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
270
3
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
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
More Decks by とすり
See All by とすり
AWS IoT GreengrassとRaspberry Piを使って、怠惰な生活検知システムを作る
tosuri13
0
37
Amazon Bedrockを活用したRAGの品質管理パイプライン構築
tosuri13
5
1.2k
Honoを使ったリモートMCPサーバでAIツールとの連携を加速させる!
tosuri13
1
310
S3 VectorsとStrands Agentsを利用したAgentic RAGシステムの構築
tosuri13
6
750
GraphRAGの仕組みまるわかり
tosuri13
10
1.8k
NL2SQLを活用したExcelの生成AI利用アプローチ
tosuri13
0
130
AWS Chaliceで始める爆速サーバレスチャットボット開発!!
tosuri13
1
320
Amazon BedrockでサーバレスなAIお料理ボットを作成する!!
tosuri13
3
700
React + TextAliveでカッコいいLyric Applicatioinを作ろう!!
tosuri13
1
960
Featured
See All Featured
The AI Revolution Will Not Be Monopolized: How open-source beats economies of scale, even for LLMs
inesmontani
PRO
3
3.7k
The MySQL Ecosystem @ GitHub 2015
samlambert
251
13k
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
28
3.6k
How to Think Like a Performance Engineer
csswizardry
28
2.7k
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
smashingmag
254
22k
Claude Code どこまでも/ Claude Code Everywhere
nwiizo
65
57k
A Modern Web Designer's Workflow
chriscoyier
698
190k
Conquering PDFs: document understanding beyond plain text
inesmontani
PRO
4
2.9k
Exploring the relationship between traditional SERPs and Gen AI search
raygrieselhuber
PRO
2
4.2k
Optimising Largest Contentful Paint
csswizardry
37
3.8k
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
141
35k
Keith and Marios Guide to Fast Websites
keithpitt
413
23k
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