Skip to content
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.

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

Add framework integration for composite retrieval #17536

Open
wants to merge 10 commits into
base: main
Choose a base branch
from

Conversation

sourabhdesai
Copy link
Contributor

@sourabhdesai sourabhdesai commented Jan 17, 2025

Description

Add LlamaCloudCompositeRetriever class. Some refactoring to reuse code that was in LlamaCloudRetriever

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 make format; make lint to appease the lint gods

@sourabhdesai sourabhdesai changed the title [DRAFT] add framework integration for composite retrieval Add framework integration for composite retrieval Jan 17, 2025
@sourabhdesai sourabhdesai marked this pull request as ready for review January 17, 2025 21:37
create_if_not_exists=True,
# CompositeRetrievalMode.FULL will query each index individually and globally rerank results at the end
mode=CompositeRetrievalMode.FULL,
rerank_top_n=5,
Copy link
Collaborator

Choose a reason for hiding this comment

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

is reranking optional?

Copy link
Contributor Author

@sourabhdesai sourabhdesai Jan 17, 2025

Choose a reason for hiding this comment

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

No it always reranks but when omitted it uses the server side default of 6

Copy link
Collaborator

Choose a reason for hiding this comment

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

Maybe this is a backend consideration then, but it might be nice to disable this and/or use something like relative score fusion instead (I feel the reranker can be a source of error depending on what your documents look like)


# Start retrieving context for your queries
# async .aretrieve() is also available
nodes = retriever.retrieve("What does YC do?")
Copy link
Collaborator

Choose a reason for hiding this comment

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

I wonder if it'd be nice to show how to plug this into an agent using, say, a RetrieverTool or similar? Maybe in its own notebook though, up to you

Copy link
Collaborator

@logan-markewich logan-markewich left a comment

Choose a reason for hiding this comment

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

Looks pretty good! Just a few minor comments.

@dosubot dosubot bot added size:XL This PR changes 500-999 lines, ignoring generated files. lgtm This PR has been approved by a maintainer labels Jan 17, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
lgtm This PR has been approved by a maintainer size:XL This PR changes 500-999 lines, ignoring generated files.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants