Skip to content

feat(core): Multimodal synthesis part 2#21561

Open
bschloss wants to merge 1 commit intorun-llama:mainfrom
bschloss:feat-multimodal-synthesis-part2
Open

feat(core): Multimodal synthesis part 2#21561
bschloss wants to merge 1 commit intorun-llama:mainfrom
bschloss:feat-multimodal-synthesis-part2

Conversation

@bschloss
Copy link
Copy Markdown
Contributor

@bschloss bschloss commented May 6, 2026

Description

Follow up PR to #21374. Implements multimodal synthesis for the remaining synthesizers.

Fixes # #21373

New Package?

Did I fill in the tool.llamahub section in the pyproject.toml and provide a detailed README.md for my new integration or package?

  • Yes
  • No

Version Bump?

Did I bump the version in the pyproject.toml file of the package I am updating? (Except for the llama-index-core package)

  • Yes
  • No

Type of Change

Please delete options that are not relevant.

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • This change requires a documentation update

How Has This Been Tested?

Your pull-request will likely not be merged unless it is covered by some form of impactful unit testing.

  • I added new unit tests to cover this change
  • I believe this change is already covered by existing unit tests

Suggested Checklist:

  • I have performed a self-review of my own code
  • I have commented my code, particularly in hard-to-understand areas
  • I have made corresponding changes to the documentation
  • I have added Google Colab support for the newly added notebooks.
  • My changes generate no new warnings
  • I have added tests that prove my fix is effective or that my feature works
  • New and existing unit tests pass locally with my changes
  • I ran uv run make format; uv run make lint to appease the lint gods

@dosubot dosubot Bot added the size:L This PR changes 100-499 lines, ignoring generated files. label May 6, 2026
@bschloss bschloss changed the title Make the rest of the synthesizers support multimodal feat: Multimodal synthesis part 2 May 6, 2026
@bschloss bschloss changed the title feat: Multimodal synthesis part 2 feat(core): Multimodal synthesis part 2 May 6, 2026
[f"Response {index + 1}: {item}" for index, item in enumerate(responses)]
)

def _make_prompt_kwargs(self, chunk: str | ChatMessage) -> dict[str, Any]:
Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

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

This function was moved and changed. Apologies for making the diff hard to read. Changes are mostly frontloaded to handle multiple templates/prompt helpers.

return self.get_response(
query_str=query_str, text_chunks=summaries, **response_kwargs
)

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

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

There is a significant amount of code duplication here. Could create an abstraction similar to some other classes. Up to you all.

"information2",
]

def test_synthesize__multimodal(
Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

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

This was simply moved. No logical changes. Also removed some unnecessary comments and standardized style.

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

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

Just standardizing style/cleanup. No logical changes.

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

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

No logical changes. Standardized style/did some clean up

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

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

No logical changes. Moved a function and standardized style.

Copy link
Copy Markdown
Contributor Author

@bschloss bschloss May 6, 2026

Choose a reason for hiding this comment

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

Longer test file, but this class has some complex parametrization and uses programs, so wanted to do some thorough testing. Definitely open to suggestions on reducing code.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

size:L This PR changes 100-499 lines, ignoring generated files.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant