OpenAI Embedding API を活用して、 高度なレコメンド機能を実装した話 - A story about implementing an advanced recommendation function using the OpenAI Embedding API

Transcript

1. OpenAI Embedding API Λ׆༻ͯ͠ɺ ߴ౓ͳϨίϝϯυػೳΛ࣮૷ͨ͠࿩ By Atsumine Kondo - @sugoikondo A story about implementing an advanced recommendation function using the OpenAI Embedding API
2. ۙ౻ ๛ๆ Atsumine Kondo • Backend / Frontend / Infra • Scala, Kotlin, Python, etc… • Vue.js, Nuxt.js, Next,.js etc… @sugoikondo MoneyForward.inc Group Management Solution dept Product development div
3. ͜ͷൃදͰֶ΂Δ͜ͱ What you can learn from this presentation
4. • จষϕΫτϧͱ͸Կ͔͕Θ͔Δ You can learn what a text vector is • ↑ ͕Θ͔Δ͜ͱͰɺҎԼιϦϡʔγϣϯ͕࣮ݱͰ͖Δ • Ϩίϝϯυ, ҟৗ஋ݕग़, ෼ྨ໰୊, ݕࡧ etc… • By learning the above, you can realize the following solution • Recommendation, outlier detection, classification problems, search etc... ͜ͷൃදͰֶ΂Δ͜ͱɾͰ͖ΔΑ͏ʹͳΔ͜ͱ
5. ͸͡Ίʹ Introduction
6. • 8 ݄ʹ AI ʹΑΔ࿈݁Պ໨Ϩίϝϯυ ػೳΛϦϦʔε We released an AI-based consolidated account recommendation in Aug. 2023 • OpenAI ࣾͷ Embedding API Λ׆༻ Using OpenAI's Embedding API Ϋϥ΢υ࿈݁ձܭʹՊ໨ϨίϝϯυػೳΛ࣮૷ ref: https://corp.moneyforward.com/news/release/service/ 20230804-mf-press-1/ We’ve Implemented a subject recommendation function in our application ※ ಛڐग़ئࡁΈ Pattent applied
7. • ݸࣾͷצఆՊ໨ʹରͯ͠ɺҙຯతʹ͍ۙ ਌ձࣾͷ࿈݁Պ໨Λ্Ґ 3 ͭΛఏҊ͢Δ • Suggest the top three parent company consolidated accounts that are semantically close to the individual company's accounts. ref: https://corp.moneyforward.com/news/release/service/ 20230804-mf-press-1/ Ϋϥ΢υ࿈݁ձܭʹՊ໨ϨίϝϯυػೳΛ࣮૷ We’ve Implemented a subject recommendation function in our application
8. • ࿩୊ੑͷߴ͔͞Βɺଟ͘ͷϝσΟΞ ͰऔΓ্͛ͯ΋Β͍·ͨ͠ɻ Due to the high profile of the topic, we have had a lot of media coverage. • https://cloud.watch.impress.co.jp/docs/ news/1522209.html • https://it.impress.co.jp/articles/-/25192 • https://officenomikata.jp/news/15534/ • In total, about 8 articles... ଟ͘ͷϝσΟΞͰऔΓ্͛ͯ௖͖·ͨ͠ We have had a lot of media coverage.
9. • צఆՊ໨ͱ͸ɺࢿ࢈ͳͲͷऔҾΛه࿥͢Δࡍʹ࢖͏໊শɾݟग़͠ • Accounts are names or headings used to record transactions of assets, etc. आํ Debit ିํ Credit ஍୅Ո௞ Rent expenses 50,000 ී௨༬ۚ Ordinary deposit 50,000 • ͜͜Ͱ͍͏ʮ஍୅Ո௞ʯͱʮී௨༬ۚʯ͕ͦΕͧΕצఆՊ໨ • The “Rent expenses" and “Ordinary deposit" here are the accounts respectively. ྫ: Ո௞ 5 ສԁΛޱ࠲Ҿ͖མͱ͠Ͱࢧ෷ͬͨ৔߹ e.g. You paid 50,000 yen rent via direct debit. צఆՊ໨/࿈݁Պ໨ͱ͸ʁ What is an account/consolidated account?
