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
190
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
NL2SQLを活用したExcelの生成AI利用アプローチ
tosuri13
0
5
AWS Chaliceで始める爆速サーバレスチャットボット開発!!
tosuri13
1
190
Amazon BedrockでサーバレスなAIお料理ボットを作成する!!
tosuri13
3
570
React + TextAliveでカッコいいLyric Applicatioinを作ろう!!
tosuri13
1
660
Radix UI & shadcn/uiのススメ
tosuri13
0
140
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
640
Featured
See All Featured
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
29
9.5k
XXLCSS - How to scale CSS and keep your sanity
sugarenia
248
1.3M
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
331
21k
Documentation Writing (for coders)
carmenintech
71
4.8k
Become a Pro
speakerdeck
PRO
28
5.3k
Making the Leap to Tech Lead
cromwellryan
133
9.3k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
5
600
Understanding Cognitive Biases in Performance Measurement
bluesmoon
29
1.7k
Building an army of robots
kneath
306
45k
Writing Fast Ruby
sferik
628
61k
Statistics for Hackers
jakevdp
799
220k
The Straight Up "How To Draw Better" Workshop
denniskardys
233
140k
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