Skip to content

docs: add robust parsing with automatic retry to structured outputs guide #33120

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 2 commits into from
Closed

docs: add robust parsing with automatic retry to structured outputs guide #33120

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
992c6b7
docs: add robust parsing with automatic retry to structured outputs g…
codeananda Sep 25, 2025
4a8e6d0
Merge branch 'master' into docs/robust-parsing-structured-output
eyurtsev Sep 26, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 17 additions & 0 deletions docs/docs/concepts/structured_outputs.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -152,3 +152,20 @@ ResponseFormatter(answer="The powerhouse of the cell is the mitochondrion. Mitoc
For more details on usage, see our [how-to guide](/docs/how_to/structured_output/#the-with_structured_output-method).

:::

## Handling parsing errors

In production, LLMs may return malformed outputs. While `with_structured_output()` doesn't provide automatic retry on parsing errors, you can use `OutputFixingParser` for this:

```python
from langchain.output_parsers import OutputFixingParser
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

FYI we're not including this in langchain_v1 yet. We'll likely need to figure out how to have the same functionality exposed in v1.

Copy link
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@eyurtsev what is the recommended approach in V1? with_structured_output?


# Create a robust parser with automatic retry
base_parser = PydanticOutputParser(pydantic_object=ResponseFormatter)
robust_parser = OutputFixingParser.from_llm(parser=base_parser, llm=model)

# Automatically fixes parsing errors by asking the LLM to correct malformed outputs
structured_output = robust_parser.parse(llm_output)
```

This works with both `PydanticOutputParser` and `JsonOutputParser`. For cases requiring the original prompt context, see the [RetryOutputParser guide](/docs/how_to/output_parser_retry).
Loading