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
LangChain Toolsの運用と改善
Search
peisuke
April 25, 2023
Technology
4
2.6k
LangChain Toolsの運用と改善
2023/4/25 LLM(GPT, PaLM等) with MLOps LT大会!!! 発表資料
peisuke
April 25, 2023
Tweet
Share
More Decks by peisuke
See All by peisuke
AI for Kids:小学生に画像認識を教えてみた話
peisuke
1
6
LangGraphで始めるマルチエージェントシステム
peisuke
13
4.2k
Self-RAG: Learning to Retrieve, Generate and Critique through Self-Reflections
peisuke
9
1.5k
Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields
peisuke
0
10k
GNeRF: GAN-based Neural Radiance Field without Posed Camera
peisuke
1
750
TTS Skins: Speaker Conversion via ASR
peisuke
0
390
A Quantum Computational Approach to Correspondence Problems on Point Sets
peisuke
0
690
F0-Consistent Many-to-many Non-parallel Voice Conversion via Conditional Autoencoder
peisuke
0
190
YOLACT real-time instance segmentation
peisuke
1
270
Other Decks in Technology
See All in Technology
運用しているアプリケーションのDBのリプレイスをやってみた
miura55
1
860
php-conference-nagoya-2025
fuwasegu
0
120
2025-02-21 ゆるSRE勉強会 Enhancing SRE Using AI
yoshiiryo1
1
430
PHPで印刷所に入稿できる名札データを作る / Generating Print-Ready Name Tag Data with PHP
tomzoh
0
160
短縮URLをお手軽に導入しよう
nakasho
0
120
CDKのコードを書く環境を作りました with Amazon Q
nobuhitomorioka
1
120
白金鉱業Meetup Vol.17_あるデータサイエンティストのデータマネジメントとの向き合い方
brainpadpr
7
940
ESXi で仮想化した ARM 環境で LLM を動作させてみるぞ
