Skip to content

chore(genkit-tools/init-ai): Update usage guides to gemini3 #4231

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ssbushi wants to merge 1 commit into
base: main
Choose a base branch
from
Open

chore(genkit-tools/init-ai): Update usage guides to gemini3 #4231

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 12 additions & 5 deletions genkit-tools/cli/context/GENKIT.go.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,8 @@ NOTE: For the sake of brevity, the snippets below use the Google AI plugin, but

---

> Note: Gemini 3.0 models are currently in preview.

## Usage Scenarios

### Basic Inference (Text Generation)
Expand All @@ -45,7 +47,7 @@ func main() {
genkit.DefineFlow(g, "basicInferenceFlow",
func(ctx context.Context, topic string) (string, error) {
response, err := genkit.Generate(ctx, g,
ai.WithModelName("googleai/gemini-2.5-pro"),
ai.WithModelName("googleai/gemini-3-flash-preview"),
ai.WithPrompt("Write a short, creative paragraph about %s.", topic),
ai.WithConfig(&genai.GenerateContentConfig{
Temperature: genai.Ptr[float32](0.8),
Expand Down Expand Up @@ -139,7 +141,7 @@ func main() {
genkit.DefineFlow(g, "imageGenerationFlow",
func(ctx context.Context, prompt string) ([]string, error) {
response, err := genkit.Generate(ctx, g,
ai.WithModelName("vertexai/imagen-3.0-generate-001"),
ai.WithModelName("googleai/gemini-3-pro-image-preview"),
ai.WithPrompt("Generate an image of %s", prompt),
ai.WithConfig(&genai.GenerateImagesConfig{
NumberOfImages: 2,
Expand Down Expand Up @@ -194,11 +196,14 @@ You can can automate starting genkit using the following steps:

Here are suggested models to use for various task types. This is NOT an exhaustive list.

> Note: Gemini 3.0 models are currently in preview.

### Advanced Text/Reasoning

```
| Plugin | Recommended Model |
|------------------------------------------------------------|------------------------------------|
| github.com/firebase/genkit/go/plugins/googlegenai | gemini-3-pro-preview (Preview) |
| github.com/firebase/genkit/go/plugins/googlegenai | gemini-2.5-pro |
| github.com/firebase/genkit/go/plugins/compat_oai/openai | gpt-4o |
| github.com/firebase/genkit/go/plugins/compat_oai/deepseek | deepseek-reasoner |
Expand All @@ -210,6 +215,7 @@ Here are suggested models to use for various task types. This is NOT an exhausti
```
| Plugin | Recommended Model |
|------------------------------------------------------------|------------------------------------|
| github.com/firebase/genkit/go/plugins/googlegenai | gemini-3-flash-preview (Preview) |
| github.com/firebase/genkit/go/plugins/googlegenai | gemini-2.5-flash |
| github.com/firebase/genkit/go/plugins/compat_oai/openai | gpt-4o-mini |
| github.com/firebase/genkit/go/plugins/compat_oai/deepseek | deepseek-chat |
Expand All @@ -230,7 +236,8 @@ Here are suggested models to use for various task types. This is NOT an exhausti
```
| Plugin | Recommended Model | Input Modalities |
|------------------------------------------------------------|------------------------------------|-------------------|
| github.com/firebase/genkit/go/plugins/googlegenai | gemini-2.5-flash-image-preview | Text, Image |
| github.com/firebase/genkit/go/plugins/googlegenai | imagen-4.0-generate-preview-06-06 | Text |
| github.com/firebase/genkit/go/plugins/compat_oai/openai | gpt-image-1 | Text |
| github.com/firebase/genkit/go/plugins/googlegenai | gemini-3-pro-image-preview (Preview) | Text, Image |
| github.com/firebase/genkit/go/plugins/googlegenai | gemini-2.5-flash-image | Text, Image |
| github.com/firebase/genkit/go/plugins/googlegenai | imagen-4.0-generate-001 | Text |
| github.com/firebase/genkit/go/plugins/compat_oai/openai | gpt-image-1 | Text |
```
29 changes: 18 additions & 11 deletions genkit-tools/cli/context/GENKIT.js.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,16 +20,18 @@ NOTE: For the sake of brevity, the snippets below use the Google AI plugin, but

2. **Model Naming**: Always specify models using the model helper. Use string identifier if model helper is unavailable.

