Update iteration_node.py to fix #14098: Token count increases exponen… #14100
Conversation
This file contains 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
…s exponentially when using parallel nodes graph_engine_copy.graph_runtime_state.total_tokens should reset to zero to make the token count correct when using parallel nodes.
dosubot
bot
added
size:XS
|
Could you please provide more details? I am unable to reproduce the exponential token growth issue on my end. |
This screenshot shows a translation task on my local machine. "创建术语表" is an iterative node, and I set the parallelism of the iterative node to 3. After the iterative node runs, the displayed statistics are 640.180M, while the actual number of tokens for this task is about 100k. The reason is as I stated in the issue, and as the number of parallel iterations increases, this value may even exceed the bigint range of PostgreSQL, causing the workflow to fail.
|
Oh, I can reproduce the issue through your screenshot. Thank you very much for your contribution. |
Nov1c444
approved these changes
Feb 21, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
graph_engine_copy.graph_runtime_state.total_tokens should reset to zero to make the token count correct when using parallel nodes.
Summary
Fixes #14098