discourse
/
discourse-ai
mirror of https://github.com/discourse/discourse-ai.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

FEATURE: Respect search filters in semantic search (#220) 

* FEATURE: Respect search filters in semantic search

* lint
This commit is contained in:
Rafael dos Santos Silva 2023-09-12 16:16:33 -03:00 committed by GitHub
parent 50d7289623
commit 2c87bb0d99
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 8 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
lib/modules/embeddings/semantic_search.rb
View File

@ -30,15 +30,17 @@ module DiscourseAi
end
def search_for_topics(query, page = 1)
max_results_per_page = 50
max_results_per_page = 100
limit = [Search.per_filter, max_results_per_page].min + 1
offset = (page - 1) * limit
search = Search.new(query, { guardian: guardian })
search_term = search.term
strategy = DiscourseAi::Embeddings::Strategies::Truncation.new
vector_rep =
DiscourseAi::Embeddings::VectorRepresentations::Base.current_representation(strategy)
digest = OpenSSL::Digest::SHA1.hexdigest(query)
digest = OpenSSL::Digest::SHA1.hexdigest(search_term)
hyde_key = build_hyde_key(digest, SiteSetting.ai_embeddings_semantic_search_hyde_model)
embedding_key =
@ -53,7 +55,7 @@ module DiscourseAi
.cache
.fetch(hyde_key, expires_in: 1.week) do
hyde_generator = DiscourseAi::Embeddings::HydeGenerators::Base.current_hyde_model.new
hyde_generator.hypothetical_post_from(query)
hyde_generator.hypothetical_post_from(search_term)
end
hypothetical_post_embedding =
@ -76,7 +78,9 @@ module DiscourseAi
.where(topic_id: candidate_topic_ids, post_number: 1)
.order("array_position(ARRAY#{candidate_topic_ids}, topic_id)")
guardian.filter_allowed_categories(semantic_results)
query_filter_results = search.apply_filters(semantic_results)
guardian.filter_allowed_categories(query_filter_results)
end
private