Fix: Limit number of retries for parse failures #1569
Merged
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Outdated suggestions cannot be applied.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.
When parsing of an LLM response fails, the invalid output is sent to the LLM to be fixed.
This PR threads the number of retries through this call, preventing unbounded recursion.
The old
max_retries
wasn't preventing this due togenerate()
andparse_output_string()
being co-recursive via the call togenerate()
hereragas/src/ragas/prompt/pydantic_prompt.py
Line 406 in ade46fb
The result was a prompt that would keep growing through recursive calls (with nested versions becoming increasingly more deeply quoted) until the prompt was too big for the LLM to process.
Addresses #1538