10. • ࿈݁ձܭจ຺Ͱ͸ɺάϧʔϓ಺ͷձࣾͷ࿈݁Պ໨ͱֹۚΛٵ্͍͛ɺͦΕΒΛ਌ձࣾͷՊ໨ Ұͭʢ࿈݁Պ໨ʣʹू໿ͤ͞Δ࡞ۀ͕͋Δɻ • In the consolidation accounting context, there is a process of taking the consolidated accounts and balance of the companies in the group and consolidating them into one account (consolidated account) of the parent company. צఆՊ໨/࿈݁Պ໨ͱ͸ʁ What is an account/consolidated account? ࢠձࣾA Company A ਌ձࣾ Parent Company ී௨༬ۚ Ordinary Deposit Aۜߦ Bank A ݱۚٴͼ༬ۚ Cash & Deposit ࢠձࣾB Company B
11. צఆՊ໨໊͸ձࣾʹΑ͔ͬͯͳΓදهΏΕ͕͋Δ Account names vary considerably from company to company.
12. ΑΓྑ͍צఆՊ໨໊ϨίϝϯυΛͲ͏࣮ݱ͢Δ͔ʁ How to achieve better account recommendations? • ୯७ͳ͍͋·͍ݕࡧɾฤूڑ཭ͳͲͰ͸ٵऩ͖͠Εͳ͍ύλʔϯ͕ଟ͍ • ྫ: ʮʓʓۜߦʯͱʮී௨༬ۚʯɺʮݱۚٴͼ༬ۚʯͳͲ • ւ֎ࢠձ͕ࣾ͋Δ৔߹͸ʮʓʓ BankʯͳͲ೔ຊޠҎ֎ͷϞϊ͕དྷΔέʔε΋͋Δ • Many patterns cannot be absorbed by simple fuzzy search, edit distance, etc. • Ex: “XX bank” and “Ordinary deposit”, “Cash and deposits”, etc. • If there is an overseas subsidiary, there are cases where things other than Japanese are sent. • ҙຯͷۙ͞΋Ճຯͯ͠ɺݸࣾͷצఆՊ໨ʹҰ൪͍ۙ࿈݁Պ໨ΛϨίϝϯυ ͢Δඞཁ͕͋Δɻ • It is necessary to recommend the consolidated accounts that are closest to the individual company's accounts, taking into account the proximity in meaning.
13. ͦ͜Ͱௐ΂͍ͯͯग़ձͬͨ΋ͷ͕… So I was researching and came across…
14. OpenAI Embedding API
15. ͔͠͠ɺEmbedding API ʹ͍ͭͯ࿩͢લʹɺ ·ͣ͸จষϕΫτϧ / ෼ࢄදݱʹֶ͍ͭͯͼ·͠ΐ͏ɻ But before we talk about the Embedding API, Let's first learn about Text vector / Embedding representation.
16. About Embedding / Word2Vec
17. • จষΛ਺஋/ϕΫτϧʹม׵͢Δٕज़ɾख๏ͷ͜ͱ • A technology or method of converting text into vectors. About Embedding / Word2Vec ”ݱ͓ۚΑͼ༬ۚ” [[-0.03455162],[-0.01306203], [ 0.01672893],…, [-0.00129271], [ 0.00694819],[-0.01055199]] • ϕΫτϧɺ෼ࢄදݱ͋Δ͍͸ຒΊࠐΈදݱͱݺ͹ΕΔ͜ͱ΋͋Δɻ • Sometimes called vector, distributed or embedded representation. ‘Cash and deposits’
18. About Embedding / Word2Vec ex: ʮݱۚʯͱʮෛ࠴ʯ͕ͦΕͧΕ [0.6, 0.8], [-0.3, 0.4]ͱ ͳΔ৔߹ When "Cash" and "Liabilities" become [0.4, 0.8] and [-0.3, 0.9], respectively ුಈখ਺఺ͷ഑ྻʹͳΔ͜ͱͰɺ࠲ඪ·ͨ͸ϕΫτϧΛද͢͜ͱ͕Ͱ͖Δɻ It can represent coordinates or vectors by being a floating-point array. -0.5 0.5 1 0.5 1 ݱۚ ෛ࠴ Liabilities Cash 0
19. ਺஋Խ/ϕΫτϧԽ͢ΔͱԿ͕خ͍͠ͷ͔ʁ What can be done by quantifying/vectorizing ?
