red-agent-48266
05/15/2025, 5:25 PMtall-airline-16756
05/15/2025, 5:25 PMtall-airline-16756
05/15/2025, 5:26 PMpip install "livekit-agents[openai]~=1.0"
2. Set your DeepSeek API key in your .env
file:
DEEPSEEK_API_KEY=<your-deepseek-api-key>
3. Use the OpenAI plugin's with_deepseek
method to configure DeepSeek as your LLM:
from livekit.plugins import openai
deepseek_llm = openai.LLM.with_deepseek(
model="deepseek-chat", # this is DeepSeek-V3
temperature=0.7
)
You can also customize parameters like:
• model: The DeepSeek model to use (default is "deepseek-chat").
• temperature: Controls output randomness (0-2, default is 1.0).
• parallel_tool_calls: Enables multiple simultaneous tool calls.
• tool_choice: Controls how the model uses tools (auto/required/none).
If you need further assistance, feel free to ask!
Sources: DeepSeek LLM integration guide | LiveKit Docsred-agent-48266
05/15/2025, 5:28 PMtall-airline-16756
05/15/2025, 5:28 PM