Package index • rlmstudio

Chat & Inference

Interact with loaded LLMs to generate text and process batches of prompts.

lms_chat(): Chat Completion with LM Studio
lms_chat_batch(): Batch Chat Completion with LM Studio
lms_chat_native(): Chat Completion via Native API
lms_chat_openai(): Chat Completion via OpenAI Compatibility API
lms_chat_openresponses(): Chat Completion via OpenResponses API
lms_score_expected(): Calculate Expected Scores and Uncertainty from Logprobs

Model Management

Discover, download, load, and manage local models.

list_models(): List available models
lms_download(): Download a model via REST API
lms_download_status(): Get the status of a download job
lms_load(): Load a model via REST API
lms_unload(): Unload a model from memory via REST API
lms_unload_all(): Unload all models from memory

Local Server Management

Control the LM Studio local REST API server.

lms_server_start(): Start the LM Studio local server
lms_server_stop(): Stop the LM Studio local server
lms_server_status(): Check the status of the LM Studio server

Headless Daemon Management

Manage the background llmster daemon required for headless environments (e.g., remote servers, Docker).

lms_daemon_start(): Start the LM Studio headless daemon
lms_daemon_stop(): Stop the LM Studio headless daemon
lms_daemon_status(): Check the global status of LM Studio
with_lms_daemon(): Run code with the LM Studio daemon active

Setup & Configuration

Install, locate, and verify the LM Studio CLI installation.

install_lmstudio(): Help the user install or update LM Studio
has_lms(): Check if LM Studio CLI is installed
check_lms_version(): Check if the installed LM Studio CLI meets the minimum requirement
lms_path(): Get the absolute path to the LMS executable