WordPress Search & Recommendations

The shortest explanation on how to build embeddings for queries and documents at scale with Vespa ! 馃槏

Table of Contents

1. Download and convert to onnx any Hugging Face聽sentence transformer model(s)

2. Declare the model(s) with an id in services.xml

=> id=”bert”

3. Use the model(s) id to declare tensor field(s) built from any text field(s)

=> indexing: input myTextField | embed bert

4. Deploy the application package on docker or Vespa cloud

5. Use the model(s) id to embed the query text

=> input.query(myEmbedding)=embed(bert, “Hello world”)

6. Use ranking(s) to build mixed BM25/ANN expressions

Read the post from Vespa blog:聽https://blog.vespa.ai/text-embedding-made-simple/

WPSOLR with Vespa:聽https://www.wpsolr.com


Read more related content