Closed gerhardcit closed 7 months ago
Workers AI
https://developers.cloudflare.com/workers-ai/tutorials/build-a-retrieval-augmented-generation-ai/
You are using: @cf/meta/llama-2-7b-chat-int8 in the general query, but using cf/baai/bge-base-en-v1.5 in the pp.post('/notes', async (c) => { sections
@cf/meta/llama-2-7b-chat-int8
cf/baai/bge-base-en-v1.5
pp.post('/notes', async (c) => {
and no explanation why and how the ai.run paramaters are different for the two.
ai.run
Can you explain the reasons why better and assist in deciding which models to use in which use cases.
No response
Howdy @gerhardcit, apologies this took a while to get to, but updated the tutorial to provide more details around the distinctions between the two models (and why they're used).
Which Cloudflare product does this pertain to?
Workers AI
Existing documentation URL(s)
https://developers.cloudflare.com/workers-ai/tutorials/build-a-retrieval-augmented-generation-ai/
What changes are you suggesting?
You are using:
@cf/meta/llama-2-7b-chat-int8
in the general query, but usingcf/baai/bge-base-en-v1.5
in thepp.post('/notes', async (c) => {
sectionsand no explanation why and how the
ai.run
paramaters are different for the two.Can you explain the reasons why better and assist in deciding which models to use in which use cases.
Additional information
No response