED] feat(vertex_ai): Support Gemini 2.0 models #1175

Closed
opened 2026-02-16 10:22:11 -05:00 by yindo · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/langgenius/dify-official-plugins/pull/201
Author: @takatea
Created: 2/11/2025
Status: Merged
Merged: 2/12/2025
Merged by: @Yeuoly

Base: mainHead: support-gemini2_0-models-for-vertix-ai


📝 Commits (4)

  • bc31729 feat(vertex_ai): add Gemini 2.0 model variants to provider
  • 9c3b5d5 chore(vertex_ai): update the dependcy version
  • 960c800 chore(vertex_ai): add .env.sample
  • 3e3b14a chore(vertex_ai): bump version to 0.0.2

📊 Changes

8 files changed (+210 additions, -2 deletions)

View changed files

models/vertex_ai/.env.example (+4 -0)
📝 models/vertex_ai/manifest.yaml (+1 -1)
models/vertex_ai/models/llm/gemini-2.0-flash-001.yaml (+41 -0)
models/vertex_ai/models/llm/gemini-2.0-flash-exp.yaml (+41 -0)
models/vertex_ai/models/llm/gemini-2.0-flash-lite-preview-02-05.yaml (+42 -0)
models/vertex_ai/models/llm/gemini-2.0-flash-thinking-exp-01-21.yaml (+39 -0)
models/vertex_ai/models/llm/gemini-2.0-pro-exp-02-05.yaml (+41 -0)
📝 models/vertex_ai/requirements.txt (+1 -1)

📄 Description

Summary

This PR adds support for new Gemini 2.0 model variants including Flash, Pro, and experimental versions for vertex ai.

Added Models

  • gemini-2.0-flash-001
  • gemini-2.0-flash-exp
  • gemini-2.0-flash-lite-preview-02-05
  • gemini-2.0-pro-exp-02-05
  • gemini-2.0-flash-thinking-exp-01-21

Screenshots

Model name Screenshots
gemini-2.0-flash-001 2_0_flash
gemini-2.0-flash-exp 2_0_exp
gemini-2.0-flash-lite-preview-02-05 2_0_flash_lite_preview
gemini-2.0-pro-exp-02-05 2_0_pro_exp_02_05
gemini-2.0-flash-thinking-exp-01-21 2_0_flash_thinking_01_21

Additional Information

The gemini-2.0-flash-thinking-exp-1219 model is available through the Gemini API, but it appears to be no longer available in Vertex AI. When attempting to use this model, the following error occurred:

google.api_core.exceptions.NotFound: 404 Publisher Model `projects/xxx/locations/us-central1/publishers/google/models/gemini-2.0-flash-thinking-exp-1219` not found.

To check this, I searched for "thinking" models in Vertex AI Studio and checked the model list in Google AI Studio. As shown in the screenshots below, the model is indeed not available in either platform.
Therefore, it's possible that gemini-2.0-flash-thinking-exp-1219 may become unavailable in the Gemini API in the near future (although it is currently accessible).

Screenshot
Vertex AI Studio Search Results (filtered by "thinking") vertex_ai_search
Google AI Studio Model List ai_studio_models

