genai - Multi-AI Providers Library for Rust

Currently supports natively: OpenAI, Anthropic, Gemini, XAI/Grok, Ollama, Groq, DeepSeek (deepseek.com & Groq), Cohere (more to come)

Also, allow custom URL with ServiceTargetResolver (see examples/c06-target-resolver.rs)

Provides a common and ergonomic single API to many generative AI providers, such as Anthropic, OpenAI, Gemini, xAI, Ollama, Groq, and more.

v0.3.0 - Released 2025-05-08

What's new:

• Gemini Thinking Budget support ReasoningEffort::Budget(num)
• Gemini-zero, -low, -medium, and -high suffixes that set the corresponding budget (0, 1k, 8k, 24k)
• When set, ReasoningEffort::Low, ... will map to their corresponding budget 1k, 8k, 24k

API-CHANGES (minors) - ReasoningEffort has now and additional Budget(num) variant - ModelIden::with_name_or_clone has been deprecated for ModelInden::from_option_name(Option<String>)

Check CHANGELOG for more info

v0.2.0 - Released 2025-04-16

Here are some of the api change. Check CHANGELOG for more info

API-CHANGES

• chat::MetaUsage has been renamed to chat::Usage
• Usage.input_tokens to Usage.prompt_tokens
• Usage.prompt_tokens to Usage.completion_tokens
• ChatMessage now takes an additional property, options: MessageOptions with and optional cache_control (CacheControl::Ephemeral)
• Now client.resolve_service_target(model) is ASYNC, so, client.resolve_service_target(model).await
• Note: At this point, we still cannot AsyncFn... traits as its support is not complete in stable (as of rust 1.86), but Auth Resolver can be async now with some Pin/Box/Future type anotation.

Thanks

• @una-spirito for gemini ReasoningEffort::Budget support.
• @jBernavaPrah For adding tracing (it was long overdue). PR #45
• @GustavoWidman for the intial gemini tool/function support!! PR #41
• @AdamStrojek for initial image support PR #36
• @semtexzv for stop_sequences Anthropic support PR #34
• @omarshehab221 for de/serialize on structs PR #19
• @tusharmath for make webc::Error PR #12
• @giangndm for make stream is send PR #10
• @stargazing-dino for PR #2 - implement Groq completions

Usage examples

• Check out AIPACK, which wraps this genai library into an agentic runtime to run, build, and share AI Agent Packs. See pro@coder for a simple example of how I use AI PACK/genai for production coding.

Note: Feel free to send me a short description and link to your application or library using genai.

Key Features

• Native Multi-AI Provider/Model: OpenAI, Anthropic, Gemini, Ollama, Groq, xAI, DeepSeek (Direct chat and stream) (see examples/c00-readme.rs)
• DeepSeekR1 support, with reasoning_content (and stream support) + DeepSeek Groq and Ollama support (and reasoning_content normalization)
• Image Analysis (for OpenAI, Gemini flash-2, Anthropic) (see examples/c07-image.rs)
• Custom Auth/API Key (see examples/c02-auth.rs)
• Model Alias (see examples/c05-model-names.rs)
• Custom Endpoint, Auth, and Model Identifier (see examples/c06-target-resolver.rs)

Examples | Thanks | Library Focus | Changelog | Provider Mapping: ChatOptions | Usage

Examples

examples/c00-readme.rs

//! Base examples demonstrating the core capabilities of genai

use genai::chat::printer::{print_chat_stream, PrintChatStreamOptions};
use genai::chat::{ChatMessage, ChatRequest};
use genai::Client;

const MODEL_OPENAI: &str = "gpt-4o-mini"; // o1-mini, gpt-4o-mini
const MODEL_ANTHROPIC: &str = "claude-3-haiku-20240307";
const MODEL_COHERE: &str = "command-light";
const MODEL_GEMINI: &str = "gemini-2.0-flash";
const MODEL_GROQ: &str = "llama3-8b-8192";
const MODEL_OLLAMA: &str = "gemma:2b"; // sh: `ollama pull gemma:2b`
const MODEL_XAI: &str = "grok-beta";
const MODEL_DEEPSEEK: &str = "deepseek-chat";

// NOTE: These are the default environment keys for each AI Adapter Type.
//       They can be customized; see `examples/c02-auth.rs`
const MODEL_AND_KEY_ENV_NAME_LIST: &[(&str, &str)] = &[
	// -- De/activate models/providers
	(MODEL_OPENAI, "OPENAI_API_KEY"),
	(MODEL_ANTHROPIC, "ANTHROPIC_API_KEY"),
	(MODEL_COHERE, "COHERE_API_KEY"),
	(MODEL_GEMINI, "GEMINI_API_KEY"),
	(MODEL_GROQ, "GROQ_API_KEY"),
	(MODEL_XAI, "XAI_API_KEY"),
	(MODEL_DEEPSEEK, "DEEPSEEK_API_KEY"),
	(MODEL_OLLAMA, ""),
];

// NOTE: Model to AdapterKind (AI Provider) type mapping rule
//  - starts_with "gpt"      -> OpenAI
//  - starts_with "claude"   -> Anthropic
//  - starts_with "command"  -> Cohere
//  - starts_with "gemini"   -> Gemini
//  - model in Groq models   -> Groq
//  - For anything else      -> Ollama
//
// This can be customized; see `examples/c03-mapper.rs`

