Skip to content

Commit

Permalink
#4292 - ollama-based recommender
Browse files Browse the repository at this point in the history
- Basic ollama-based recommender (highly experimental)
  • Loading branch information
reckart committed Nov 12, 2023
1 parent 80fb3ec commit b47d477
Show file tree
Hide file tree
Showing 16 changed files with 727 additions and 0 deletions.
4 changes: 4 additions & 0 deletions inception/inception-app-webapp/pom.xml
Original file line number Diff line number Diff line change
Expand Up @@ -235,6 +235,10 @@
<groupId>de.tudarmstadt.ukp.inception.app</groupId>
<artifactId>inception-imls-hf</artifactId>
</dependency>
<dependency>
<groupId>de.tudarmstadt.ukp.inception.app</groupId>
<artifactId>inception-imls-ollama</artifactId>
</dependency>
<!--
<dependency>
<groupId>de.tudarmstadt.ukp.inception.app</groupId>
Expand Down
5 changes: 5 additions & 0 deletions inception/inception-bom/pom.xml
Original file line number Diff line number Diff line change
Expand Up @@ -272,6 +272,11 @@
<artifactId>inception-imls-lapps</artifactId>
<version>30.0-SNAPSHOT</version>
</dependency>
<dependency>
<groupId>de.tudarmstadt.ukp.inception.app</groupId>
<artifactId>inception-imls-ollama</artifactId>
<version>30.0-SNAPSHOT</version>
</dependency>
<dependency>
<groupId>de.tudarmstadt.ukp.inception.app</groupId>
<artifactId>inception-imls-weblicht</artifactId>
Expand Down
1 change: 1 addition & 0 deletions inception/inception-imls-ollama/marker-wicket-module
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
Marker file which activates the profile "wicket-module" from the parent POM.
129 changes: 129 additions & 0 deletions inception/inception-imls-ollama/pom.xml
Original file line number Diff line number Diff line change
@@ -0,0 +1,129 @@
<!--
Licensed to the Technische Universität Darmstadt under one
or more contributor license agreements. See the NOTICE file
distributed with this work for additional information
regarding copyright ownership. The Technische Universität Darmstadt
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.
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.
-->
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<parent>
<groupId>de.tudarmstadt.ukp.inception.app</groupId>
<artifactId>inception-app</artifactId>
<version>30.0-SNAPSHOT</version>
</parent>

<artifactId>inception-imls-ollama</artifactId>
<name>INCEpTION - ML - Ollama</name>

<repositories>
<repository>
<id>ollama4j-from-ossrh</id>
<url>https://s01.oss.sonatype.org/content/repositories/snapshots</url>
</repository>
</repositories>

<dependencies>
<dependency>
<groupId>io.github.amithkoujalgi</groupId>
<artifactId>ollama4j</artifactId>
<version>1.0-SNAPSHOT</version>
<exclusions>
<exclusion>
<groupId>ch.qos.logback</groupId>
<artifactId>logback-classic</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>com.hubspot.jinjava</groupId>
<artifactId>jinjava</artifactId>
<version>2.7.1</version>
</dependency>

<dependency>
<groupId>de.tudarmstadt.ukp.inception.app</groupId>
<artifactId>inception-recommendation-api</artifactId>
</dependency>

<dependency>
<groupId>de.tudarmstadt.ukp.inception.app</groupId>
<artifactId>inception-model</artifactId>
</dependency>
<dependency>
<groupId>de.tudarmstadt.ukp.inception.app</groupId>
<artifactId>inception-api-render</artifactId>
</dependency>
<dependency>
<groupId>de.tudarmstadt.ukp.inception.app</groupId>
<artifactId>inception-support</artifactId>
</dependency>

<dependency>
<groupId>org.apache.commons</groupId>
<artifactId>commons-lang3</artifactId>
</dependency>

<!-- UIMA -->
<dependency>
<groupId>org.apache.uima</groupId>
<artifactId>uimaj-core</artifactId>
</dependency>

<!-- Spring -->
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-context</artifactId>
</dependency>
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-web</artifactId>
</dependency>
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-autoconfigure</artifactId>
</dependency>

<dependency>
<groupId>org.apache.wicket</groupId>
<artifactId>wicket-core</artifactId>
</dependency>
<dependency>
<groupId>org.apache.wicket</groupId>
<artifactId>wicket-spring</artifactId>
</dependency>
<dependency>
<groupId>com.googlecode.wicket-jquery-ui</groupId>
<artifactId>wicket-kendo-ui</artifactId>
</dependency>
<dependency>
<groupId>com.googlecode.wicket-jquery-ui</groupId>
<artifactId>wicket-jquery-ui-core</artifactId>
</dependency>
<dependency>
<groupId>org.danekja</groupId>
<artifactId>jdk-serializable-functional</artifactId>
</dependency>

