Hugging Face bge-large-en 임베딩 설정? -> RAG 봇 응답 없음!

지원
, ,
1

자문드립니다. bge-large-en 임베딩 모델을 Discourse AI의 기본 벡터 서비스로 작동시키려면 어떤 설정이 가장 좋은가요?

AWS에서 bge-large-en 인스턴스를 실행 중이며, Discourse AI가 해당 인스턴스와 통신하고 있다는 것을 알고 있습니다(아래 테스트 참조). 그러나 임베딩이 일반적으로 작동하지 않습니다(OpenAI 임베딩은 정상적으로 작동합니다).

문제 요약: 임베딩을 HF bge-large-en으로 설정하면 RAG 봇이 응답하지 않습니다

AWS 임베딩 모델은 다음과 같습니다:

image
image1260×535 54 KB

Discourse AI 설정은 다음과 같습니다:

image
image920×338 35.1 KB

image
image946×185 16.1 KB

연결성을 확인하기 위한 Discourse 커스텀 LLM ‘테스트 실행’ 결과입니다:

image
image1106×151 14.7 KB

AWS 측의 bge-large-en 로그는 다음과 같습니다:

image
image1089×132 5.78 KB

감사합니다!!

에러 로그는 다음과 같습니다..

Job exception: can't quote Array

hostname ai-qa-ubuntu-s-1vcpu-2gb-amd-sfo3-01-app
process_id 1165935
application_version f9192835a7e4d2067c3d1844f43f9e7b69de39e7
current_db default
current_hostname ai-qa.net
job Jobs::CreateAiReply
problem_db default
time 7:22 pm
opts post_id 618
--- --- --- ---
--- ---
bot_user_id -1208
persona_id 5
current_site_id default


