promptLayer

[med-dak]

I tried using promptLayer, following the documentation :

os.environ["PROMPTLAYER_API_KEY"] = "pl_..."
from llama_index import set_global_handler
set_global_handler("promptlayer", pl_tags=["paul graham", "essay"])

, but I encountered this error:
While logging your request PromptLayer had the following error: maximum recursion depth exceeded while calling a Python object

When I use the code from the promptLayer documentation, it works. Furthermore, when I change the placement of this line : set_global_handler("promptlayer", pl_tags=["paul graham", "essay"]), I no longer get an error, but I don't find anything in the promptLayer dashboard.

[dosubot[bot]]

🤖

Hey @med-dak, good to see you back! Running into new adventures, I see.

Based on the error message you provided, it seems like you're encountering a RecursionError: maximum recursion depth exceeded while calling a Python object. This error typically occurs when a function calls itself (or calls another function which in turn calls the original function) too many times, exceeding the maximum recursion depth limit set by Python.

There are a couple of similar issues that have been resolved in the LlamaIndex repository:

1. Bug: RecursionError: maximum recursion depth exceeded while calling a Python object for HierarchicalNodeParser - This issue was resolved by improving the error logs for text splitters. You can check the pull request here for more details.

2. Question: Error using Prompts - This issue was referenced by two other issues (#9277 and #9903) and might provide some insight into your problem.

Regarding the set_global_handler function, it is used to set the global evaluation handler in the LlamaIndex codebase. It takes in two parameters: eval_mode and eval_params. The eval_mode is a string that determines which type of handler to create, and eval_params are any additional parameters needed for the handler. You can find more details about this function in the source code.

As for the promptLayer function, it seems there might be some confusion. The LlamaIndex codebase does not contain a function named promptLayer. However, it does have a PromptLayerHandler class that interacts with the PromptLayer API. This class handles different aspects of the interaction with the PromptLayer API, such as adding events, retrieving events, and sending requests to the API. You can find more details about this class in the source code.

If you're still encountering the error, it would be helpful if you could provide more details about the context in which the error occurs. For example, what are the values of eval_mode and eval_params when you call set_global_handler? Also, could you clarify what you mean by promptLayer? Are you referring to a function in your own code, or is it something in the LlamaIndex codebase? Any additional information you can provide will help in diagnosing the issue.

Sources

• [Bug]: RecursionError: maximum recursion depth exceeded while calling a Python object for HierarchicalNodeParser
• [Question]: Error using Prompts
• llama_index/callbacks/global_handlers.py
• llama_index/callbacks/promptlayer_handler.py

About Dosu

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.