llama

package
v0.14.1 Latest Latest
Warning

This package is not in the latest version of its module.

Go to latest
Published: Aug 25, 2026 License: Apache-2.0 Imports: 8 Imported by: 0

Documentation

Overview

Package llama provides Meta's hosted Llama API through its documented OpenAI-compatible Chat Completions endpoint.

Index

Constants

View Source
const (
	DefaultBaseURL    = "https://api.llama.com/compat/v1"
	APIKeyEnvironment = "LLAMA_API_KEY" // #nosec G101 -- environment variable name, not a credential value
)

Variables

This section is empty.

Functions

func New

func New(selected model.Model, key auth.APIKey, options ...Option) (inference.Client, error)

New constructs a hosted Meta Llama Chat Completions client. An explicit key takes precedence; when it is empty, the documented LLAMA_API_KEY environment variable is used.

func NewCounter

func NewCounter(_ auth.APIKey) (contextcount.ContextCounter, error)

NewCounter reports that the hosted Llama compatibility API documents no exact input-token counting endpoint in this package's supported contract.

Types

type CounterSupportError

type CounterSupportError = llm.CounterSupportError

type Option

type Option = simple.Option

func WithHeader

func WithHeader(name, value string) Option

WithHeader adds a provider or gateway header to requests.

func WithReasoningEffort

func WithReasoningEffort(effort string) Option

WithReasoningEffort adds the documented OpenAI-compatible reasoning_effort request field for models that support reasoning controls.

func WithServiceTier

func WithServiceTier(tier string) Option

WithServiceTier adds the documented OpenAI-compatible service_tier field.

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL