Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
RAGの精度が全然上がらない!! AOSSを使った社内RAG開発の反省
Search
とすり
December 13, 2024
2
180
RAGの精度が全然上がらない!! AOSSを使った社内RAG開発の反省
とすり
December 13, 2024
Tweet
Share
More Decks by とすり
See All by とすり
AWS Chaliceで始める爆速サーバレスチャットボット開発!!
tosuri13
1
130
Amazon BedrockでサーバレスなAIお料理ボットを作成する!!
tosuri13
3
520
React + TextAliveでカッコいいLyric Applicatioinを作ろう!!
tosuri13
1
590
Radix UI & shadcn/uiのススメ
tosuri13
0
120
Amazon BedrockとOpenSearch Serviceでなんでも答えられる社内RAGを作成する!!
tosuri13
3
520
Featured
See All Featured
Large-scale JavaScript Application Architecture
addyosmani
511
110k
How to train your dragon (web standard)
notwaldorf
91
5.8k
Designing Experiences People Love
moore
140
23k
Fireside Chat
paigeccino
34
3.2k
Thoughts on Productivity
jonyablonski
69
4.5k
Dealing with People You Can't Stand - Big Design 2015
cassininazir
366
25k
Save Time (by Creating Custom Rails Generators)
garrettdimon
PRO
29
1k
Building a Scalable Design System with Sketch
lauravandoore
461
33k
[RailsConf 2023] Rails as a piece of cake
palkan
53
5.2k
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
133
33k
Stop Working from a Prison Cell
hatefulcrawdad
267
20k
Code Reviewing Like a Champion
maltzj
521
39k
Transcript
RAGͷਫ਼͕શવ্͕Βͳ͍!! AOSSΛͬͨࣾRAG։ൃͷল 2024.12.13 JAWS-UG ਆށ #3 ΕେLTେձ @tosuri13
ͱ͢Γ @tosuri13 MOTEXגࣜձࣾ ࡶ༻ܥΤϯδχΞ(ࣗশ) Stor a ge Browser for Am
a zon S3Λ Amplifyൈ͖Ͱ͑ͳ͍͔ࡧதͰ͢🥺
ࣾจॻΛѻ͑ΔRAGγεςϜΛAWSͰ։ൃɾӡ༻த… RAGͷਫ਼্ʹେۤઓ!! ՝লϙΠϯτʹ͍͍ͭͯͨ͠ͱࢥ͍·͢ ↑ ࠓ7݄ͷBedrock Night in େࡕͰͨ͠RAGγεςϜͰ͢☺
ͬ͘͟Γݱঢ়ͷAWSߏਤ
RAGͷਫ਼͕શવ্͕Βͳ͍!!
AOSSʹυΩϡϝϯτΛେྔೖͯ͠ӡ༻։࢝!! → ͔͠͠ظ͢Δճ͕શવฦͬͯ͜ͳ͍!! ݪҼΛ୳Δ͜ͱʹ… ͜ͷػೳ͕Ճ͞Εͨͷͬͯ Ͳͷόʔδϣϯ͔Β? ͳͳ Βͳ͍Ͱ͢ ࣾRAGϘοτ
RAGʹ͓͍ͯҰ൪ॏཁͳϑΣʔζͲ͔͜? https:// a ws. a m a zon.com/jp/blogs/news/ a -pr
a ctic a l-guide-to-improve-r a g-systems-with- a dv a nced-r a g-on- a ws ΑΓҾ༻
https:// a ws. a m a zon.com/jp/blogs/news/ a -pr a
ctic a l-guide-to-improve-r a g-systems-with- a dv a nced-r a g-on- a ws ΑΓҾ༻ ҰൠతʹRetrieveॲཧͩͱݴΘΕ͍ͯΔ (ແؔͳσʔλΛͯ͠͠·͏ͱɺͲΕ͚ͩᘳͳLLMͰదͳճ͕Ͱ͖ͳ͍ͨΊ)
ͦͷͨΊɺRetrieveॲཧΛ࠷దԽ͢ΔΑ͏ʹ ༷ʑͳΞϓϩʔνͰ࣮ݧɺௐࠪΛॏͶΔ… Am a zon BedrockͷຒΊࠐΈϞσϧΛม͑ͯΈͨΓ… (EmbeddingҎ֎ʹϝλσʔλΛೖΕͨΓ) AOSSͷANNϥΠϒϥϦΛม͑ͨΓ HNSWͷύϥϝʔλΛ͍͔͍ͭͬͯ͘͡ΈͨΓ… F
a iss͔nmslib͔…
ͦͷͨΊɺRetrieveॲཧΛ࠷దԽ͢ΔΑ͏ʹ ༷ʑͳΞϓϩʔνͰ࣮ݧɺௐࠪΛॏͶΔ… Am a zon BedrockͷຒΊࠐΈϞσϧΛม͑ͯΈͨΓ… (EmbeddingҎ֎ʹϝλσʔλΛೖΕͨΓ) AOSSͷANNϥΠϒϥϦΛม͑ͨΓ HNSWͷύϥϝʔλΛ͍͔͍ͭͬͯ͘͡ΈͨΓ… F
a iss͔nmslib͔… …͕!! ճશવվળ͞Εͳ͍!!
