Skip to content

Latest commit

 

History

History
45 lines (34 loc) · 2.26 KB

README.md

File metadata and controls

45 lines (34 loc) · 2.26 KB

Vespa

You can use the vespa.ai cloud service, or download and run Vespa with Docker.

Make sure you configure Docker with at least 4GB RAM.

docker info | grep "Total Memory" # make sure it's at least 4Gb
docker pull vespaengine/vespa

Start Vespa.

docker run --detach --name vespa --hostname vespa-container \
  --publish 8080:8080 --publish 19071:19071 \
  vespaengine/vespa

Deploy the sample application and schema.

(cd vector-app && zip -r - .) | \
  curl --header Content-Type:application/zip --data-binary @- \
  localhost:19071/application/v2/tenant/default/prepareandactivate

curl --header Content-Type:application/zip -XPOST localhost:19071/application/v2/tenant/default/session

Finally, run the Vespa sample ingestion and search. You might have to wait for a few seconds for the endpoint to be ready after the last command.

poetry install
ENDPOINT=http://localhost:8080 CONFIG_ENDPOINT=http://localhost:19071 poetry run ./hello.py

> POST http://localhost:8080/document/v1/vector/vector/docid/vec1
< POST http://localhost:8080/document/v1/vector/vector/docid/vec1 - 200
> POST http://localhost:8080/document/v1/vector/vector/docid/vec2
< POST http://localhost:8080/document/v1/vector/vector/docid/vec2 - 200
> GET http://localhost:8080/search/?yql=select%20%2A%20from%20sources%20%2A%20where%20%7BtargetHits%3A%201%7D%20nearestNeighbor%28values%2Cvector_query_embedding%29&ranking.profile=vector_similarity&hits=1&input.query%28vector_query_embedding%29=%5B0.1%2C0.2%2C0.3%5D
< GET http://localhost:8080/search/?yql=select%20%2A%20from%20sources%20%2A%20where%20%7BtargetHits%3A%201%7D%20nearestNeighbor%28values%2Cvector_query_embedding%29&ranking.profile=vector_similarity&hits=1&input.query%28vector_query_embedding%29=%5B0.1%2C0.2%2C0.3%5D - 200
{'sddocname': 'vector', 'documentid': 'id:vector:vector::vec1', 'id': 'vec1', 'values': {'type': 'tensor<float>(x[3])', 'values': [0.10000000149011612, 0.20000000298023224, 0.30000001192092896]}, 'metadata': {'genre': 'drama'}}
> DELETE http://localhost:19071/application/v2/tenant/default/application/default
< DELETE http://localhost:19071/application/v2/tenant/default/application/default - 200