[PR] OPENNLP-1895: Add quantized vector storage and search for static embeddings (opennlp)

["krickert (via GitHub)" <gi...@apache.org>]

krickert opened a new pull request, #1213:
URL: https://github.com/apache/opennlp/pull/1213

   ## Summary
   
   Depends on #1152 (OPENNLP-1877 static embeddings). Please review this after its parent.
   
   This adds compact quantized storage and similarity search for OpenNLP static embedding models:
   
   * randomized Hadamard rotation and Gaussian scalar quantization
   * packed quantized embedding rows with validated serialization
   * loading quantized and full-precision embedding tables through the same model API
   * cosine similarity and nearest-neighbor behavior over quantized models
   * command-line and manual coverage for producing and using quantized models
   
   The implementation remains inside the existing opennlp-embeddings module and does not introduce a general search server or distributed index.
   
   ## Verification
   
   The branch was restacked on the current #1152 tip and passed the complete 15-project compilation, packaging, Checkstyle, forbidden-API, Javadoc, and RAT reactor gate with opennlp.forkCount=1. The quantization and direct embeddings suites also passed on the complete stack.
   
   The unrestricted upstream reactor test command additionally encountered unrelated model-download failures in inherited runtime and formats tests. Those failures could not obtain public tokenizer and sentence models; 1,682 runtime unit tests passed before the download-dependent failures.
   
   ## JIRA
   
   https://issues.apache.org/jira/browse/OPENNLP-1895
   


-- 
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: commits-unsubscribe@opennlp.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org

Re: [PR] OPENNLP-1895: Add quantized vector storage and search for static embeddings (opennlp)

["krickert (via GitHub)" <gi...@apache.org>]

krickert closed pull request #1213: OPENNLP-1895: Add quantized vector storage and search for static embeddings
URL: https://github.com/apache/opennlp/pull/1213


-- 
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: commits-unsubscribe@opennlp.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org