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
2.5k
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
LangGraphで始めるマルチエージェントシステム
peisuke
13
3.9k
AutoGenで作るLLM Agen
peisuke
1
1.3k
Self-RAG: Learning to Retrieve, Generate and Critique through Self-Reflections
peisuke
9
1.4k
Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields
peisuke
0
9k
GNeRF: GAN-based Neural Radiance Field without Posed Camera
peisuke
1
720
TTS Skins: Speaker Conversion via ASR
peisuke
0
370
A Quantum Computational Approach to Correspondence Problems on Point Sets
peisuke
0
660
F0-Consistent Many-to-many Non-parallel Voice Conversion via Conditional Autoencoder
peisuke
0
170
YOLACT real-time instance segmentation
peisuke
1
250
Other Decks in Technology
See All in Technology
20241120_JAWS_東京_ランチタイムLT#17_AWS認定全冠の先へ
tsumita
2
300
AIチャットボット開発への生成AI活用
ryomrt
0
170
障害対応指揮の意思決定と情報共有における価値観 / Waroom Meetup #2
arthur1
5
480
テストコード品質を高めるためにMutation Testingライブラリ・Strykerを実戦導入してみた話
ysknsid25
7
2.7k
New Relicを活用したSREの最初のステップ / NRUG OKINAWA VOL.3
isaoshimizu
3
630
SSMRunbook作成の勘所_20241120
koichiotomo
3
160
適材適所の技術選定 〜GraphQL・REST API・tRPC〜 / Optimal Technology Selection
kakehashi
1
690
安心してください、日本語使えますよ―Ubuntu日本語Remix提供休止に寄せて― 2024-11-17
nobutomurata
1
1k
第1回 国土交通省 データコンペ参加者向け勉強会③- Snowflake x estie編 -
estie
0
130
OCI 運用監視サービス 概要
oracle4engineer
PRO
0
4.8k
複雑なState管理からの脱却
sansantech
PRO
1
150
Taming you application's environments
salaboy
0
190
Featured
See All Featured
GraphQLの誤解/rethinking-graphql
sonatard
67
10k
The Success of Rails: Ensuring Growth for the Next 100 Years
eileencodes
44
6.8k
Fashionably flexible responsive web design (full day workshop)
malarkey
405
65k
Thoughts on Productivity
jonyablonski
67
4.3k
Keith and Marios Guide to Fast Websites
keithpitt
409
22k
Reflections from 52 weeks, 52 projects
jeffersonlam
346
20k
Happy Clients
brianwarren
98
6.7k
10 Git Anti Patterns You Should be Aware of
lemiorhan
655
59k
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
PRO
10
720
We Have a Design System, Now What?
morganepeng
50
7.2k
A Tale of Four Properties
chriscoyier
156
23k
Put a Button on it: Removing Barriers to Going Fast.
kastner
59
3.5k
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·͢