Genkit Go
Genkit Go is an AI SDK for Go that provides generation, structured output, streaming, tool calling, prompts, and flows with a unified interface across model providers.
Hello World
package main
import (
"context"
"fmt"
"log"
"net/http"
"github.com/genkit-ai/genkit/go/ai"
"github.com/genkit-ai/genkit/go/genkit"
"github.com/genkit-ai/genkit/go/plugins/googlegenai"
"github.com/genkit-ai/genkit/go/plugins/server"
)
func main() {
ctx := context.Background()
g := genkit.Init(ctx, genkit.WithPlugins(&googlegenai.GoogleAI{}))
genkit.DefineFlow(g, "jokeFlow", func(ctx context.Context, topic string) (string, error) {
return genkit.GenerateText(ctx, g,
ai.WithModelName("googleai/gemini-flash-latest"),
ai.WithPrompt("Tell me a joke about %s", topic),
)
})
mux := http.NewServeMux()
for _, f := range genkit.ListFlows(g) {
mux.HandleFunc("POST /"+f.Name(), genkit.Handler(f))
}
log.Fatal(server.Start(ctx, "127.0.0.1:8080", mux))
}
Core Features
Load the appropriate reference based on what you need:
| Feature |
Reference |
When to load |
| Initialization |
references/getting-started.md |
Setting up genkit.Init, plugins, the *Genkit instance pattern |
| Generation |
references/generation.md |
Generate, GenerateText, GenerateData, streaming, output formats |
| Prompts |
references/prompts.md |
DefinePrompt, DefineDataPrompt, .prompt files, schemas |
| Tools |
references/tools.md |
DefineTool, tool interrupts, RestartWith/RespondWith |
| Flows & HTTP |
references/flows-and-http.md |
DefineFlow, DefineStreamingFlow, genkit.Handler, HTTP serving |
| Model Providers |
references/providers.md |
Google AI, Vertex AI, Anthropic, OpenAI-compatible, Ollama setup |
Genkit CLI
Check if installed: genkit --version
Installation:
curl -sL cli.genkit.dev | bash
Key commands:
# Start app with Developer UI (tracing, flow testing) at http://localhost:4000
genkit start -- go run .
genkit start -o -- go run . # also opens browser
# Run a flow directly from the CLI
genkit flow:run myFlow '{"data": "input"}'
genkit flow:run myFlow '{"data": "input"}' --stream # with streaming
genkit flow:run myFlow '{"data": "input"}' --wait # wait for completion
# Look up Genkit documentation
genkit docs:search "streaming" go
genkit docs:list go
genkit docs:read go/flows.md
See references/getting-started.md for full CLI and Developer UI details.
Key Guidance
- Pass
g explicitly. The *Genkit instance returned by genkit.Init is the central registry. Pass it to all Genkit functions rather than storing it as a global. This is a core pattern throughout the SDK.
- Wrap AI logic in flows. Flows give you tracing, observability, HTTP deployment via
genkit.Handler, and the ability to test from the Developer UI and CLI. Any generation call worth keeping should live in a flow.
- Use
jsonschema:"description=..." struct tags on output types. The model uses these descriptions to understand what each field should contain. Without them, structured output quality drops significantly.
- Write good tool descriptions. The model decides which tools to call based on their description string. Vague descriptions lead to missed or incorrect tool calls.
- Use
.prompt files for complex prompts. They separate prompt content from Go code, support Handlebars templating, and can be iterated on without recompilation. Code-defined prompts are better for simple, single-line cases.
- Look up the latest model IDs. Model names change frequently. Check provider documentation for current model IDs rather than relying on hardcoded names. See references/providers.md.
1---2name: developing-genkit-go3description: Develop AI-powered applications using Genkit in Go. Use when the user asks to build AI features, agents, flows, or tools in Go using Genkit, or when working with Genkit Go code involving generation, prompts, streaming, tool calling, or model providers.4---5
6# Genkit Go
7
8Genkit Go is an AI SDK for Go that provides generation, structured output, streaming, tool calling, prompts, and flows with a unified interface across model providers.