Related PR


🔄 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/201 **Author:** [@takatea](https://github.com/takatea) **Created:** 2/11/2025 **Status:** ✅ Merged **Merged:** 2/12/2025 **Merged by:** [@Yeuoly](https://github.com/Yeuoly) **Base:** `main` ← **Head:** `support-gemini2_0-models-for-vertix-ai` --- ### 📝 Commits (4) - [`bc31729`](https://github.com/langgenius/dify-official-plugins/commit/bc31729920404fb3f4d9ff9260ff0139f22fb241) feat(vertex_ai): add Gemini 2.0 model variants to provider - [`9c3b5d5`](https://github.com/langgenius/dify-official-plugins/commit/9c3b5d5a429fe6e41801c2da3a193790af142d42) chore(vertex_ai): update the dependcy version - [`960c800`](https://github.com/langgenius/dify-official-plugins/commit/960c800d8c9b8d880f30e7e89bb29d37ea4bbfc4) chore(vertex_ai): add .env.sample - [`3e3b14a`](https://github.com/langgenius/dify-official-plugins/commit/3e3b14a58352af8a80d0d1fabfba4191f67b9155) chore(vertex_ai): bump version to 0.0.2 ### 📊 Changes **8 files changed** (+210 additions, -2 deletions) <details> <summary>View changed files</summary> ➕ `models/vertex_ai/.env.example` (+4 -0) 📝 `models/vertex_ai/manifest.yaml` (+1 -1) ➕ `models/vertex_ai/models/llm/gemini-2.0-flash-001.yaml` (+41 -0) ➕ `models/vertex_ai/models/llm/gemini-2.0-flash-exp.yaml` (+41 -0) ➕ `models/vertex_ai/models/llm/gemini-2.0-flash-lite-preview-02-05.yaml` (+42 -0) ➕ `models/vertex_ai/models/llm/gemini-2.0-flash-thinking-exp-01-21.yaml` (+39 -0) ➕ `models/vertex_ai/models/llm/gemini-2.0-pro-exp-02-05.yaml` (+41 -0) 📝 `models/vertex_ai/requirements.txt` (+1 -1) </details> ### 📄 Description ## Summary This PR adds support for new Gemini 2.0 model variants including Flash, Pro, and experimental versions for vertex ai. ### Added Models - gemini-2.0-flash-001 - gemini-2.0-flash-exp - gemini-2.0-flash-lite-preview-02-05 - gemini-2.0-pro-exp-02-05 - gemini-2.0-flash-thinking-exp-01-21 ## Screenshots | Model name | Screenshots | |--------|--------| | gemini-2.0-flash-001 | <img width="300" alt="2_0_flash" src="https://github.com/user-attachments/assets/ef26dbfd-66f9-4942-b8ba-0168ef9d9273" />| | gemini-2.0-flash-exp | <img width="300" alt="2_0_exp" src="https://github.com/user-attachments/assets/9293d031-6ba6-4746-81ca-bad81b305dfc" />| | gemini-2.0-flash-lite-preview-02-05 |<img width="300" alt="2_0_flash_lite_preview" src="https://github.com/user-attachments/assets/e2a4da7f-c14f-4939-9367-9c2fee5dd29e" /> | | gemini-2.0-pro-exp-02-05 | <img width="300" alt="2_0_pro_exp_02_05" src="https://github.com/user-attachments/assets/d6e76e9d-f322-49c3-bf5d-33ed0a1182eb" /> | | gemini-2.0-flash-thinking-exp-01-21| <img width="300" alt="2_0_flash_thinking_01_21" src="https://github.com/user-attachments/assets/8d2d08b6-6e8a-4e76-98eb-72622815f594" />| ### Additional Information The `gemini-2.0-flash-thinking-exp-1219` model is available through the Gemini API, but it appears to be no longer available in Vertex AI. When attempting to use this model, the following error occurred: ``` google.api_core.exceptions.NotFound: 404 Publisher Model `projects/xxx/locations/us-central1/publishers/google/models/gemini-2.0-flash-thinking-exp-1219` not found. ``` To check this, I searched for "thinking" models in Vertex AI Studio and checked the model list in Google AI Studio. As shown in the screenshots below, the model is indeed not available in either platform. Therefore, it's possible that `gemini-2.0-flash-thinking-exp-1219` may become unavailable in the Gemini API in the near future (although it is currently accessible). | | Screenshot | |-------------|------------| | Vertex AI Studio Search Results (filtered by "thinking") | <img width="300" alt="vertex_ai_search" src="https://github.com/user-attachments/assets/96f3f481-ad39-46ff-aed5-b2f23e10541c" /> | | Google AI Studio Model List | <img width="300" alt="ai_studio_models" src="https://github.com/user-attachments/assets/bacd29fc-7ed1-4cf5-9fd1-2f45bdf3aa8c" /> | ## Related PR * https://github.com/langgenius/dify-official-plugins/pull/192 --- <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 10:22:11 -05:00
yindo closed this issue 2026-02-16 10:22:11 -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#1175