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
200
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
GraphRAGの仕組みまるわかり
tosuri13
9
610
NL2SQLを活用したExcelの生成AI利用アプローチ
tosuri13
0
64
AWS Chaliceで始める爆速サーバレスチャットボット開発!!
tosuri13
1
220
Amazon BedrockでサーバレスなAIお料理ボットを作成する!!
tosuri13
3
630
React + TextAliveでカッコいいLyric Applicatioinを作ろう!!
tosuri13
1
720
Radix UI & shadcn/uiのススメ
tosuri13
0
150
Amazon BedrockとOpenSearch Serviceでなんでも答えられる社内RAGを作成する!!
tosuri13
4
720
Featured
See All Featured
JavaScript: Past, Present, and Future - NDC Porto 2020
reverentgeek
50
5.5k
Embracing the Ebb and Flow
colly
87
4.8k
個人開発の失敗を避けるイケてる考え方 / tips for indie hackers
panda_program
110
20k
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
36
2.5k
Easily Structure & Communicate Ideas using Wireframe
afnizarnur
194
16k
CSS Pre-Processors: Stylus, Less & Sass
bermonpainter
358
30k
The Straight Up "How To Draw Better" Workshop
denniskardys
236
140k
Thoughts on Productivity
jonyablonski
69
4.8k
Automating Front-end Workflow
addyosmani
1370
200k
Code Reviewing Like a Champion
maltzj
525
40k
Unsuck your backbone
ammeep
671
58k
GraphQLとの向き合い方2022年版
quramy
49
14k
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