ercsonusharma commented on code in PR #3418: URL: https://github.com/apache/solr/pull/3418#discussion_r2198420584
########## solr/core/src/java/org/apache/solr/search/combine/ReciprocalRankFusion.java: ########## @@ -0,0 +1,234 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.solr.search.combine; + +import java.io.IOException; +import java.util.ArrayList; +import java.util.Collections; +import java.util.HashMap; +import java.util.List; +import java.util.Map; +import java.util.StringJoiner; +import org.apache.lucene.document.Document; +import org.apache.lucene.search.Explanation; +import org.apache.lucene.search.Query; +import org.apache.lucene.search.TotalHits; +import org.apache.solr.common.params.CombinerParams; +import org.apache.solr.common.params.SolrParams; +import org.apache.solr.common.util.NamedList; +import org.apache.solr.common.util.SimpleOrderedMap; +import org.apache.solr.handler.component.ShardDoc; +import org.apache.solr.schema.IndexSchema; +import org.apache.solr.search.DocIterator; +import org.apache.solr.search.DocList; +import org.apache.solr.search.DocSlice; +import org.apache.solr.search.QueryResult; +import org.apache.solr.search.SolrIndexSearcher; +import org.apache.solr.search.SortedIntDocSet; + +/** + * The ReciprocalRankFusion class implements a query and response combiner that uses the Reciprocal + * Rank Fusion (RRF) algorithm to combine multiple ranked lists into a single ranked list. + */ +public class ReciprocalRankFusion extends QueryAndResponseCombiner { + + private final int k; + + /** + * Constructs a ReciprocalRankFusion instance. + * + * @param requestParams the SolrParams containing the configuration parameters for this combiner. + */ + public ReciprocalRankFusion(SolrParams requestParams) { + super(requestParams); + this.k = + requestParams.getInt(CombinerParams.COMBINER_RRF_K, CombinerParams.COMBINER_RRF_K_DEFAULT); + } + + @Override + public QueryResult combine(List<QueryResult> rankedLists) { + List<DocList> docLists = new ArrayList<>(rankedLists.size()); + for (QueryResult rankedList : rankedLists) { + docLists.add(rankedList.getDocList()); + } + QueryResult combinedResult = new QueryResult(); + combineResults(combinedResult, docLists, false); + return combinedResult; + } + + @Override + public List<ShardDoc> combine(Map<String, List<ShardDoc>> shardDocMap) { + HashMap<String, Float> docIdToScore = new HashMap<>(); + Map<String, ShardDoc> docIdToShardDoc = new HashMap<>(); + List<ShardDoc> finalShardDocList = new ArrayList<>(); + for (Map.Entry<String, List<ShardDoc>> shardDocEntry : shardDocMap.entrySet()) { + List<ShardDoc> shardDocList = shardDocEntry.getValue(); + int ranking = 1; + while (ranking <= shardDocList.size() && ranking <= upTo) { + String docId = shardDocList.get(ranking - 1).id.toString(); + docIdToShardDoc.put(docId, shardDocList.get(ranking - 1)); + float rrfScore = 1f / (k + ranking); + docIdToScore.compute(docId, (id, score) -> (score == null) ? rrfScore : score + rrfScore); + ranking++; + } + } + // TODO: Add the remaining items out of upTo limit to the docIdToScore + List<Map.Entry<String, Float>> sortedByScoreDescending = + docIdToScore.entrySet().stream() + .sorted(Collections.reverseOrder(Map.Entry.comparingByValue())) + .toList(); + for (Map.Entry<String, Float> scoredDoc : sortedByScoreDescending) { + String docId = scoredDoc.getKey(); + Float score = scoredDoc.getValue(); + ShardDoc shardDoc = docIdToShardDoc.get(docId); + shardDoc.score = score; + finalShardDocList.add(shardDoc); + } + return finalShardDocList; + } + + private Map<Integer, Integer[]> combineResults( + QueryResult combinedRankedList, + List<DocList> rankedLists, + boolean saveRankPositionsForExplain) { + Map<Integer, Integer[]> docIdToRanks = null; + HashMap<Integer, Float> docIdToScore = new HashMap<>(); + long totalMatches = 0; + for (DocList rankedList : rankedLists) { + DocIterator docs = rankedList.iterator(); + totalMatches = Math.max(totalMatches, rankedList.matches()); + int ranking = 1; + while (docs.hasNext() && ranking <= upTo) { + int docId = docs.nextDoc(); Review Comment: As usual, User-specified top N is being enforced at the shard level [here](https://github.com/ercsonusharma/solr/blob/9b0c76ef88a204829bbe1a2cb1cdec938d1b8586/solr/core/src/java/org/apache/solr/handler/component/QueryComponent.java#L1163-L1163) and search index level at SolrIndexSearcher by setting the nums and offset in SortSpec. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: issues-unsubscr...@solr.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@solr.apache.org For additional commands, e-mail: issues-h...@solr.apache.org