<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-annotations</artifactId>
</dependency>
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-databind</artifactId>
</dependency>
</dependencies>
</project>
Original file line number Diff line number Diff line change
@@ -0,0 +1,159 @@
/*
* Licensed to the Technische Universität Darmstadt under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The Technische Universität Darmstadt
* 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.
*
* 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 de.tudarmstadt.ukp.inception.recommendation.imls.ollama;

import static de.tudarmstadt.ukp.clarin.webanno.api.annotation.util.WebAnnoCasUtil.selectOverlapping;

import java.io.IOException;
import java.lang.invoke.MethodHandles;
import java.nio.charset.Charset;
import java.util.Map;

import org.apache.commons.lang3.exception.ExceptionUtils;
import org.apache.uima.cas.CAS;
import org.apache.uima.fit.util.CasUtil;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import com.hubspot.jinjava.Jinjava;
import com.hubspot.jinjava.JinjavaConfig;
import com.hubspot.jinjava.interpret.JinjavaInterpreter;
import com.hubspot.jinjava.loader.ResourceLocator;
import com.hubspot.jinjava.loader.ResourceNotFoundException;

import de.tudarmstadt.ukp.dkpro.core.api.segmentation.type.Sentence;
import de.tudarmstadt.ukp.inception.recommendation.api.model.Recommender;
import de.tudarmstadt.ukp.inception.recommendation.api.recommender.NonTrainableRecommenderEngineImplBase;
import de.tudarmstadt.ukp.inception.recommendation.api.recommender.RecommendationException;
import de.tudarmstadt.ukp.inception.recommendation.api.recommender.RecommenderContext;
import de.tudarmstadt.ukp.inception.rendering.model.Range;
import io.github.amithkoujalgi.ollama4j.core.OllamaAPI;
import io.github.amithkoujalgi.ollama4j.core.exceptions.OllamaBaseException;

public class OllamaRecommender
extends NonTrainableRecommenderEngineImplBase
{
private static final String VAR_TEXT = "text";

private final static Logger LOG = LoggerFactory.getLogger(MethodHandles.lookup().lookupClass());

private final OllamaRecommenderTraits traits;

private final OllamaAPI ollamaApi;
private final Jinjava jinjava;

public OllamaRecommender(Recommender aRecommender, OllamaRecommenderTraits aTraits)
{
super(aRecommender);

traits = aTraits;

var config = new JinjavaConfig();
jinjava = new Jinjava(config);
jinjava.setResourceLocator(new ResourceLocator()
{
@Override
public String getString(String aFullName, Charset aEncoding,
JinjavaInterpreter aInterpreter)
throws IOException
{
throw new ResourceNotFoundException("Couldn't find resource: " + aFullName);
}
});

ollamaApi = new OllamaAPI(traits.getUrl());
}

@Override
public Range predict(RecommenderContext aContext, CAS aCas, int aBegin, int aEnd)
throws RecommendationException
{
switch (traits.getProcessingMode()) {
case PER_ANNOTATION:
return predictPerAnnotation(aContext, aCas, aBegin, aEnd);
case PER_SENTENCE:
return predictPerSentence(aContext, aCas, aBegin, aEnd);
default:
throw new RecommendationException(
"Unsupported mode [" + traits.getProcessingMode() + "]");
}
}

private Range predictPerSentence(RecommenderContext aContext, CAS aCas, int aBegin, int aEnd)
{
var candidateType = CasUtil.getAnnotationType(aCas, Sentence.class);
var predictedType = getPredictedType(aCas);
var predictedFeature = getPredictedFeature(aCas);
var isPredictionFeature = getIsPredictionFeature(aCas);

for (var candidate : selectOverlapping(aCas, candidateType, aBegin, aEnd)) {
var bindings = Map.of(VAR_TEXT, candidate.getCoveredText());
var prompt = jinjava.render(traits.getPrompt(), bindings);

try {
var response = ask(prompt);

var prediction = aCas.createAnnotation(predictedType, candidate.getBegin(),
candidate.getEnd());
prediction.setFeatureValueFromString(predictedFeature, response);
prediction.setBooleanValue(isPredictionFeature, true);
aCas.addFsToIndexes(prediction);
}
catch (OllamaBaseException | IOException e) {
LOG.error("Ollama [{}] failed to respond: {}", traits.getModel(),
ExceptionUtils.getRootCauseMessage(e));
}
}

return new Range(aBegin, aEnd);
}

private Range predictPerAnnotation(RecommenderContext aContext, CAS aCas, int aBegin, int aEnd)
{
var predictedType = getPredictedType(aCas);
var predictedFeature = getPredictedFeature(aCas);
var isPredictionFeature = getIsPredictionFeature(aCas);

for (var candidate : selectOverlapping(aCas, predictedType, aBegin, aEnd)) {
var bindings = Map.of(VAR_TEXT, candidate.getCoveredText());
var prompt = jinjava.render(traits.getPrompt(), bindings);

try {
var response = ask(prompt);

var prediction = candidate;
prediction.setFeatureValueFromString(predictedFeature, response);
prediction.setBooleanValue(isPredictionFeature, true);
}
catch (OllamaBaseException | IOException e) {
LOG.error("Ollama [{}] failed to respond: {}", traits.getModel(),
ExceptionUtils.getRootCauseMessage(e));
}
}

return new Range(aBegin, aEnd);
}

private String ask(String prompt) throws OllamaBaseException, IOException
{
LOG.trace("Asking ollama [{}]: [{}]", traits.getModel(), prompt);
var response = ollamaApi.ask(traits.getModel(), prompt).trim();
LOG.trace("Ollama [{}] responds: [{}]", traits.getModel(), response);
return response;
}
}
Loading

0 comments on commit b47d477

Please sign in to comment.