Description
This is a ticket to integrate learning to rank machine learning models into Solr. Solr Learning to Rank (LTR) provides a way for you to extract features directly inside Solr for use in training a machine learned model. You can then deploy that model to Solr and use it to rerank your top X search results. This concept was previously presented by the authors at Lucene/Solr Revolution 2015.
Solr Reference Guide documentation:
Source code and README files:
Attachments
Attachments
Issue Links
- breaks
-
SOLR-9746 Eclipse project broken due to duplicate package-info.java in LTR contrib
- Resolved
- is related to
-
SOLR-10667 Solr packaging doesn't include Learn To Rank examples
- Open
-
SOLR-9929 Documentation and sample code about how to train the model using user clicks when use ltr module
- Resolved
- relates to
-
SOLR-10005 solr/contrib/ltr : add missing class-level javadocs
- Open
-
SOLR-15569 MultipleAdditiveTreesModel does not split as expected when the node value equals the split threshold
- Open
-
SOLR-10192 fix copy/paste in solr/contrib/ltr/pom.xml.template
- Resolved
-
SOLR-10283 SolrFeature fails to reject searches with missing efi (if used by fq)
- Resolved
-
SOLR-10963 Sample model json format for MultipleAdditiveTreesModel is incorrect
- Resolved
-
SOLR-10383 NPE on debug query in SOLR UI - LTR OriginalScoreFeature
- Closed
-
SOLR-10421 solr/contrib/ltr (MinMax|Standard)Normalizer.paramsToMap needs to save float as string
- Closed
-
SOLR-11163 Normalizer fails to restore itself when reload or restart solr cores.
- Closed
-
SOLR-10451 Remove contrib/ltr/lib from lib includes in the techproducts example config
- Closed
-
SOLR-8183 Add Learning to Rank framework to Solr
- Open
-
SOLR-10081 Web UI (Generate Training Data ) for LTR plugin
- Open
-
SOLR-10811 Speed up MultipleAdditiveTreesModel by using QuickScorer algorithm
- Open
-
SOLR-10077 TestManagedFeatureStore extends LuceneTestCase, but has no tests and just hosts a static method.
- Resolved
-
SOLR-10072 The test TestSelectiveWeightCreation appears to be unreliable.
- Closed
-
SOLR-10174 fix 3x in @Ignore TestLTRReRankingPipeline and TestMultipleAdditiveTreesModel
- Closed
-
LEGAL-276 SOLR-8542 contribution and potential patent concerns
- Closed
- requires
-
SOLR-9161 SolrPluginUtils.invokeSetters should accommodate setter variants
- Closed
-
SOLR-9412 Update Macro Expander for replacement logic
- Resolved
-
SOLR-9331 Can we remove ReRankQuery's length constructor argument?
- Resolved
-
SOLR-9353 factor out ReRankQParserPlugin.ReRankQueryRescorer private class
- Resolved
-
SOLR-9543 reduce code duplication in ReRankQParserPlugin.ReRankCollector.topDocs
- Resolved
-
SOLR-9567 factor out ReRankCollector from ReRankQParserPlugin
- Resolved
-
SOLR-9574 factor out AbstractReRankQuery class
- Resolved
-
SOLR-9410 make ReRankQParserPlugin's private ReRankWeight public
- Closed
- links to