OpenAI RateLimitError

[sudhakarsingh27]

It wasn't possible to run this tutorial https://help.getzep.com/graphiti/graphiti/lang-graph-agent consistently without adding this rate limiting API.

---

Important

Adds rate limiting handling with exponential backoff to generate_response() in openai_client.py.

• Behavior:
  • Adds rate limiting handling in generate_response() in openai_client.py using exponential backoff.
  • Implements _parse_retry_after() to extract retry time from error messages or fallback to exponential backoff.
  • Logs rate limit hits and retry attempts.
• Error Handling:
  • Catches RateLimitError and retries with delay.
  • Continues to raise RefusalError without retry.
  • Handles other OpenAI errors by deferring to OpenAI's client retry logic.

^{This description was created by for 1511121. It will automatically update as commits are pushed.}

[github-actions]

Thank you for your submission, we really appreciate it. Like many open-source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution. You can sign the CLA by just posting a Pull Request Comment same as the below format.

---

I have read the CLA Document and I hereby sign the CLA

---

_{You can retrigger this bot by commenting recheck in this Pull Request. Posted by the CLA Assistant Lite bot.}

[ellipsis-dev]

❌ Changes requested. Reviewed everything up to 1511121 in 1 minute and 43 seconds

More details

• Looked at 48 lines of code in 1 files
• Skipped 0 files when reviewing.
• Skipped posting 3 drafted comments based on config settings.

1. graphiti_core/llm_client/openai_client.py:149

• Draft comment:
  max_delay is not defined. Define max_delay or replace it with a defined variable.
• Reason this comment was not posted:
  Marked as duplicate.

2. graphiti_core/llm_client/openai_client.py:162

• Draft comment:
  Convert RateLimitError to string to extract retry time. Use str(e) in _parse_retry_after.
• Reason this comment was not posted:
  Marked as duplicate.

3. graphiti_core/llm_client/openai_client.py:139

• Draft comment:
  Define _parse_retry_after as a separate function or a static method for better readability and reusability.
• Reason this comment was not posted:
  Confidence changes required: 80%
  The _parse_retry_after function is defined inside the generate_response method, which is not idiomatic in Python. It should be defined as a separate method or a static method if it doesn't use any instance variables.

Workflow ID: wflow_vEEQ61N6ZkfozhXO

---

Want Ellipsis to fix these issues? Tag @ellipsis-dev in a comment. You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet mode, and more.

[ellipsis-dev]

max_delay is not defined. This will cause a NameError. Define max_delay or replace it with a valid variable.

[ellipsis-dev]

_parse_retry_after expects a string, but e is an exception object. Pass str(e) instead.