Nick Weiland
Nick Weiland
@seuros long delay here :) but I added to changelog. Can we could get this pr merged?
The existing `Rails/EnumHash` cop also doesn't work well with Postgres enums as it auto converts arrays of strings to hashes with integers as values.
Shouldn't the cache layer be as simple as hashing the inputs to the api calls and caching the results that way? GPTCache looks like it's solving for a semantic cache...
Connection pool issue when using Blazer with a read replica and Rails automatic connection switching
@bdschultzAU it actually ended up not working. We ended up moving Blazer back to the primary for now.
Connection pool issue when using Blazer with a read replica and Rails automatic connection switching
Closed because we changed our reporting infra, but I think this is still a problem.
The docs here work, but the confusing part is that json mode only works when using Vertex. https://ai.google.dev/gemini-api/docs/api-overview#json i.e. ```ruby client.generate_content( contents: messages, system_instructions: options[:system_message], generation_config: { response_mime_type: "application/json" }...
Heads up: Using JSON schema in the generation config only works with Pro. "While Gemini 1.5 Flash models only accept a text description of the JSON schema you want returned,...