support question answering model #2208
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -13,5 +13,6 @@ public enum MLInputDataType { | |
| DATA_FRAME, | ||
| TEXT_DOCS, | ||
| REMOTE, | ||
| TEXT_SIMILARITY, | ||
| QUESTION_ANSWERING | ||
| } | ||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,51 @@ | ||
| /* | ||
| * Copyright OpenSearch Contributors | ||
| * SPDX-License-Identifier: Apache-2.0 | ||
| */ | ||
| package org.opensearch.ml.common.dataset; | ||
|
|
||
| import lombok.AccessLevel; | ||
| import lombok.Builder; | ||
| import lombok.Getter; | ||
| import lombok.experimental.FieldDefaults; | ||
| import org.opensearch.core.common.io.stream.StreamInput; | ||
| import org.opensearch.core.common.io.stream.StreamOutput; | ||
| import org.opensearch.ml.common.annotation.InputDataSet; | ||
|
|
||
| import java.io.IOException; | ||
|
|
||
| @Getter | ||
| @FieldDefaults(makeFinal = true, level = AccessLevel.PRIVATE) | ||
| @InputDataSet(MLInputDataType.QUESTION_ANSWERING) | ||
| public class QuestionAnsweringInputDataSet extends MLInputDataset { | ||
|
|
||
| String question; | ||
|
|
||
| String context; | ||
|
|
||
| @Builder(toBuilder = true) | ||
| public QuestionAnsweringInputDataSet(String question, String context) { | ||
| super(MLInputDataType.QUESTION_ANSWERING); | ||
| if(question == null) { | ||
| throw new IllegalArgumentException("Question is not provided"); | ||
| } | ||
| if(context == null) { | ||
| throw new IllegalArgumentException("Context is not provided"); | ||
| } | ||
| this.question = question; | ||
| this.context = context; | ||
| } | ||
|
|
||
| public QuestionAnsweringInputDataSet(StreamInput in) throws IOException { | ||
| super(MLInputDataType.QUESTION_ANSWERING); | ||
| this.question = in.readString(); | ||
| this.context = in.readString(); | ||
| } | ||
|
|
||
| @Override | ||
| public void writeTo(StreamOutput out) throws IOException { | ||
| super.writeTo(out); | ||
| out.writeString(question); | ||
| out.writeString(context); | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,91 @@ | ||
| /* | ||
| * Copyright OpenSearch Contributors | ||
| * SPDX-License-Identifier: Apache-2.0 | ||
| */ | ||
| package org.opensearch.ml.common.input.nlp; | ||
|
|
||
| import org.opensearch.core.common.io.stream.StreamInput; | ||
| import org.opensearch.core.common.io.stream.StreamOutput; | ||
| import org.opensearch.core.xcontent.XContentBuilder; | ||
| import org.opensearch.core.xcontent.XContentParser; | ||
| import org.opensearch.ml.common.FunctionName; | ||
| import org.opensearch.ml.common.dataset.MLInputDataset; | ||
| import org.opensearch.ml.common.dataset.QuestionAnsweringInputDataSet; | ||
| import org.opensearch.ml.common.input.MLInput; | ||
|
|
||
| import java.io.IOException; | ||
|
|
||
| import static org.opensearch.core.xcontent.XContentParserUtils.ensureExpectedToken; | ||
|
|
||
|
|
||
| /** | ||
| * MLInput which supports a question answering algorithm | ||
| * Inputs are question and context. Output is the answer | ||
| */ | ||
| @org.opensearch.ml.common.annotation.MLInput(functionNames = {FunctionName.QUESTION_ANSWERING}) | ||
| public class QuestionAnsweringMLInput extends MLInput { | ||
|
|
||
| public QuestionAnsweringMLInput(FunctionName algorithm, MLInputDataset dataset) { | ||
| super(algorithm, null, dataset); | ||
| } | ||
|
|
||
| public QuestionAnsweringMLInput(StreamInput in) throws IOException { | ||
| super(in); | ||
| } | ||
|
|
||
| @Override | ||
| public void writeTo(StreamOutput out) throws IOException { | ||
| super.writeTo(out); | ||
| } | ||
|
|
||
| @Override | ||
| public XContentBuilder toXContent(XContentBuilder builder, Params params) throws IOException { | ||
| builder.startObject(); | ||
| builder.field(ALGORITHM_FIELD, algorithm.name()); | ||
| if(parameters != null) { | ||
| builder.field(ML_PARAMETERS_FIELD, parameters); | ||
| } | ||
| if(inputDataset != null) { | ||
| QuestionAnsweringInputDataSet ds = (QuestionAnsweringInputDataSet) this.inputDataset; | ||
| String question = ds.getQuestion(); | ||
| String context = ds.getContext(); | ||
| builder.field(QUESTION_FIELD, question); | ||
| builder.field(CONTEXT_FIELD, context); | ||
| } | ||
| builder.endObject(); | ||
| return builder; | ||
| } | ||
|
|
||
| public QuestionAnsweringMLInput(XContentParser parser, FunctionName functionName) throws IOException { | ||
| super(); | ||
| this.algorithm = functionName; | ||
| String question = null; | ||
| String context = null; | ||
|
|
||
| ensureExpectedToken(XContentParser.Token.START_OBJECT, parser.currentToken(), parser); | ||
| while (parser.nextToken() != XContentParser.Token.END_OBJECT) { | ||
| String fieldName = parser.currentName(); | ||
| parser.nextToken(); | ||
|
|
||
| switch (fieldName) { | ||
| case QUESTION_FIELD: | ||
| question = parser.text(); | ||
|
|
||
| break; | ||
| case CONTEXT_FIELD: | ||
| context = parser.text(); | ||
| break; | ||
| default: | ||
| parser.skipChildren(); | ||
| break; | ||
| } | ||
| } | ||
| if(question == null) { | ||
| throw new IllegalArgumentException("Question is not provided"); | ||
| } | ||
| if(context == null) { | ||
| throw new IllegalArgumentException("Context is not provided"); | ||
| } | ||
| inputDataset = new QuestionAnsweringInputDataSet(question, context); | ||
| } | ||
|
|
||
| } | ||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Oops, something went wrong.
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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
should we put algorithm field or function name field?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
It is algorithm since the super class MLInput has algorithm. Within the model index, it is stored as algorithm rather than function name