6 Commits

Author	SHA1	Message	Date
arcticfly	6fb7a82d72	Add support for switching to Llama models (#80) ... * Add support for switching to Llama models * Fix prettier	2023-07-21 20:10:59 -07:00
Kyle Corbitt	741128e0f4	Better division of labor between frontend and backend model providers ... A bit better thinking on which types go where.	2023-07-21 11:49:35 -07:00
Kyle Corbitt	7e1fbb3767	Slightly better typings for ModelProviders ... Still not great because the `any`s loosen some call sites up more than I'd like, but better than the broken types before.	2023-07-21 06:50:05 -07:00
Kyle Corbitt	847753c32b	replicate/llama2 provider ... Still need to fix the types but it runs	2023-07-20 19:55:03 -07:00
Kyle Corbitt	332a2101c0	More work on modelProviders ... I think everything that's OpenAI-specific is inside modelProviders at this point, so we can get started adding more providers.	2023-07-20 18:54:26 -07:00
Kyle Corbitt	ded6678e97	Prep for more model providers ... Adds a `modelProvider` field to `promptVariants`, currently just set to "openai/ChatCompletion" for all variants for now. Adds a `modelProviders/` directory where we can define and store pluggable model providers. Currently just OpenAI. Not everything is pluggable yet -- notably the code to actually generate completions hasn't been migrated to this setup yet. Does a lot of work to get the types working. Prompts are now defined with a function `definePrompt(modelProvider, config)` instead of `prompt = config`. Added a script to migrate old prompt definitions. This is still partial work, but the diff is large enough that I want to get it in. I don't think anything is broken but I haven't tested thoroughly.	2023-07-20 14:49:22 -07:00