llamacloud-demo/examples/report_generati...

Question

hey @Logan M so I am doing this tutorial:https://github.com/run-llama/llamacloud-demo/blob/main/examples/report_generation/report_generation.ipynbwhen I get to the cell to do this:ret = await agent.run( input="Tell me about the top-level assets and liabilities for Tesla in 2021, and compare it against those of Apple in 2021. Which company is doing better?"
)I kept getting too many tokens for gpt-4o. Then when I attempt to repeat the steps I get:Running step prepare_chat_history
Step prepare_chat_history produced event InputEvent
Running step handle_llm_input
Step handle_llm_input produced event ReportGenerationEvent
Running step generate_report
Step generate_report produced event StopEvent

cmosguy · Answer

I keep getting RateLimitError: Error code: 429 - {'error': {'message': 'Request too large for gpt-4o in organization org-T0X9LWcRYHfZOOQBDFrB37VX on tokens per min (TPM): Limit 30000, Requested 140099. The input or output tokens must be reduced in order to run successfully. Visit https://platform.openai.com/account/rate-limits to learn more.', 'type': 'tokens', 'param': None, 'code': 'rate_limit_exceeded'}}is there something else that is expected to get the workflow working with llama index and GPT-4o?

cmosguy · Answer

here is more info:

cmosguy · Answer

damn I just discovered that you have to be in Tier 2 with OpenAI. I think your docs should explain this.

Logan M · Answer

Yea this is a limit on your openai account. I guess we have the highest tier, never realized that would be an issue 😅

Logan M · Answer

Feel free to make a PR to add that note!

cmosguy · Answer

If I find the time to do the PR I will

Find answers from the community

llamacloud-demo/examples/report_generati...