Module completion 

Provider-agnostic completion and chat abstractions.

This module contains the low-level request and response types used by provider implementations, plus the high-level traits most callers use through Agent:

• Prompt sends one user prompt and returns assistant text.
• Chat sends a prompt with existing history and returns assistant text.
• TypedPrompt requests structured output and deserializes it into a Rust type.
• Completion exposes a request builder for call-site overrides.
• CompletionModel is the provider-facing trait implemented by completion models.

CompletionRequest is Rig’s canonical request representation. Provider modules translate it into provider-specific request bodies and convert responses back into CompletionResponse.

Example

use rig_core::{
    client::{CompletionClient, ProviderClient},
    completion::Prompt,
    providers::openai,
};

let client = openai::Client::from_env()?;
let agent = client
    .agent(openai::GPT_5_2)
    .preamble("Answer concisely.")
    .build();

let answer = agent.prompt("What is Rig?").await?;
println!("{answer}");

Modules

message

request

Completion request, response, and provider trait definitions.

Structs

CompletionRequest

Struct representing a general completion request that can be sent to a completion model provider.

CompletionRequestBuilder

Builder struct for constructing a completion request.

CompletionResponse

General completion response struct that contains the high-level completion choice and the raw response. The completion choice contains one or more assistant content.

Document

ProviderToolDefinition

Provider-native tool definition.

ToolDefinition

Usage

Struct representing the token usage for a completion request. If tokens used are 0, then the provider failed to supply token usage metrics.

Enums

AssistantContent

Describes responses from a provider which is either text or a tool call.

CompletionError

Message

A provider-agnostic chat message.

MessageError

Error type to represent issues with converting messages to and from specific provider messages.

PromptError

Prompt errors

StructuredOutputError

Errors that can occur when using typed structured output via TypedPrompt::prompt_typed.

Traits

Chat

Trait defining a high-level LLM chat interface (i.e.: prompt and chat history in, response out).

Completion

Trait defining a low-level LLM completion interface

CompletionModel

Trait defining a completion model that can be used to generate completion responses. This trait is meant to be implemented by the user to define a custom completion model, either from a third party provider (e.g.: OpenAI) or a local model.

GetTokenUsage

A trait for grabbing the token usage of a completion response.

Prompt

Trait defining a high-level LLM simple prompt interface (i.e.: prompt in, response out).

TypedPrompt

Trait defining a high-level typed prompt interface for structured output.