Skip to main content

​
Overview

SimplismartLLMService generates chat completions using Simplismart’s OpenAI-compatible Chat Completions API. It extends Pipecat’s OpenAILLMService, so it supports the familiar streaming, settings, and metrics patterns.

Source Repository

Source code, examples, and issues for the Simplismart integration

Simplismart

Learn more about Simplismart’s inference platform

​
Installation

This is a community-maintained package distributed separately from pipecat-ai. Install from source: 
git clone https://github.com/simpli-smart/pipecat-simplismart.git
cd pipecat-simplismart
uv pip install -e .
See the source repository for the latest install instructions and any published package details.

​
Prerequisites

​
Simplismart Account Setup

Before using the Simplismart LLM service, you need a Simplismart account and an API key (a JWT bearer token). See Simplismart to get started.

​
Required Environment Variables

  • SIMPLISMART_API_KEY: Bearer JWT used to authenticate LLM requests.
  • SIMPLISMART_LLM_URL: OpenAI-compatible base URL (default https://api.simplismart.live).

​
Configuration

​
api_key
str
required
Simplismart API key (JWT bearer token).
​
base_url
str
default:"https://api.simplismart.live"
API base URL (no trailing path; the client appends /v1/...).
​
model
str
default:"None"
Deprecated convenience override for the model. Prefer setting the model via settings.
​
settings
SimplismartLLMService.Settings
default:"None"
Runtime-updatable LLM settings, merged into the service defaults. The default model is "google/gemma-4-31B-it".
SimplismartLLMService extends Pipecat’s OpenAILLMService, and its Settings inherit from BaseOpenAILLMService.Settings. See the source repository for the authoritative, up-to-date list of settings.

​
Usage

from pipecat_simplismart import SimplismartLLMService

llm = SimplismartLLMService(
    api_key="YOUR_KEY",
    base_url="https://api.simplismart.live",
    settings=SimplismartLLMService.Settings(model="google/gemma-4-31B-it"),
)

# ... add llm to your pipeline

​
Compatibility

Tested with Pipecat v1.1.0 (pipecat-ai>=0.0.86). Check the source repository for the latest tested version and changelog.