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
	let question = "Why is the sky red?";

	let chat_req = ChatRequest::new(vec![
		// -- Messages (de/activate to see the differences)
		ChatMessage::system("Answer in one sentence"),
		ChatMessage::user(question),
	]);

	let client = Client::default();

	let print_options = PrintChatStreamOptions::from_print_events(false);

	for (model, env_name) in MODEL_AND_KEY_ENV_NAME_LIST {
		// Skip if the environment name is not set
		if !env_name.is_empty() && std::env::var(env_name).is_err() {
			println!("===== Skipping model: {model} (env var not set: {env_name})");
			continue;
		}

		let adapter_kind = client.resolve_service_target(model)?.model.adapter_kind;

		println!("\n===== MODEL: {model} ({adapter_kind}) =====");

		println!("\n--- Question:\n{question}");

		println!("\n--- Answer:");
		let chat_res = client.exec_chat(model, chat_req.clone(), None).await?;
		println!("{}", chat_res.content_text_as_str().unwrap_or("NO ANSWER"));

		println!("\n--- Answer: (streaming)");
		let chat_res = client.exec_chat_stream(model, chat_req.clone(), None).await?;
		print_chat_stream(chat_res, Some(&print_options)).await?;

		println!();
	}

	Ok(())
}

More Examples

• examples/c00-readme.rs - Quick overview code with multiple providers and streaming.
• examples/c01-conv.rs - Shows how to build a conversation flow.
• examples/c02-auth.rs - Demonstrates how to provide a custom AuthResolver to provide auth data (i.e., for api_key) per adapter kind.
• examples/c03-mapper.rs - Demonstrates how to provide a custom AdapterKindResolver to customize the "model name" to "adapter kind" mapping.
• examples/c04-chat-options.rs - Demonstrates how to set chat generation options such as temperature and max_tokens at the client level (for all requests) and per request level.
• examples/c05-model-names.rs - Shows how to get model names per AdapterKind.
• examples/c06-target-resolver.rs - For custom Auth, Endpoint, and Model.
• examples/c07-image.rs - Image Analysis support

• genai ModelMapper code demo (v0.1.7)

• genai introduction (v0.1.0)

• genai live coding, code design, & best practices

  • Adding Gemini Structured Output (vid-0060)
  • Adding OpenAI Structured Output (vid-0059)
  • Splitting the json value extension trait to its own public crate value-ext value-ext
  • (part 1/3) Module, Error, constructors/builders
  • (part 2/3) Extension Traits, Project Files, Versioning
  • (part 3/3) When to Async? Project Files, Versioning strategy

Library Focus:

• Focuses on standardizing chat completion APIs across major AI services.

• Native implementation, meaning no per-service SDKs.

  • Reason: While there are some variations between all of the various APIs, they all follow the same pattern and high-level flow and constructs. Managing the differences at a lower layer is actually simpler and more cumulative across services than doing SDKs gymnastics.

• Prioritizes ergonomics and commonality, with depth being secondary. (If you require a complete client API, consider using async-openai and ollama-rs; they are both excellent and easy to use.)

• Initially, this library will mostly focus on text chat API (images, or even function calling in the first stage).

ChatOptions

• (1) - OpenAI compatibles notes
  • Models: OpenAI, DeepSeek, Groq, Ollama, xAI

Property	OpenAI Compatibles (*1)	Anthropic	Gemini generationConfig.	Cohere
temperature	temperature	temperature	temperature	temperature
max_tokens	max_tokens	max_tokens (default 1024)	maxOutputTokens	max_tokens
top_p	top_p	top_p	topP	p

Usage

Property	OpenAI Compatibles (1)	Anthropic usage.	Gemini usageMetadata.	Cohere meta.tokens.
prompt_tokens	prompt_tokens	input_tokens (added)	promptTokenCount (2)	input_tokens
completion_tokens	completion_tokens	output_tokens (added)	candidatesTokenCount (2)	output_tokens
total_tokens	total_tokens	(computed)	totalTokenCount (2)	(computed)
prompt_tokens_details	prompt_tokens_details	cached/cache_creation	N/A for now	N/A for now
completion_tokens_details	completion_tokens_details	N/A for now	N/A for now	N/A for now

• (1) - OpenAI compatibles notes

  • Models: OpenAI, DeepSeek, Groq, Ollama, xAI
  • For Groq, the property x_groq.usage.
  • At this point, Ollama does not emit input/output tokens when streaming due to the Ollama OpenAI compatibility layer limitation. (see ollama #4448 - Streaming Chat Completion via OpenAI API should support stream option to include Usage)
  • prompt_tokens_details and completion_tokens_details will have the value sent by the compatible provider (or None)

• (2): Gemini tokens

  • Right now, with Gemini Stream API, it's not really clear if the usage for each event is cumulative or needs to be added. Currently, it appears to be cumulative (i.e., the last message has the total amount of input, output, and total tokens), so that will be the assumption. See possible tweet answer for more info.

Notes on Possible Direction

• Will add more data on ChatResponse and ChatStream, especially metadata about usage.
• Add vision/image support to chat messages and responses.
• Add function calling support to chat messages and responses.
• Add embed and embed_batch
• Add the AWS Bedrock variants (e.g., Mistral, and Anthropic). Most of the work will be on "interesting" token signature scheme (without having to drag big SDKs, might be below feature).
• Add the Google VertexAI variants.
• (might) add the Azure OpenAI variant (not sure yet).

Links

• crates.io: crates.io/crates/genai
• GitHub: github.com/jeremychone/rust-genai
• Sponsored by BriteSnow (Jeremy Chone's consulting company)