Skip to content

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

Update Perplexity example in documentation (#1623)

Andy Brombergf8ca49d8df36
diff --git a/docs/concepts/llms.mdx b/docs/concepts/llms.mdx
index 5211e6652..798fea726 100644
--- a/docs/concepts/llms.mdx
+++ b/docs/concepts/llms.mdx
@@ -310,8 +310,8 @@ These are examples of how to configure LLMs for your agent.
from crewai import LLM
llm = LLM(
- model="perplexity/mistral-7b-instruct",
- base_url="https://api.perplexity.ai/v1",
+ model="llama-3.1-sonar-large-128k-online",
+ base_url="https://api.perplexity.ai/",
api_key="your-api-key-here"
)
agent = Agent(llm=llm, ...)
@@ -400,4 +400,4 @@ This is particularly useful when working with OpenAI-compatible APIs or when you
- **API Errors**: Check your API key, network connection, and rate limits.
- **Unexpected Outputs**: Refine your prompts and adjust temperature or top_p.
- **Performance Issues**: Consider using a more powerful model or optimizing your queries.
-- **Timeout Errors**: Increase the `timeout` parameter or optimize your input.
\ No newline at end of file
+- **Timeout Errors**: Increase the `timeout` parameter or optimize your input.