minibox-llm (0.19.0)

Published 2026-05-31 14:31:46 -05:00 by joe

Set up this registry in the Cargo configuration file (for example ~/.cargo/config.toml):

[registry]
default = "gitea"

[registries.gitea]
index = "sparse+" # Sparse index
# index = "" # Git

[net]
git-fetch-with-cli = true

To install the package using Cargo, run the following command:

cargo add minibox-llm@0.19.0

For more information on the Cargo registry, see the documentation.

minibox-llm

Multi-provider LLM client with structured output support and fallback chains.

Provider	Feature	Models
Claude (Anthropic)	`anthropic`	claude-opus-4-6, claude-sonnet-4-6, claude-haiku-4-5
OpenAI	`openai`	gpt-4-turbo, gpt-4o, etc.
Google Gemini	`gemini`	gemini-2.0-flash, etc.

use minibox_llm::LlmClient;

let client = LlmClient::anthropic("your-api-key");
let response = client.complete("Explain containers").await?;

Use with_schema() to define JSON schemas for responses, enabling type-safe extraction:

let schema = json!({"type": "object", "properties": {...}});
let response = client.with_schema(schema).complete(prompt).await?;

Stack providers for automatic fallback:

let chain = vec![
    Box::new(LlmClient::anthropic(key1)),
    Box::new(LlmClient::openai(key2)),
];

Default features include all three providers. Disable individually as needed.

Details

Cargo

2026-05-31 14:31:46 -05:00

MIT OR Apache-2.0

35 KiB

Assets (1)

minibox-llm-0.19.0.crate 35 KiB

Versions (1) View all

0.19.0

2026-05-31