SambaNova LLM

​

Overview

​

Installation

uv add "pipecat-ai[sambanova]"

​

Prerequisites

​

SambaNova Account Setup

1. SambaNova Account: Sign up at SambaNova Cloud
2. API Key: Generate an API key from your account dashboard
3. Model Selection: Choose from available high-performance models

​

Required Environment Variables

• SAMBANOVA_API_KEY: Your SambaNova API key for authentication

​

Configuration

​

Settings

​

Usage

​

Basic Setup

import os
from pipecat.services.sambanova.llm import SambaNovaLLMService

llm = SambaNovaLLMService(
    api_key=os.getenv("SAMBANOVA_API_KEY"),
    settings=SambaNovaLLMService.Settings(model="Meta-Llama-3.3-70B-Instruct"),
)

​

With Custom Settings

from pipecat.services.sambanova.llm import SambaNovaLLMService

llm = SambaNovaLLMService(
    api_key=os.getenv("SAMBANOVA_API_KEY"),
    settings=SambaNovaLLMService.Settings(
        model="Meta-Llama-3.3-70B-Instruct",
        temperature=0.7,
        top_p=0.9,
        max_tokens=1024,
    ),
)

​

Notes

• SambaNova does not support the developer message role. Messages with this role are sent as user messages.
• A tool call that arrives with empty arguments (rather than {}) is skipped, so its function handler doesn’t run. When that call is the last one in the response, none of the response’s tool calls run.
• Token usage reporting includes cache_read_input_tokens and reasoning_tokens when available from the provider.
• SambaNova is known for high-throughput inference on large language models.