21 Commits

Author SHA1 Message Date
CaIon
a29f4d88c5 Update model-ratio.go 2025-04-04 23:41:41 +08:00
Sh1n3zZ
e1b9f164f9 feat: gemini Embeddings support 2025-03-10 23:32:06 +08:00
1808837298@qq.com
ed4e1c2332 fix: Update Gemini safety settings category 2025-02-26 19:18:00 +08:00
1808837298@qq.com
e19b244e73 feat: Add Gemini safety settings configuration support (close #703) 2025-02-26 16:54:43 +08:00
Sh1n3zZ
61d2a2f92d feat: add Gemini Imagen image generation support 2025-02-18 01:41:58 +08:00
HynoR
efdd6fb657 chore: sync gemini aistudio model 2025-02-06 13:32:19 +08:00
CalciumIon
f9a7f6085e feat: Add GEMINI_VISION_MAX_IMAGE_NUM configuration
- Introduced `GEMINI_VISION_MAX_IMAGE_NUM` to README files for better user guidance.
- Updated `env.go` to retrieve the maximum image number from environment variables, defaulting to 16.
- Modified image handling logic in `relay-gemini.go` to respect the new configuration, allowing disabling of the limit by setting it to -1.
- Removed hardcoded constant for maximum image number in `constant.go` to streamline configuration management.
2024-12-20 21:36:23 +08:00
HynoR
f3a7119745 chore: 更新gemini模型 2024-12-20 19:17:56 +08:00
HynoR
3fa1d93b9c chore: 更新gemini模型 2024-12-20 19:14:53 +08:00
CalciumIon
cab30014ad feat: Add new experimental Gemini versions to ModelList
- Included additional versions: "gemini-2.0-flash-thinking-exp" and "gemini-2.0-flash-thinking-exp-1219".
- Added comments to categorize versions as old, experimental, and flash experimental for better clarity.
2024-12-20 13:26:51 +08:00
CalciumIon
9a54b345c5 feat: support gemini-2.0-flash-thinking #639 #637 2024-12-20 13:20:07 +08:00
CalciumIon
e6c6bbdef9 feat: support gemini SystemInstructions #408 2024-12-16 20:19:29 +08:00
CalciumIon
b1fb595610 feat: add model gemini-2.0-flash-exp 2024-12-12 17:21:37 +08:00
CalciumIon
024cdb08df feat: Update model lists and enhance model retrieval in Adaptor
- Refactored ModelList in the gemini constant to include new models and remove outdated ones.
- Modified the GetModelList function in the Adaptor to consolidate model lists from multiple sources, ensuring a comprehensive and updated list is returned.
- Commented out deprecated models in the vertex constants for clarity and future reference.
2024-12-11 21:39:41 +08:00
leezhuuuuu
5d96f7b2cc 增加对于gemini-exp-1114模型的支持,映射到v1beta
feat(gemini): add support for gemini-exp-1114 model

- Add gemini-exp-1114 to ModelList in constant.go
- Update GetRequestURL in adaptor.go to use v1beta API version for gemini-exp-1114
- Keep backward compatibility for other models

This change enables the use of the experimental gemini-exp-1114 model by correctly routing its requests to the v1beta API endpoint while maintaining existing functionality for other models.
2024-11-16 21:29:35 +08:00
Yan
0b5f2a7089 add gemini exp 2024-09-11 19:37:03 +08:00
HowieWu
a3a6733fb5 Update constant.go 2024-05-15 10:28:30 +08:00
Maple Gao
3b6ea51033 fix: rename the latest Gemini model name 2024-04-15 14:22:40 +08:00
Maple Gao
21250a46a6 feat: support google v1beta and Gemini Ultra 2024-04-15 14:19:19 +08:00
CaIon
1587ea565b feat: support gemini-1.5 2024-03-25 22:33:46 +08:00
1808837298@qq.com
5b18cd6b0a feat: 初步重构 2024-02-29 01:08:18 +08:00