> Note: Gemini 3.0 models are currently in preview. Use 2.5 models for GA use-cases.

```ts
// PREFERRED: Using the model helper
const response = await ai.generate({
model: googleAI.model('gemini-2.5-pro'),
model: googleAI.model('gemini-3-flash-preview'),
// ...
});

// LESS PREFERRED: Full string identifier
const response = await ai.generate({
model: 'googleai/gemini-2.5-pro',
model: 'googleai/gemini-3-flash-preview',
// ...
});
```
Expand All @@ -51,7 +53,7 @@ export const basicInferenceFlow = ai.defineFlow(
},
async (topic) => {
const response = await ai.generate({
model: googleAI.model('gemini-2.5-pro'),
model: googleAI.model('gemini-3-flash-preview'),
prompt: `Write a short, creative paragraph about ${topic}.`,
config: { temperature: 0.8 },
});
Expand Down Expand Up @@ -170,7 +172,7 @@ export const imageGenerationFlow = ai.defineFlow(
},
async (prompt) => {
const response = await ai.generate({
model: googleAI.model('imagen-3.0-generate-002'),
model: googleAI.model('gemini-3-pro-image-preview'),
prompt,
output: { format: 'media' },
});
Expand Down Expand Up @@ -203,7 +205,7 @@ export const videoGenerationFlow = ai.defineFlow(
},
async (prompt) => {
let { operation } = await ai.generate({
model: googleAI.model('veo-3.0-generate-preview'),
model: googleAI.model('veo-3.1-generate-preview'),
prompt,
});

Expand Down Expand Up @@ -277,11 +279,14 @@ You can can automate starting genkit using the following steps:
Here are suggested models to use for various task types. This is NOT an
exhaustive list.

> Note: Gemini 3.0 models are currently in preview.

### Advanced Text/Reasoning

```
| Plugin | Recommended Model |
|------------------------------------|------------------------------------|
| @genkit-ai/google-genai | gemini-3-pro-preview (Preview) |
| @genkit-ai/google-genai | gemini-2.5-pro |
| @genkit-ai/compat-oai/openai | gpt-4o |
| @genkit-ai/compat-oai/deepseek | deepseek-reasoner |
Expand All @@ -293,6 +298,7 @@ exhaustive list.
```
| Plugin | Recommended Model |
|------------------------------------|------------------------------------|
| @genkit-ai/google-genai | gemini-3-flash-preview (Preview) |
| @genkit-ai/google-genai | gemini-2.5-flash |
| @genkit-ai/compat-oai/openai | gpt-4o-mini |
| @genkit-ai/compat-oai/deepseek | deepseek-chat |
Expand All @@ -311,17 +317,18 @@ exhaustive list.
### Image Generation

```
| Plugin | Recommended Model | Input Modalities |
|------------------------------------|------------------------------------|-------------------|
| @genkit-ai/google-genai | gemini-2.5-flash-image-preview | Text, Image |
| @genkit-ai/google-genai | imagen-4.0-generate-preview-06-06 | Text |
| @genkit-ai/compat-oai/openai | gpt-image-1 | Text |
| Plugin | Recommended Model | Input Modalities |
|------------------------------------|--------------------------------------|-------------------|
| @genkit-ai/google-genai | gemini-3-pro-image-preview (Preview) | Text, Image |
| @genkit-ai/google-genai | gemini-2.5-flash-image | Text, Image |
| @genkit-ai/google-genai | imagen-4.0-generate-001 | Text |
| @genkit-ai/compat-oai/openai | gpt-image-1 | Text |
```

### Video Generation

```
| Plugin | Recommended Model |
|------------------------------------|------------------------------------|
| @genkit-ai/google-genai | veo-3.0-generate-preview |
| @genkit-ai/google-genai | veo-3.1-generate-preview (Preview) |
```
Loading