20. 2. ϕΫτϧಉ࢜ͷՃࢉɾݮࢉͳͲ ɹ ਺஋ܭࢉ͕Ͱ͖ΔΑ͏ʹͳΔ ϕΫτϧԽ͢ΔͱͰ͖Δ͜ͱ What you can implement when vectorize texts 1. ϕΫτϧಉ࢜ͷྨࣅ౓ΛଌΔ͜ͱ ͕Ͱ͖Δ Can calculate similarity between vectors Can perform numerical operations such as addition and subtraction against vectors
21. 2. ϕΫτϧಉ࢜ͷՃࢉɾݮࢉͳͲ ɹ ਺஋ܭࢉ͕Ͱ͖ΔΑ͏ʹͳΔ 1. ϕΫτϧಉ࢜ͷྨࣅ౓ΛଌΔ͜ͱ ͕Ͱ͖Δ Can calculate similarity between vectors Can perform numerical operations such as addition and subtraction between vectors ← ࠓճ͸ ͬͪ͜ This time we talk about this mainly. ϕΫτϧԽ͢ΔͱͰ͖Δ͜ͱ What you can implement when vectorize texts
22. 1. ϕΫτϧಉ࢜ͷྨࣅ౓ΛଌΔ͜ͱ͕Ͱ͖Δ Can calculate similarity between vectors
23. • 2 ͭͷϕΫτϧͷؒʹͳ֯͢౓ΛٻΊΔ͜ͱ ͰɺϕΫτϧͷ޲͖ͷྨࣅ౓Λࢉग़Ͱ͖Δ • By calculating the angle between two vectors, the similarity of vector orientation can be calculated • ίαΠϯྨࣅ౓͕Ұൠత • + Ͱਖ਼ͷ૬ؔɺ- Ͱෛͷ૬ؔ • Cosine similarity is generally used. • Plus means positive correction, negative means negative correction 1. ϕΫτϧಉ࢜ͷྨࣅ౓ΛଌΔ͜ͱ͕Ͱ͖Δ ݱۚ A ۜߦ ஍୅Ո௞ cos(‘ݱۚ’, ‘Aۜߦ’) = 0.85 cos(‘ݱۚ’, ‘஍୅Ո௞’) = 0.05 Rent expenses Rent expenses Cash Cash Cash Bank A Bank A Can calculate similarity between vectors
24. จষؒͷྨࣅ౓ΛٻΊΔ͜ͱ͕Ͱ͖ΔͷͰɺ͜ΕΒιϦϡʔγϣϯ͕࣮ݱͰ͖Δ Since similarity between sentences can be determined, you can apply it for the below solution 1. ϕΫτϧಉ࢜ͷྨࣅ౓ΛଌΔ͜ͱ͕Ͱ͖Δ • Ϩίϝϯυʢྨࣅ౓͕ߴ͍΋ͷʣ- Recommendations (highly similarity) • ҟৗ஋ݕग़ (ྨࣅ౓͕௿͍΋ͷ) - Outlier detection (low similarity) • ෼ྨ໰୊ʢྨࣅ౓͕͍ۙ΋ͷಉ࢜Ͱ෼ྨ͢Δʣ- Classification (Classify by its similarity) Can calculate similarity between vectors
