JiriOndrusek opened a new issue, #3086: URL: https://github.com/apache/camel-kamelets/issues/3086
The langchain4j-ingest sink caps the extracted text in characters, after the parse. A parse is itself memory- and CPU-expensive, and a remote request with Docling Serve, so the parser actions should reject an oversized raw payload first. Proposal: a maxDocumentSize property (bytes, 0 = no limit, the default) on both actions, checked before the parse or conversion with a precondition choice, failing the exchange with an IllegalArgumentException naming the document; plus a Citrus test covering under the cap, over the cap through Docling and over the cap from the file source. Kamelet twin of the raw-size guard in the Camel Quarkus langchain4j-ingest extension (apache/camel-quarkus#9152). -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
