Add PyTerrier_ChatNoir to the plugin section #452
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Outdated suggestions cannot be applied.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.
Dear all,
we have a PyTerrier plugin for ChatNoir (cf. the paper, respectively an example query to allow retrieval/re-ranking against large datasets (e.g., ClueWeb09, ClueWeb12, ClueWeb22, the recent MS MARCO V2.1 inclusion is in progress for TREC RAG) that we would like to add to the documentation of available plugins. With this plugin, users can re-rank the results without having to index the corpora themselves.
The covered parts of the REST API allows for retrieval and for random-document access (but this random document access is much slower compared to a locally available ir_dataset, but is still valuable I think, for example when users do not want to download the complete datasets but still apply re-ranking pipelines).
In the next weeks, I would like to add more of the public ir_datasets to ChatNoir, which could make this plugin really cool I think.