Backtrace

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8.1/lib/active_record/connection_adapters/abstract/quoting.rb:25:in `quote'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8.1/lib/active_record/connection_adapters/postgresql/quoting.rb:69:in `quote'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8.1/lib/active_record/connection_adapters/abstract/quoting.rb:51:in `quote_bound_value'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8.1/lib/active_record/sanitization.rb:193:in `block in quote_bound_value'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8.1/lib/active_record/sanitization.rb:193:in `map!'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8.1/lib/active_record/sanitization.rb:193:in `quote_bound_value'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8.1/lib/active_record/sanitization.rb:171:in `replace_bind_variable'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8.1/lib/active_record/sanitization.rb:180:in `block in replace_named_bind_variables'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8.1/lib/active_record/sanitization.rb:176:in `gsub'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8.1/lib/active_record/sanitization.rb:176:in `replace_named_bind_variables'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8.1/lib/active_record/sanitization.rb:128:in `sanitize_sql_array'
/var/www/discourse/lib/mini_sql_multisite_connection.rb:21:in `public_send'
/var/www/discourse/lib/mini_sql_multisite_connection.rb:21:in `encode'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/mini_sql-1.5.0/lib/mini_sql/connection.rb:64:in `to_sql'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/mini_sql-1.5.0/lib/mini_sql/postgres/connection.rb:202:in `run'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/mini_sql-1.5.0/lib/mini_sql/active_record_postgres/connection.rb:38:in `block in run'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/mini_sql-1.5.0/lib/mini_sql/active_record_postgres/connection.rb:34:in `block in with_lock'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activesupport-7.0.8.1/lib/active_support/concurrency/load_interlock_aware_monitor.rb:25:in `handle_interrupt'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activesupport-7.0.8.1/lib/active_support/concurrency/load_interlock_aware_monitor.rb:25:in `block in synchronize'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activesupport-7.0.8.1/lib/active_support/concurrency/load_interlock_aware_monitor.rb:21:in `handle_interrupt'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activesupport-7.0.8.1/lib/active_support/concurrency/load_interlock_aware_monitor.rb:21:in `synchronize'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/mini_sql-1.5.0/lib/mini_sql/active_record_postgres/connection.rb:34:in `with_lock'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/mini_sql-1.5.0/lib/mini_sql/active_record_postgres/connection.rb:38:in `run'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/mini_sql-1.5.0/lib/mini_sql/postgres/connection.rb:99:in `query'
/var/www/discourse/plugins/discourse-ai/lib/embeddings/vector_representations/base.rb:272:in `asymmetric_rag_fragment_similarity_search'
/var/www/discourse/plugins/discourse-ai/lib/ai_bot/personas/persona.rb:286:in `rag_fragments_prompt'
/var/www/discourse/plugins/discourse-ai/lib/ai_bot/personas/persona.rb:156:in `craft_prompt'
/var/www/discourse/plugins/discourse-ai/lib/ai_bot/bot.rb:54:in `reply'
/var/www/discourse/plugins/discourse-ai/lib/ai_bot/playground.rb:424:in `reply_to'
/var/www/discourse/plugins/discourse-ai/app/jobs/regular/create_ai_reply.rb:18:in `execute'
/var/www/discourse/app/jobs/base.rb:305:in `block (2 levels) in perform'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/rails_multisite-6.0.0/lib/rails_multisite/connection_management/null_instance.rb:49:in `with_connection'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/rails_multisite-6.0.0/lib/rails_multisite/connection_management.rb:21:in `with_connection'
/var/www/discourse/app/jobs/base.rb:292:in `block in perform'
/var/www/discourse/app/jobs/base.rb:288:in `each'
/var/www/discourse/app/jobs/base.rb:288:in `perform'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/sidekiq-6.5.12/lib/sidekiq/processor.rb:202:in `execute_job'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/sidekiq-6.5.12/lib/sidekiq/processor.rb:170:in `block (2 levels) in process'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/sidekiq-6.5.12/lib/sidekiq/middleware/chain.rb:177:in `block in invoke'
/var/www/discourse/lib/sidekiq/pausable.rb:132:in `call'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/sidekiq-6.5.12/lib/sidekiq/middleware/chain.rb:179:in `block in invoke'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/sidekiq-6.5.12/lib/sidekiq/middleware/chain.rb:182:in `invoke'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/sidekiq-6.5.12/lib/sidekiq/processor.rb:169:in `block in process'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/sidekiq-6.5.12/lib/sidekiq/processor.rb:136:in `block (6 levels) in dispatch'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/sidekiq-6.5.12/lib/sidekiq/job_retry.rb:113:in `local'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/sidekiq-6.5.12/lib/sidekiq/processor.rb:135:in `block (5 levels) in dispatch'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/sidekiq-6.5.12/lib/sidekiq.rb:44:in `block in <module:Sidekiq>'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/sidekiq-6.5.12/lib/sidekiq/processor.rb:131:in `block (4 levels) in dispatch'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/sidekiq-6.5.12/lib/sidekiq/processor.rb:263:in `stats'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/sidekiq-6.5.12/lib/sidekiq/processor.rb:126:in `block (3 levels) in dispatch'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/sidekiq-6.5.12/lib/sidekiq/job_logger.rb:13:in `call'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/sidekiq-6.5.12/lib/sidekiq/processor.rb:125:in `block (2 levels) in dispatch'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/sidekiq-6.5.12/lib/sidekiq/job_retry.rb:80:in `global'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/sidekiq-6.5.12/lib/sidekiq/processor.rb:124:in `block in dispatch'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/sidekiq-6.5.12/lib/sidekiq/job_logger.rb:39:in `prepare'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/sidekiq-6.5.12/lib/sidekiq/processor.rb:123:in `dispatch'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/sidekiq-6.5.12/lib/sidekiq/processor.rb:168:in `process'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/sidekiq-6.5.12/lib/sidekiq/processor.rb:78:in `process_one'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/sidekiq-6.5.12/lib/sidekiq/processor.rb:68:in `run'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/sidekiq-6.5.12/lib/sidekiq/component.rb:8:in `watchdog'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/sidekiq-6.5.12/lib/sidekiq/component.rb:17:in `block in safe_thread'
3

알려주셔서 감사합니다. 확인해 보겠습니다!

4

다음 명령어를 Rails 콘솔에서 실행하면 어떤 출력이 발생합니까?

strategy = DiscourseAi::Embeddings::Strategies::Truncation.new
vector_rep = DiscourseAi::Embeddings::VectorRepresentations::Base.current_representation(strategy)
vector_rep.vector_from("test")

또한, 우리의 API는 문서에 따라 사용자가 GitHub - huggingface/text-embeddings-inference: A blazing fast inference solution for text embeddings models · GitHub 를 직접 실행하는 환경에서 동작하도록 설계되어 있으므로, 호스팅된 버전에서는 작동하지 않을 수 있습니다.

스택 트레이스(backtrace)를 제공해 주시면 작동하도록 조사해 보겠습니다.

