1

I trained a rankprob model using tensorflow. The input to the model is a query and 2 documents. The model's output is the probability that doc1 is ranked higher compared to doc2. Is it possible to use this model as a level2 reranking in Vespa? If yes, can some one point me to relevant documentation?

Ashish
  • 23
  • 2

1 Answers1

2

When Vespa evaluates the ranking expressions configured in your ranking profile it does a document at a time and produce a final relevancy score which can be used to rank (order) the recalled documents.

For tensorflow model integration see:

https://docs.vespa.ai/documentation/tutorials/blog-recommendation-nn.html https://docs.vespa.ai/documentation/tensorflow.html

Jo Kristian Bergum
  • 2,984
  • 5
  • 8
  • Thanks for your response. I had actually looked at the blogs you pointed out and thats what got me interested in exploring Vespa as an alternative to host my neural model. It seems from your response that my model cannot be hosted in Vespa and used for reranking. – Ashish Jul 12 '18 at 04:35
  • 1
    That's correct. You can plug in your own reranking code in Java to rerank the returned documents inn this way, but you cannot evaluate such models distributed on the content nodes (which is what is configured in ranking expressions). – Jon Jul 12 '18 at 17:12