Varun Srinivasan
@v
A public good that would be really useful is a public dataset of embeddings for casts. Assuming it's legal to do, would drastically reduce the cost of building embeddings based models on Farcaster
11 replies
56 recasts
108 reactions
borodutch
@warpcastadmin.eth
like get a cast, it's embeds, and return head og tags for each embed (url)?
1 reply
0 recast
0 reaction
Varun Srinivasan
@v
no, i mean like vector embeddings for the text
2 replies
0 recast
1 reaction
shoni.eth
@alexpaden
What are you using the embeddings for in training- it's typically search and classification llm fine tuning and new training uses raw text i can provide snapshots if someone would like but custom transformations then embedded are where the value would be.. embedding every raw cast is a lot less useful imo
0 reply
0 recast
0 reaction
