docs: Gemini thinking budget configuration (#32002)

Release Notes: - N/A

Oleksiy Syvokon committed 1 year ago

Commit 1bc052d1 parent 29cb95a1 file · +10 −4Browse files

Showing the changes to docs/src (1 of 1 file). Show all

Unified · Split

 #### Custom Models {#google-ai-custom-models}
-By default, Zed will use `stable` versions of models, but you can use specific versions of models, including [experimental models](https://ai.google.dev/gemini-api/docs/models/experimental-models), with the Google AI provider by adding the following to your Zed `settings.json`:
+By default, Zed will use `stable` versions of models, but you can use specific versions of models, including [experimental models](https://ai.google.dev/gemini-api/docs/models/experimental-models). You can configure a model to use [thinking mode](https://ai.google.dev/gemini-api/docs/thinking) (if it supports it) by adding a `mode` configuration to your model. This is useful for controlling reasoning token usage and response speed. If not specified, Gemini will automatically choose the thinking budget.
+Here is an example of a custom Google AI model you could add to your Zed `settings.json`:
 ```json
 {
     "google": {
       "available_models": [
         {
-          "name": "gemini-1.5-flash-latest",
+          "name": "gemini-2.5-flash-preview-05-20",
-          "display_name": "Gemini 1.5 Flash (Latest)",
+          "display_name": "Gemini 2.5 Flash (Thinking)",
-          "max_tokens": 1000000
+          "max_tokens": 1000000,
+          "mode": {
+            "type": "thinking",
+            "budget_tokens": 24000
+          }
         }
       ]
     }