9
10## Hello World
11
12```go
13package main
14
15import (
16 "context"
17 "fmt"
18 "log"
19 "net/http"
20
21 "github.com/genkit-ai/genkit/go/ai"
22 "github.com/genkit-ai/genkit/go/genkit"
23 "github.com/genkit-ai/genkit/go/plugins/googlegenai"
24 "github.com/genkit-ai/genkit/go/plugins/server"
25)
26
27func main() {
28 ctx := context.Background()
29 g := genkit.Init(ctx, genkit.WithPlugins(&googlegenai.GoogleAI{}))
30
31 genkit.DefineFlow(g, "jokeFlow", func(ctx context.Context, topic string) (string, error) {
32 return genkit.GenerateText(ctx, g,
33 ai.WithModelName("googleai/gemini-flash-latest"),
34 ai.WithPrompt("Tell me a joke about %s", topic),
35 )
36 })
37
38 mux := http.NewServeMux()
39 for _, f := range genkit.ListFlows(g) {
40 mux.HandleFunc("POST /"+f.Name(), genkit.Handler(f))
41 }
42 log.Fatal(server.Start(ctx, "127.0.0.1:8080", mux))
43}
44```
45
46## Core Features
47
48Load the appropriate reference based on what you need:
49
50| Feature | Reference | When to load |
51| --- | --- | --- |
52| Initialization | [references/getting-started.md](references/getting-started.md) | Setting up `genkit.Init`, plugins, the `*Genkit` instance pattern |
53| Generation | [references/generation.md](references/generation.md) | `Generate`, `GenerateText`, `GenerateData`, streaming, output formats |
54| Prompts | [references/prompts.md](references/prompts.md) | `DefinePrompt`, `DefineDataPrompt`, `.prompt` files, schemas |
55| Tools | [references/tools.md](references/tools.md) | `DefineTool`, tool interrupts, `RestartWith`/`RespondWith` |
56| Flows & HTTP | [references/flows-and-http.md](references/flows-and-http.md) | `DefineFlow`, `DefineStreamingFlow`, `genkit.Handler`, HTTP serving |
57| Model Providers | [references/providers.md](references/providers.md) | Google AI, Vertex AI, Anthropic, OpenAI-compatible, Ollama setup |
58
59## Genkit CLI
60
61Check if installed: `genkit --version`
62
63**Installation:**
64```bash
65curl -sL cli.genkit.dev | bash
66```
67
68**Key commands:**
69
70```bash
71# Start app with Developer UI (tracing, flow testing) at http://localhost:4000
72genkit start -- go run .
73genkit start -o -- go run . # also opens browser
74
75# Run a flow directly from the CLI
76genkit flow:run myFlow '{"data": "input"}'
77genkit flow:run myFlow '{"data": "input"}' --stream # with streaming
78genkit flow:run myFlow '{"data": "input"}' --wait # wait for completion
79
80# Look up Genkit documentation
81genkit docs:search "streaming" go
82genkit docs:list go
83genkit docs:read go/flows.md
84```
85
86See [references/getting-started.md](references/getting-started.md) for full CLI and Developer UI details.
87
88## Key Guidance
89
90- **Pass `g` explicitly.** The `*Genkit` instance returned by `genkit.Init` is the central registry. Pass it to all Genkit functions rather than storing it as a global. This is a core pattern throughout the SDK.
91- **Wrap AI logic in flows.** Flows give you tracing, observability, HTTP deployment via `genkit.Handler`, and the ability to test from the Developer UI and CLI. Any generation call worth keeping should live in a flow.
92- **Use `jsonschema:"description=..."` struct tags on output types.** The model uses these descriptions to understand what each field should contain. Without them, structured output quality drops significantly.
93- **Write good tool descriptions.** The model decides which tools to call based on their description string. Vague descriptions lead to missed or incorrect tool calls.
94- **Use `.prompt` files for complex prompts.** They separate prompt content from Go code, support Handlebars templating, and can be iterated on without recompilation. Code-defined prompts are better for simple, single-line cases.
95- **Look up the latest model IDs.** Model names change frequently. Check provider documentation for current model IDs rather than relying on hardcoded names. See [references/providers.md](references/providers.md).
aiskillstore