unnowataru
0
140
レビューを増やしつつ 高評価維持するテクニック
tsuzuki817
2
860
脳波を用いた嗜好マッチングシステム
hokkey621
0
220
Amazon S3 Tablesと外部分析基盤連携について / Amazon S3 Tables and External Data Analytics Platform
nttcom
0
150
ビジネスモデリング道場 目的と背景
masuda220
PRO
9
680
Featured
See All Featured
Music & Morning Musume
bryan
46
6.4k
Git: the NoSQL Database
bkeepers
PRO
427
65k
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
330
21k
Facilitating Awesome Meetings
lara
52
6.2k
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
21
2.5k
Put a Button on it: Removing Barriers to Going Fast.
kastner
60
3.7k
The Cost Of JavaScript in 2023
addyosmani
47
7.3k
Code Review Best Practice
trishagee
67
18k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
129
19k
Principles of Awesome APIs and How to Build Them.
keavy
126
17k
How to Think Like a Performance Engineer
csswizardry
22
1.4k
Building Adaptive Systems
keathley
40
2.4k
Transcript
LangChain Toolsͷӡ༻ͱվળ !QFJTVLF
ࣗݾհ ໊લɿ౻ຊ ܟհ ॴଐɿ"#&+"ʢ-BCTʣ ෭ۀɿ.-Λத৺ʹ૬ஊ͔Β։ൃ·Ͱͬͯ·͢ ੋඇ͓͕͚Լ͍͞ ׆ಈɿ5XJUUFS!QFJTVLF (JUIVC IUUQTHJUIVCDPNQFJTVLF 2JJUB
IUUQTRJJUBDPNQFJTVLF 4MJEF4IBSF IUUQTXXXTMJEFTIBSFOFU'VKJNPUP,FJTVLF গ͚ͩ͠ॻ͍ͯ·͢
ࠓճͷςʔϚʹ͍ͭͯ • --.୯ಠͩͱ༻్ʹݶք͕͋Γɺ֎෦πʔϧͱͷ࿈ܞ͕େࣄ • -BOH$IBJO5PPMTͷՄೳੑ͕ੌ͍ • 5PPMΛݺͼग़ͨ͢Ίʹઃఆ͢Δ%FTDSJQUJPOΛɺ.-ͷϊϦͰ ςετɾमਖ਼Λ͢ΔΈͷఏҊͱ࣮ݧ
--.ͷݶք • --.୯ಠͰ༻ͨ͠߹ͷݶք • ֶश͍ͤͯ͞ͳ͍σʔλʹରԠͰ͖ͳ͍ͨΊɺϦΞϧλΠϜͳ࣭ ઐతɾಠࣗͷ࣭ʹ͑ΒΕͳ͍ • ౦ژͷਓޱͱ͍ͬͨಛఆͷ࣭ʹ͍ͭͯޡͬͨճΛ͕ͪ͠ • ͍͔ʹͯ͠ޡͬͨճΛग़͞ͳ͍Α͏ʹͭͭ͠ɺ༗༻ͳ݁ՌΛ
