Crate rivven_llm 

rivven-llm — LLM Provider Facade

Unified async API for Large Language Model providers.

This crate provides a provider-agnostic interface for:

• Chat completions — send messages, get structured responses
• Text embeddings — generate vector representations of text

Supported Providers

Provider	Feature	Chat	Embeddings
OpenAI	openai (default)	✓	✓
AWS Bedrock	bedrock	✓	✓

Quick Start

use rivven_llm::{LlmProvider, ChatRequest, ChatMessage, Role};
use rivven_llm::openai::OpenAiProvider;

let provider = OpenAiProvider::builder()
    .api_key("sk-...")
    .model("gpt-4o-mini")
    .build()?;

let request = ChatRequest::builder()
    .message(ChatMessage::user("Summarize this text: ..."))
    .temperature(0.3)
    .max_tokens(256)
    .build();

let response = provider.chat(&request).await?;
println!("{}", response.content());

Re-exports

pub use error::LlmError;

pub use error::LlmResult;

pub use provider::LlmProvider;

pub use types::ChatChoice;

pub use types::ChatMessage;

pub use types::ChatRequest;

pub use types::ChatRequestBuilder;

pub use types::ChatResponse;

pub use types::Embedding;

pub use types::EmbeddingRequest;

pub use types::EmbeddingRequestBuilder;

pub use types::EmbeddingResponse;

pub use types::EmbeddingUsage;

pub use types::FinishReason;

pub use types::Role;

pub use types::Usage;

Modules

error

Error types for rivven-llm

openai

OpenAI provider — chat completions and embeddings via the OpenAI REST API

provider

LLM provider trait — the core abstraction

types

Core types for LLM interactions