Fix llm client retry - Githubissues

getzep / graphiti

Build and query dynamic, temporally-aware Knowledge Graphs

https://help.getzep.com/graphiti

Apache License 2.0

1.36k stars 72 forks source link

Fix llm client retry #102

Closed danielchalef closed 2 months ago

danielchalef commented 2 months ago

:rocket:	This description was created by Ellipsis for commit 461780cba3a62329f2fc711c63d3af626e9d6a57

Summary:

This PR introduces RateLimitError and updates LLM client retry logic to handle rate limit errors using exponential backoff.

Key points:

Introduces RateLimitError in graphiti_core/llm_client/errors.py.
Updates graphiti_core/llm_client/__init__.py to export RateLimitError.
Modifies graphiti_core/llm_client/client.py to retry on RateLimitError using tenacity with exponential backoff.
Updates graphiti_core/llm_client/anthropic_client.py, groq_client.py, and openai_client.py to raise RateLimitError on rate limit exceptions.

Generated with :heart: by ellipsis.dev