alessandrobenedetti commented on code in PR #3151: URL: https://github.com/apache/solr/pull/3151#discussion_r1943565203
########## solr/modules/llm/src/java/org/apache/solr/llm/texttovector/update/processor/TextToVectorUpdateProcessor.java: ########## @@ -0,0 +1,100 @@ +/* + * 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.llm.texttovector.update.processor; + +import org.apache.solr.common.SolrException; +import org.apache.solr.common.SolrInputDocument; +import org.apache.solr.common.SolrInputField; +import org.apache.solr.llm.texttovector.model.SolrTextToVectorModel; +import org.apache.solr.llm.texttovector.store.rest.ManagedTextToVectorModelStore; +import org.apache.solr.request.SolrQueryRequest; +import org.apache.solr.update.AddUpdateCommand; +import org.apache.solr.update.processor.UpdateRequestProcessor; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.io.IOException; +import java.lang.invoke.MethodHandles; +import java.util.ArrayList; +import java.util.List; + + +class TextToVectorUpdateProcessor extends UpdateRequestProcessor { + private static final Logger log = LoggerFactory.getLogger(MethodHandles.lookup().lookupClass()); + + private final String inputField; + private final String outputField; + private final String model; + private SolrTextToVectorModel textToVector; + private ManagedTextToVectorModelStore modelStore = null; + + public TextToVectorUpdateProcessor( + String inputField, + String outputField, + String model, + SolrQueryRequest req, + UpdateRequestProcessor next) { + super(next); + this.inputField = inputField; + this.outputField = outputField; + this.model = model; + this.modelStore = ManagedTextToVectorModelStore.getManagedModelStore(req.getCore()); + } + + /** + * @param cmd the update command in input containing the Document to process + * @throws IOException If there is a low-level I/O error + */ + @Override + public void processAdd(AddUpdateCommand cmd) throws IOException { + this.textToVector = modelStore.getModel(model); + if (textToVector == null) { + throw new SolrException( + SolrException.ErrorCode.BAD_REQUEST, + "The model requested '" + + model + + "' can't be found in the store: " + + ManagedTextToVectorModelStore.REST_END_POINT); + } + + SolrInputDocument doc = cmd.getSolrInputDocument(); + SolrInputField inputFieldContent = doc.get(inputField); + if (!isNullOrEmpty(inputFieldContent, doc, inputField)) { + String textToVectorise = inputFieldContent.getValue().toString();//add null checks and + float[] vector = textToVector.vectorise(textToVectorise); Review Comment: 1) @cpoerschke : I double checked and the langchain4j library 'embed' method (that's used in our 'vectorise' method) returns a RuntimeException . That's bad as it was not detected without investigating the internals of the code (I hate these practices). I'll give it a thought, any suggestion is welcome! 2) @epugh : given that 'update.chain' is a parameter, if you configure a chain with no vector enrichment and a chain with vector enrichment, what prevents you from first index using the 'no vectors' chain and then slowly updating the index with atomic updates that add vectors (using the vector-chain)? We should double check and add to the documentation once we consolidate the code, what do you think? -- 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
