awesome-bookmarks/goose
3
0
Fork 0
mirror of https://github.com/block/goose.git synced 2026-07-17 12:56:20 +02:00
Code Issues Packages Projects Releases Wiki Activity

feat: update Groq models for better tool calling support (#3676)

Browse Source 
Co-authored-by: kenneth.kimani <kenneth.kimani@savannahinformatics.com>
Co-authored-by: Douwe Osinga <douwe@block.xyz>
This commit is contained in:
Kenneth Mungai
2025-07-29 17:33:21 +03:00
committed by GitHub
parent 4ac5fe4f8d
commit 9d996c3957
3 changed files with 48 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
crates/goose/src/model.rs
+6 -1
View File
@@ -28,9 +28,14 @@ static MODEL_SPECIFIC_LIMITS: Lazy<HashMap<&'static str, usize>> = Lazy::new(||
map.insert("llama3.3", 128_000);
// x.ai Grok models, https://docs.x.ai/docs/overview
map.insert("grok", 131_072);
// Groq models, https://console.groq.com/docs/models
map.insert("gemma2-9b", 8_192);
map.insert("kimi-k2", 131_072);
map.insert("qwen3-32b", 131_072);
map.insert("grok-3", 131_072);
map.insert("grok-4", 256_000); // 256K
map.insert("qwen3-coder", 262_144); // 262K
map
crates/goose/src/providers/groq.rs
+7 -2
View File
@@ -13,8 +13,13 @@ use std::time::Duration;
use url::Url;
pub const GROQ_API_HOST: &str = "https://api.groq.com";
pub const GROQ_DEFAULT_MODEL: &str = "llama-3.3-70b-versatile";
pub const GROQ_KNOWN_MODELS: &[&str] = &["gemma2-9b-it", "llama-3.3-70b-versatile"];
pub const GROQ_DEFAULT_MODEL: &str = "moonshotai/kimi-k2-instruct";
pub const GROQ_KNOWN_MODELS: &[&str] = &[
"gemma2-9b-it",
"llama-3.3-70b-versatile",
"moonshotai/kimi-k2-instruct",
"qwen/qwen3-32b",
];
pub const GROQ_DOC_URL: &str = "https://console.groq.com/docs/models";
documentation/docs/getting-started/providers.md
+35
View File
@@ -247,6 +247,41 @@ These free options are a great way to get started with Goose and explore its cap
:::
### Groq
Groq provides free access to open source models with high-speed inference. To use Groq with Goose, you need an API key from [Groq Console](https://console.groq.com/keys).
Groq offers several open source models that support tool calling:
- **moonshotai/kimi-k2-instruct** - Mixture-of-Experts model with 1 trillion parameters, optimized for agentic intelligence and tool use
- **qwen/qwen3-32b** - 32.8 billion parameter model with advanced reasoning and multilingual capabilities
- **gemma2-9b-it** - Google's Gemma 2 model with instruction tuning
- **llama-3.3-70b-versatile** - Meta's Llama 3.3 model for versatile applications
To set up Groq with Goose, follow these steps:
<Tabs groupId="interface">
<TabItem value="ui" label="Goose Desktop" default>
**To update your LLM provider and API key:**
1. Click the <PanelLeft className="inline" size={16} /> button in the top-left to open the sidebar.
2. Click the `Settings` button on the sidebar.
3. Click the `Models` tab.
4. Click `Configure Providers`
5. Choose `Groq` as provider from the list.
6. Click `Configure`, enter your API key, and click `Submit`.
</TabItem>
<TabItem value="cli" label="Goose CLI">
1. Run:
```sh
goose configure
```
2. Select `Configure Providers` from the menu.
3. Follow the prompts to choose `Groq` as the provider.
4. Enter your API key when prompted.
5. Enter the Groq model of your choice (e.g., `moonshotai/kimi-k2-instruct`).
</TabItem>
</Tabs>
### Google Gemini
Google Gemini provides a free tier. To start using the Gemini API with Goose, you need an API Key from [Google AI studio](https://aistudio.google.com/app/apikey).