mirror of
https://github.com/discourse/discourse-ai.git
synced 2025-11-01 15:08:38 +00:00
2c0f535bab
* FEATURE: HyDE-powered semantic search. It relies on the new outlet added on discourse/discourse#23390 to display semantic search results in an unobtrusive way. We'll use a HyDE-backed approach for semantic search, which consists on generating an hypothetical document from a given keywords, which gets transformed into a vector and used in a asymmetric similarity topic search. This PR also reorganizes the internals to have less moving parts, maintaining one hierarchy of DAOish classes for vector-related operations like transformations and querying. Completions and vectors created by HyDE will remain cached on Redis for now, but we could later use Postgres instead. * Missing translation and rate limiting --------- Co-authored-by: Roman Rizzi <rizziromanalejandro@gmail.com>
28 lines
652 B
Ruby
28 lines
652 B
Ruby
# frozen_string_literal: true
|
|
|
|
module DiscourseAi
|
|
module Embeddings
|
|
module HydeGenerators
|
|
class Llama2Ftos < DiscourseAi::Embeddings::HydeGenerators::Llama2
|
|
def prompt(search_term)
|
|
<<~TEXT
|
|
### System:
|
|
You are a helpful bot
|
|
You create forum posts about a given topic
|
|
|
|
### User:
|
|
Topic: #{search_term}
|
|
|
|
### Assistant:
|
|
Here is a forum post about the above topic:
|
|
TEXT
|
|
end
|
|
|
|
def models
|
|
%w[StableBeluga2 Upstage-Llama-2-*-instruct-v2]
|
|
end
|
|
end
|
|
end
|
|
end
|
|
end
|