feat: add FastembedColBERTRanker for bi-encoder reranking #10458
+605
−0
Conversation
This file contains hidden or 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
Add support for ColBERT models via FastEmbed with MaxSim scoring. Addresses issue deepset-ai#8245
adrianegraphene
requested review from
anakin87 and
Copilot
and removed request for
a team and
Copilot
|
@adrianegraphene is attempting to deploy a commit to the deepset Team on Vercel. A member of the Team first needs to authorize it. |
|
|
github-actions
bot
added
topic:tests
topic:build/distribution
type:documentation
anakin87
requested changes
Jan 28, 2026
Member
anakin87
left a comment
anakin87
left a comment
There was a problem hiding this comment.
Hey @adrianegraphene, thanks for contributing!
We already have an integration with FastEmbed here: https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/fastembed
So I recommend closing this PR and opening another one targeting the Haystack Core Integrations repository.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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.
Add support for ColBERT models via FastEmbed with MaxSim scoring.
Related Issues
Proposed Changes:
This PR adds a feature for
FastembedColBERTRanker, a new ranker component that enables bi-encoder reranking using ColBERT models through the FastEmbed library.What's included:
FastembedColBERTRankercomponent inhaystack/components/rankers/colbert-ir/colbertv2.0,answerdotai/answerai-colbert-small-v1)How did you test it?
pytest test/components/rankers/test_fastembed_colbert.py -m "not integration" -vNotes for the reviewer
I just worked on something similar and wanted to get the patterns out of my head while it was fresh. I saw this issue needed contributions, so decided I'd help. Happy to fix up / add / remove anything at all.
Checklist
fix:,feat:,build:,chore:,ci:,docs:,style:,refactor:,perf:,test:and added!in case the PR includes breaking changes.