[
https://issues.apache.org/jira/browse/TIKA-4972?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=18128942#comment-18128942
]
Hudson commented on TIKA-4972:
------------------------------
SUCCESS: Integrated in Jenkins build Tika ยป tika-main-jdk17 #1720 (See
[https://ci-builds.apache.org/job/Tika/job/tika-main-jdk17/1720/])
TIKA-4972: try to do what we can with vlm ocr engines (#3348) (github:
[https://github.com/apache/tika/commit/67aea63ea2b147d8de2d75e7655947ed4f205d16])
* (edit)
tika-parsers/tika-http-jdk/src/test/java/org/apache/tika/http/TikaTestHttpServer.java
* (edit)
tika-parsers/tika-parsers-ml/tika-vlm/src/test/java/org/apache/tika/parser/vlm/OpenAIVLMParserTest.java
* (edit)
tika-parsers/tika-parsers-ml/tika-vlm/src/main/java/org/apache/tika/parser/vlm/AbstractVLMParser.java
* (add)
tika-image-processing/src/test/java/org/apache/tika/imageprocessing/ImageFixtures.java
* (edit) docs/modules/ROOT/pages/migration-to-4x/migrating-to-4x.adoc
* (add)
tika-image-processing/src/main/java/org/apache/tika/imageprocessing/BlankImageCheck.java
* (add)
tika-image-processing/src/test/java/org/apache/tika/imageprocessing/ImageChecksConfigTest.java
* (add)
tika-image-processing/src/main/java/org/apache/tika/imageprocessing/ImageDecoding.java
* (edit)
tika-parsers/tika-parsers-ml/tika-vlm/src/main/java/org/apache/tika/parser/vlm/GeminiVLMParser.java
* (edit)
tika-parsers/tika-parsers-ml/tika-vlm/src/test/java/org/apache/tika/parser/vlm/ClaudeVLMParserTest.java
* (edit)
tika-core/src/main/java/org/apache/tika/metadata/TikaCoreProperties.java
* (add)
tika-core/src/main/java/org/apache/tika/parser/enricher/RecordedSizeCheck.java
* (add) docs/modules/ROOT/examples/jina-ocr-basic.json
* (add)
tika-core/src/test/java/org/apache/tika/parser/enricher/ImageProbeTest.java
* (edit) docs/modules/ROOT/pages/configuration/inference.adoc
* (edit) docs/modules/ROOT/pages/configuration/parsers/vlm-parsers.adoc
* (add)
tika-core/src/test/java/org/apache/tika/parser/enricher/GatedEnricherTest.java
* (add)
tika-parsers/tika-parsers-ml/tika-vlm/src/test/java/org/apache/tika/parser/vlm/VLMPdfPageEndToEndTest.java
* (edit) docs/modules/ROOT/pages/configuration/index.adoc
* (edit)
tika-core/src/main/java/org/apache/tika/parser/enricher/ContentEnrichers.java
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
* (edit)
tika-metadata-schema/src/main/resources/org/apache/tika/metadata/metadata-key-fields.json
* (edit)
tika-parsers/tika-parsers-ml/tika-inference/src/main/java/org/apache/tika/inference/OpenAIEmbeddingEngine.java
* (edit) tika-bom/pom.xml
* (add)
tika-image-processing/src/main/java/org/apache/tika/imageprocessing/ByteSizeCheck.java
* (add) tika-image-processing/pom.xml
* (edit)
tika-serialization/src/main/java/org/apache/tika/config/loader/TikaObjectMapperFactory.java
* (add)
tika-image-processing/src/main/java/org/apache/tika/imageprocessing/MinImageSizeCheck.java
* (edit)
tika-serialization/src/main/java/org/apache/tika/config/loader/ContentEnricherLoader.java
* (edit)
tika-metadata-schema/src/main/resources/org/apache/tika/metadata/metadata-keys.json
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/AbstractPDF2XHTML.java
* (edit)
tika-serialization/src/test/java/org/apache/tika/config/loader/ContentEnricherLoaderTest.java
* (edit) CHANGES.txt
* (edit) tika-app/pom.xml
* (edit)
tika-core/src/test/java/org/apache/tika/parser/enricher/ContentEnrichersTest.java
* (edit) tika-server/tika-server-standard/pom.xml
* (edit) pom.xml
* (edit)
tika-parsers/tika-http-jdk/src/main/java/org/apache/tika/http/TikaHttpClient.java
* (edit)
tika-parsers/tika-parsers-ml/tika-vlm/src/test/java/org/apache/tika/parser/vlm/VLMConfigExamplesTest.java
* (edit)
tika-core/src/main/java/org/apache/tika/parser/enricher/SizeGatedEnricher.java
* (add) tika-app/src/test/java/org/apache/tika/cli/TikaCLIOcrWarningsTest.java
* (edit) .skills/devs/development/SKILL.md
* (edit)
tika-parsers/tika-parsers-ml/tika-vlm/src/test/java/org/apache/tika/parser/vlm/VLMOperatorOnlyConfigTest.java
* (add)
tika-parsers/tika-parsers-ml/tika-vlm/src/test/resources/config-examples/jina-ocr-basic.json
* (add)
tika-image-processing/src/test/java/org/apache/tika/imageprocessing/ByteSizeCheckTest.java
* (edit)
tika-parsers/tika-parsers-ml/tika-vlm/src/main/java/org/apache/tika/parser/vlm/ClaudeVLMParser.java
* (add) tika-core/src/main/java/org/apache/tika/parser/enricher/ImageProbe.java
* (edit)
tika-annotation-processor/src/main/java/org/apache/tika/annotation/TikaComponentProcessor.java
* (add)
tika-image-processing/src/test/java/org/apache/tika/imageprocessing/ImageDecodingTest.java
* (add)
tika-image-processing/src/test/java/org/apache/tika/imageprocessing/BlankImageCheckTest.java
* (edit)
tika-parsers/tika-http-jdk/src/test/java/org/apache/tika/http/TikaHttpClientTest.java
* (edit)
tika-parsers/tika-parsers-ml/tika-vlm/src/test/java/org/apache/tika/parser/vlm/GeminiVLMParserTest.java
* (add)
tika-core/src/main/java/org/apache/tika/parser/enricher/GatedEnricher.java
* (add) tika-core/src/main/java/org/apache/tika/parser/enricher/ImageCheck.java
* (edit)
tika-parsers/tika-parsers-ml/tika-vlm/src/main/java/org/apache/tika/parser/vlm/VLMOCRConfig.java
* (add) tika-core/src/main/java/org/apache/tika/parser/enricher/OcrWarnings.java
* (add)
tika-image-processing/src/test/java/org/apache/tika/imageprocessing/MinImageSizeCheckTest.java
* (edit)
tika-parsers/tika-parsers-ml/tika-vlm/src/main/java/org/apache/tika/parser/vlm/OpenAIVLMParser.java
> Try to do what we can with vlm ocr output that's gone off the rails
> -------------------------------------------------------------------
>
> Key: TIKA-4972
> URL: https://issues.apache.org/jira/browse/TIKA-4972
> Project: Tika
> Issue Type: Task
> Reporter: Tim Allison
> Priority: Major
>
--
This message was sent by Atlassian Jira
(v8.20.10#820010)