ճͷ࣭ԼΛট͍͍ͯͨຊͷݪҼ… https:// a ws. a m a zon.com/jp/blogs/news/ a -pr
a ctic a l-guide-to-improve-r a g-systems-with- a dv a nced-r a g-on- a ws ΑΓҾ༻
ͩͬͨ͜͜!! https:// a ws. a m a zon.com/jp/blogs/news/ a -pr
a ctic a l-guide-to-improve-r a g-systems-with- a dv a nced-r a g-on- a ws ΑΓҾ༻
ݪҼௐࠪΛਐΊΔ্Ͱ͔ͬͨͷ… ʮͦͦͷυΩϡϝϯτ͕͓͔͍͠!!ʯͱ͍͏͜ͱ ֦ுࢠͱ࣮ࡍͷத͕ Կނ͔ҧ͏ϑΝΠϧ ΫΫΫ… ↑ mdʹٖଶ͢Δxml ωਃExcelͷଘࡏ (ҳ͍ͨ͠ํͷExcelγʔτ) ແҙຯͳใͰ
ຒΊਚ͘͞ΕͨHTML ϦϯΫେྔʹ࣋ͬͯ·͢
ݪҼௐࠪΛਐΊΔ্Ͱ͔ͬͨͷ… ʮͦͦͷυΩϡϝϯτ͕͓͔͍͠!!ʯͱ͍͏͜ͱ ֦ுࢠͱ࣮ࡍͷத͕ Կނ͔ҧ͏ϑΝΠϧ ΫΫΫ… ↑ mdʹٖଶ͢Δxml ωਃExcelͷଘࡏ (ҳ͍ͨ͠ํͷExcelγʔτ) ແҙຯͳใͰ
ຒΊਚ͘͞ΕͨHTML ϦϯΫେྔʹ࣋ͬͯ·͢ ݕࡧͷϊΠζʹͳΓɺదͳσʔλΛ ఏڙͰ͖ͳ͘ͳ͍ͬͯΔ!!
લॲཧ + νϟϯΩϯάΛ͘ݟ͍ͯͨͷ͕ݪҼ!! (L a ngCh a inඋ͚͑ͷϩʔμʔʹॲཧΛؙ͍ͤͯͨ͠ѱ͔ͬͨ…) ݕূ࣌ ࣮ӡ༻࣌
͋Δఔ៉ྷͳυΩϡϝϯτΛ ͬͯݕূͨͨ͠Ίʹؾ͚ͣ… શવେৎͩͳ!! ࣮ࡍͷυΩϡϝϯτۄੴࠞަঢ়ଶ!! اۀͷ࣮ଶʹԊͬͨॲཧΛΉඞཁ͕͋Δ
֤υΩϡϝϯτͱਅʹ͖߹͍ ͦΕͧΕ࠷దͳܗͰม͍ͯ͘͠ॲཧΛߦͳͬͨ ࣄલʹυΩϡϝϯτΛ֬ೝ͠ ѻ͑ͳ͍ͷೖΕͳ͍ தXML͡ΌΜ!! ωਃ͔Β͑Δ෦Λநग़ LLMͰཁͯ͠Ϩίʔυܗࣜʹ BS4Ͱղੳͯ͠ ෆཁͳλάΛΫϦʔχϯά
͢ΔͱɺಛʹߏઃఆมΘ͍ͬͯͳ͍ͷʹ ظ͢Δճ͕͑ΔΑ͏ʹͳͬͨ!! ͜ͷػೳ͕Ճ͞Εͨͷͬͯ Ͳͷόʔδϣϯ͔Β? όʔδϣϯX.X͔ΒͰ͢ ࣾRAGϘοτ ͍͍ײ͡ͷػೳ͕૿͑·ͨ͠
None
·ͱΊ
ɾAIٕज़ཁૉʹਅʹ͖߹͓͏!! ɾRAGΛݕ౼͢ΔલʹυΩϡϝϯτཧΛ!! → ͦͦRAGΛΘͣͱɺ͙͢ʹυΩϡϝϯτΛݟ͚ͭΒΕΔঢ়ଶ͕·͍͠Ͱ͢ → ීஈ͔Β៉ྷͳυΩϡϝϯτΛॻ͖·͠ΐ͏!! → લॲཧΛͤͣʹదʹಥͬࠐΉͱμϝͩͱ͍͏ͷ͕Α͔͘Γ·ͨ͠ → طଘͷAIαʔϏεͤͰͳ͘ɺటष͍͍ͯ͘ͷͰਅʹ͖߹͏͜ͱ͕େࣄͰͨ͠
Th a nk you for listening!! @tosuri13 ← Α͔ͬͨΒTwitterϑΥϩʔͯ͠Ͷ