ಘΔ͔͕ࠓޙͷ׆༻ͷϙΠϯτʹͳͬͯ͘Δ
ํ • ཁ݅తͳͱ͜Ζ • --.͕ճෆՄೳͳઐతͳࣝ˞ͷΞΫηε ˞࠷৽ͷใɺ࢛ଇԋࢉɺࣾͷφϨοδɺͦͷଞ༷ʑͳΈ • ͳΔ͘ޡͬͨճΛग़͞ͳ͍Α͏ʹ͢Δ • ղܾํ
• --.୯ಠͰΘͣɺͦͷଞͷΈͱ࿈ܞ͢Δ • ݕࡧͷΈͱΈ߹Θͤͨ-MBNB*OEFYͳͲ͕͋Δ
--.ͷࠓޙͷΘΕํͷఆ ཁɺ༁ φϨοδݕࡧ ϨίϝϯυͳͲ ϑΣʔζ̍ ϑΣʔζ̎ ϑΣʔζ̏ --.୯ಠͰͷར༻ खॱͷܾ·ͬͨλ εΫ
ϧʔϧϕʔεͰ--. ͱผϩδοΫͷΈ ߹Θͤ ॊೈʹෳϩδοΫ Λݺͼग़ͯ͠ར༻ ֓ཁ ಛ ۩ମྫ ֎෦φϨοδΛ Θͳ͍ɺରͷத Ͱ݁Ͱ͖Δ ࣗ༝ͳରγες ϜɺෳࡶͳλεΫ ෳͷΈΛΈ߹Θͤ ʢ-MBNB*OEFYʣ ʢ(151MVHJOTɺ+"37*4ɺ -BOH$IBJO5PPMʣ
--.ͷࠓޙͷΘΕํͷఆ ཁɺ༁ φϨοδݕࡧ ϨίϝϯυͳͲ ϑΣʔζ̍ ϑΣʔζ̎ ϑΣʔζ̏ --.୯ಠͰͷར༻ खॱͷܾ·ͬͨλ εΫ
ϧʔϧϕʔεͰ--. ͱผϩδοΫͷΈ ߹Θͤ ॊೈʹෳϩδοΫ Λݺͼग़ͯ͠ར༻ ֓ཁ ಛ ۩ମྫ ֎෦φϨοδΛ Θͳ͍ɺରͷத Ͱ݁Ͱ͖Δ ࣗ༝ͳରγες ϜɺෳࡶͳλεΫ ෳͷΈΛΈ߹Θͤ ʢ-MBNB*OEFYʣ ʢ(151MVHJOTɺ+"37*4ɺ -BOH$IBJO5PPMTʣ ຊͷλʔήοτ
-BOH$IBJO5PPMTͷ؆୯ͳઆ໌ʢʣ • ֎෦ͷπʔϧΛॊೈʹར༻Ͱ͖ΔΈ • ಠࣗͷπʔϧΛ༻ҙ͓͖ͯ͠ʢԼਤ̍ࢀরʣɺBHFOUʹରͯ͠ ΫΤϦΛ͛ΔʢԼਤ̎ࢀরʣ • ྫɿϗςϧϨίϝϯυπʔϧ SVOϝιουͰ݁ՌΛฦ
-BOH$IBJO5PPMTͷ؆୯ͳઆ໌ʢʣ • -BOH$IBJOଆͰπʔϧΛ͏͖͔Ͳ͏͔ɺͲͷπʔϧΛ ͏͖͔Λஅͯ͠ɺπʔϧΛۦͭͭ݁͠ՌΛฦ͢ πʔϧΛ͏͔Λఆ ͏πʔϧΛܾఆ
-BOH$IBJO5PPMTͷ؆୯ͳઆ໌ʢʣ • ෳͷπʔϧΛ࿈ܞͤͨ͞ߴͳ݁ՌΛฦ͢͜ͱՄೳ ݕࡧπʔϧ ܭࢉπʔϧ
-BOH$IBJO5PPMTΛ࣮ࡍʹ͏্Ͱͷ՝ • %FTDSJQUJPOͷఆ͕ٛʮ͔ͳΓʯ͍͠ • 5PPM͕૿͑ͯ͘Δͱɺఆ௨Γʹ5PPMΛͬͯ͘Εͳ͍ • ӡ༻ͷதͰదʹ5PPMΛબͯ͘͠ΕΔΑ͏मਖ਼͍ͯ͘͠ඞཁ͕͋Δ %FTDSJQUJPO
ʮ%FTDSJQUJPO0QTʯ Λߟ͑ͯΈͨ
%FTDSJQUJPO0QTͱ • ʮ͜ͷΫΤϦʹରͯ͠ɺ͜ͷπʔϧͱ͜ͷπʔϧ͕ݺΕΔ͖ʯͱ͍͏ɺ ೖྗͱਖ਼ղͷϖΞΛ༧Ίࢁ༻ҙ͓ͯ͘͠ʢ.-ʹ͓͚Δڭࢣσʔλʣ • ࣮ࡍʹΫΤϦΛୟ͍ͯΈͯɺఆ௨Γͷπʔϧ͕ݺΕ͍ͯΔ͔Λςετ ʢ.-ʹ͓͚Δਪʣ • ݺΕ͍ͯͳ͔ͬͨΒɺ݁ՌΛ--.ʹͯ͠मਖ਼͠ɺ͜ΕΛ܁Γฦ͢ ʢ.-ʹ͓͚Δֶशʣ
͜ͷΛ͍ɺӡ༻தʹվળͷϓϩηεΛճ͢ʂ ʢͱ͍͏ϑϨʔϜϫʔΫͷఏҊʣ
