Implement rate limiting in all API models by albertvillanova · Pull Request #1516 · huggingface/smolagents (original) (raw)

- AI CODE CREATION
  * GitHub CopilotWrite better code with AI
  * GitHub SparkBuild and deploy intelligent apps
  * GitHub ModelsManage and compare prompts
  * MCP RegistryNewIntegrate external tools

View all features

Pricing

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Appearance settings

Conversation

Implement rate limiting in all API models.

This PR implements rate limiting across all API model classes by adding calls to self._apply_rate_limit() before API requests are made.

Changes:

Implement RateLimiter class
Added RateLimiter class initialization in ApiModel.init
Implemented _apply_rate_limit() method in ApiModel
Added rate limiting calls in all API model implementations:
- LiteLLMModel
- InferenceClientModel
- OpenAIServerModel
- AzureOpenAIServerModel
- AmazonBedrockServerModel
- LiteLLMRouterModel
Added calls in both generate() and generate_stream() methods

Follow-up to:

Implement rate limit mechanism in ApiWebSearchTool #1508 (review)

It seems to me that common providers lit rate limits more in Requests Per Minute (RPM), cf Nebius, Anthropic...: maybe implement this per minute instead of per second?

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you! It would be nice to add a mention of this possibility to rate limit in the docs and add the arg in some of the examples!

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.Learn more about bidirectional Unicode characters