Slackbot
12/13/2023, 9:40 AMDavid Paulsson
12/13/2023, 9:40 AMKishore Nallan
12/13/2023, 9:51 AMKishore Nallan
12/13/2023, 9:51 AMKishore Nallan
12/13/2023, 9:52 AMDavid Paulsson
12/21/2023, 12:22 PM{
name: 'embedding',
type: 'float[]',
num_dim: embeddingsData[0].embedding.length,
optional: true,
},
embeddingsData is an array like this { sku: string, embedding: number[] }[]
so my problem is that I'm running out of memory on typesense cloud now. sure these embedding fields are quite large (the generated .json file with my embeddings are 25.5 MB). any tricks to lower memory usage?David Paulsson
12/21/2023, 12:25 PMKishore Nallan
12/21/2023, 1:01 PMDavid Paulsson
12/21/2023, 1:16 PMKishore Nallan
12/21/2023, 1:19 PMe5-small is good. There are some newer models which claim to be better but getting hard to believe the benchmarks because some models are suspected of training on benchmark data. E5 family is from Microsoft so it's reliable.David Paulsson
12/21/2023, 8:12 PM