%FTDSJQUJPO0QTͷ࣮ݧ • ΦεεϝͷגͷฑΛग़ྗͦ͠ͷࣄۀ༰Λग़ྗ͢ΔΈΛ ରʹ͢Δ • גͷฑ͚ͩϨίϝϯυ͞ΕͯɺͦͷϏδωεϞσϧച্ΛҰॹ ʹΓͨ͘ͳΔ • ࣗͰ৭ΜͳใΛௐͯௐࠪΛͤͣͱɺ5PPMTͷΈΛ͍ඞ ཁͳใΛҰׅͰूΊ͍ͨ
• ҎԼͷطଘπʔϧ܈Λ͍࣋ͬͯΔ͜ͱΛఆ • πʔϧ̍ɿΦεεϝͷגͷձ໊ࣾΛग़ྗ͢Δ"1* • πʔϧ̎ɿձ໊͔ࣾΒฑίʔυʹม͢Δ"1* • πʔϧ̏ɿฑίʔυʹରԠ͢Δࣄۀ༰Λग़ྗ͢Δ"1*
ςετ༻ͷ5PPMΛ࡞͓ͯ͘͠ • 5PPM͕ݺΕΔ͔͚ͩݟΕྑ͍ͷͰɺ"1*ࣗମϞοΫΞο ϓͰ0, • Սۭͷձ໊ࣾΛೖΕ͓ͯ͘͜ͱͰɺ(15ࣗମ͕͑ͳ͍Α ͏ʹ͓ͯ͘͠
%FTDSJQUJPO0QTͷϑϩʔ ਖ਼ղσʔλͷೖྗ ॳظͷ%FTDSJQUJPOઃఆ ༩͑ͨ%FTDSJQUJPOΛݩʹπʔϧΛݺͼग़͠ ਖ਼ղσʔλͱൺֱͯ͠ɺͲͷҐͷਫ਼Ͱπʔϧ͕ݺͼग़͞Ε ͔ͨΛςετ
ਫ਼্͕͕ΔΑ͏ʹ%FTDSJQUJPOΛमਖ਼ ʹΔ
%FTDSJQUJPO0QTͷϑϩʔ ਖ਼ղσʔλͷೖྗ ॳظͷ%FTDSJQUJPOઃఆ ༩͑ͨ%FTDSJQUJPOΛݩʹπʔϧΛݺͼग़͠ ਖ਼ղσʔλͱൺֱͯ͠ɺͲͷҐͷਫ਼Ͱπʔϧ͕ݺͼग़͞Ε ͔ͨΛςετ
ਫ਼্͕͕ΔΑ͏ʹ%FTDSJQUJPOΛमਖ਼ ʹΔ
ਖ਼ղσʔλͷ࡞ ΫΤϦαϯϓϧ ݺͼग़͞ΕΔ͖ 5PPM܈ͱఆग़ྗ
%FTDSJQUJPO0QTͷϑϩʔ ਖ਼ղσʔλͷೖྗ ॳظͷ%FTDSJQUJPOઃఆ ༩͑ͨ%FTDSJQUJPOΛݩʹπʔϧΛݺͼग़͠ ਖ਼ղσʔλͱൺֱͯ͠ɺͲͷҐͷਫ਼Ͱπʔϧ͕ݺͼग़͞Ε ͔ͨΛςετ
ਫ਼্͕͕ΔΑ͏ʹ%FTDSJQUJPOΛमਖ਼ ʹΔ
ॳظͷ%FTDSJQUJPOઃఆ • ͪΌΜͱֶश͞ΕΔࣄΛ֬ೝ͍ͨ͠ͷͰɺ࠷ॳదͳ༰Λ ೖΕ͓ͯ͘
%FTDSJQUJPO0QTͷϑϩʔ ਖ਼ղσʔλͷೖྗ ॳظͷ%FTDSJQUJPOઃఆ ༩͑ͨ%FTDSJQUJPOΛݩʹπʔϧΛݺͼग़͠ ਖ਼ղσʔλͱൺֱͯ͠ɺͲͷҐͷਫ਼Ͱπʔϧ͕ݺͼग़͞Ε ͔ͨΛςετ
ਫ਼্͕͕ΔΑ͏ʹ%FTDSJQUJPOΛमਖ਼ ʹΔ
मਖ਼ϓϩϯϓτͷ࡞ ݱࡏͷEFTDSJQUJPO ݺΕͨ5PPMͱݺΕͳ ͔ͬͨ5PPMΛ༩͑Δ ग़ྗϑΥʔϚοτΛࢦఆ ϢʔβͷΫΤϦࣗମʹ ༩͖͢ใ
ఆྔධՁ ਖ਼ मਖ਼ճ FQPDI • मਖ਼ʹΑͬͯਫ਼্͕͢Δ͜ͱ֬ೝ • దͳमਖ਼͕ͳ͞Εͣɺ࠷ޙʹਫ਼͕Լ͕ͬͯ͠·͏ࣄ͕͋Δ
ఆੑධՁ • ੜ͞Εͨ%FTDSJQUJPOͱΫΤϦͷՃใ %FTDSJQUJPO Ճใ
ఆੑධՁ • աֶशͯ͠͠·͏ྫʢ͜ͷล.-ͬΆ͍ʣ ˞मਖ਼༻ͷϓϩϯϓτΛ࿔͍ͬͯͨΒ࿉͞Εͨ݁Ռ ֶशσʔλʹؚ·ΕΔΫΤϦ ͱ͑Λ֮͑ͯ͠·ͬͨ
·ͱΊ • --.ͱɺͦΕҎ֎Λͭͳ͛ΔՄೳੑ͕ੌ͍ʂ • ؆୯ʹܨ͕Βͳ͍ɺ൚༻Λࢦ͢΄Ͳੑೳ্͕͕Βͳ͍ • .-ͷཁྖͰɺ%FTDSJQUJPOΛςετɾվળ͢ΔΈΛߟҊ • %FTDSJQUJPO0QTͱݴ͍ͭͭɺ·ͩ0QTͷΈ·Ͱ࡞ͬ ͍ͯͳ͍ͷͰɺࠓޙؤுΓ·͢