5

@Falco

bge-large-en을 AWS 전용 엔드포인트 인스턴스에 임베딩 모델로 구성하여 테스트 코드를 실행했을 때 다음과 같은 상황이 발생했습니다.

image
image833×121 9.63 KB

root@studyqa-ubuntu-s-1vcpu-2gb-amd-sfo3-01-app:/var/www/discourse# rails c

[1] pry(main)> strategy = DiscourseAi::Embeddings::Strategies::Truncation.new

puts "Strategy initialized"

vector_rep = DiscourseAi::Embeddings::VectorRepresentations::Base.current_representation(strategy)

puts "Vector representation obtained"

vector = vector_rep.vector_from("test")

[1] pry(main)> strategy = DiscourseAi::Embeddings::Strategies::Truncation.new

puts "Strategy initialized"

vector_rep = DiscourseAi::Embeddings::VectorRepresentations::Base.current_representation(strategy)

puts "Vector representation obtained"

vector = vector_rep.vector_from("test")

puts "Vector generated"

puts vector.inspect

Strategy initialized

Vector representation obtained

Vector generated

[:embeddings, [-0.0020444912370294333, 0.008787356317043304, -0.010865539312362671, 0.01865551434457302, -0.02099628746509552, -0.009864491410553455, -0.0011329081607982516, 0.02949545904994011, 0.027839021757245064, 0.043966952711343765, 0.0406080037355423, 0.0016647017328068614, 0.007204003632068634, -0.03770752251148224, -0.025242917239665985, -0.0015279072104021907, -0.02805529721081257, -0.020901955664157867, -0.029206447303295135, -0.006209365092217922, -0.02105099707841873,

등등.

aws의 bge-large-en을 호출하는 것으로 보입니다:

- 2024-05-29T13:57:34.609+00:00 Batches: 0%| | 0/1 [00:00<?, ?it/s] Batches: 100%|██████████| 1/1 [00:00<00:00, 4.80it/s] Batches: 100%|██████████| 1/1 [00:00<00:00, 4.79it/s]

• 2024/05/29 09:57:34
INFO | POST / | Duration: 212.84 ms


- 2024-05-29T13:57:53.806+00:00 Batches: 0%| | 0/1 [00:00<?, ?it/s] Batches: 100%|██████████| 1/1 [00:01<00:00, 1.97s/it] Batches: 100%|██████████| 1/1 [00:01<00:00, 1.97s/it]

• 2024/05/29 09:57:53
INFO | POST / | Duration: 1978.36 ms
6

그래서 지금은 정상적으로 작동하는 것 같나요?

아마도 문제가 리랭커(reranker) 때문일 수 있습니다. ai_hugging_face_tei_reranker_endpoint을 unset하고 RAG가 작동하는지 테스트해 보시겠어요?

7

reranker를 꺼놨고.. 아직 embedding도 없는데.. 양쪽 모두 이 메시지가 뜨고 있습니다:

Discourse LLM 실행 테스트:

모델에 연결을 시도했지만 다음 오류가 반환되었습니다: {“error”:“Body needs to provide a inputs key, recieved: b’{"model":"bge-large-en","temperature":0.7,"messages":[{"role":"system","content":"You are a helpful bot"},{"role":"user","content":"How much is 1 + 1?"}],"max_tokens":1009}'”}

bge-large-en 로그

• 2024/05/29 13:40:03

ERROR | Body needs to provide a inputs key, recieved: b’{“model”:“bge-large-en”,“temperature”:0.7,“messages”:[{“role”:“system”,“content”:“You are a helpful bot”},{“role”:“user”,“content”:“How much is 1 + 1?”}],“max_tokens”:1009}’

discourse b1b218aa99
discourse-ai d812ecf5

8

임베딩을 테스트하는 방식이 아닙니다. :slight_smile: 이는 임베딩 모델 테스트가 아니라 LLM 테스트이며, 숫자가 반환되기를 기대하는 임베딩 모델 테스트와는 다릅니다. LLM UI에서는 이 모델을 추가할 수 없으며, 아직 존재하지 않는 임베딩 전용 UI가 필요합니다. 임베딩 모델은 사이트 설정에서만 구성할 수 있습니다.

9

네. 그럴 수 있겠네요.

( LLM 실행 테스트를 “연결성” 확인(아래 참조)에만 사용했음을 언급하려고 했는데, 더 명확하게 설명했어야 했는데. )

image
image715×305 35.5 KB