25. จষؒͷྨࣅ౓ΛٻΊΔ͜ͱ͕Ͱ͖ΔͷͰɺ͜ΕΒιϦϡʔγϣϯ͕࣮ݱͰ͖Δ Since similarity between sentences can be determined, you can apply it for the below solution 1. ϕΫτϧಉ࢜ͷྨࣅ౓ΛଌΔ͜ͱ͕Ͱ͖Δ • Ϩίϝϯυʢྨࣅ౓͕ߴ͍΋ͷʣ- Recommendations (highly similarity) • ҟৗ஋ݕग़ (ྨࣅ౓͕௿͍΋ͷ) - Outlier detection (low similarity) • ෼ྨ໰୊ʢྨࣅ౓͕͍ۙ΋ͷಉ࢜Ͱ෼ྨ͢Δʣ- Classification (Classify by its similarity) Can calculate similarity between vectors
26. 1. ϕΫτϧಉ࢜ͷྨࣅ౓ΛଌΔ͜ͱ͕Ͱ͖Δ ฤूڑ཭΍ LIKE ݕࡧͰ͸΄΅ແཧͳϨίϝϯυ΋… Recommendations that are almost impossible with edit distance or LIKE search… Can calculate similarity between vectors
27. 1. ϕΫτϧಉ࢜ͷྨࣅ౓ΛଌΔ͜ͱ͕Ͱ͖Δ ϕΫτϧൺֱͳΒͰ͖Δɻ - But vector comparisons can. Can calculate similarity between vectors
28. 2. ϕΫτϧಉ࢜ͷՃࢉɾݮࢉͳͲ਺஋ܭࢉ͕Ͱ͖ΔΑ͏ʹͳΔ Can perform numerical operations such as addition and subtraction against vectors
29. • ϕΫτϧ͸୯ͳΔଟ࣍ݩ഑ྻͳͷͰɺ࣍ݩ਺ ͕߹͑͹Ճࢉɾݮࢉʢ߹੒ʣ͕Ͱ͖Δ • Vectors are simply multidimensional arrays, so they can be added or subtracted (combined) if the number of dimensions matches. • ϕΫτϧಉ࢜Λ߹੒͢Δ͜ͱͰɺෳ਺ͷϕΫ τϧͷҙຯΛ࣋ͬͨ··ɺҰͭͷϕΫτϧʹ ͢Δ͜ͱ͕Ͱ͖Δ • Vectors can be combined into a single vector with the meaning of multiple vectors 2. ϕΫτϧಉ࢜ͷՃࢉɾݮࢉͳͲ਺஋ܭࢉ͕Ͱ͖ΔΑ͏ʹͳΔ IT ΦϨϯδ ۚ༥ܥ MoneyForward Can perform numerical operations such as addition and subtraction against vectors Orange Fintech
30. ίϨʹ͍ۙ΋ͷ͕࣮ݱͰ͖Δ Something close to this can be implemented. 2. ϕΫτϧಉ࢜ͷՃࢉɾݮࢉͳͲ਺஋ܭࢉ͕Ͱ͖ΔΑ͏ʹͳΔ Ref: https://www.google.com/ ͭ·Γɺ Can perform numerical operations such as addition and subtraction against vectors So, IT Orange Fintech
31. ίϨʹ͍ۙ΋ͷ΋࣮ݱͰ͖Δ (લͷྫͳΒ IT ͕ώοτ) Something similar to this can also be implemented (IT will hit in the previous example). 2. ϕΫτϧಉ࢜ͷՃࢉɾݮࢉͳͲ਺஋ܭࢉ͕Ͱ͖ΔΑ͏ʹͳΔ Ref: https://www.google.com/ ΋ͪΖΜݮࢉ΋Ͱ͖ΔͷͰɺ Of course, we can also subtract them, Can perform numerical operations such as addition and subtraction against vectors MoneyForward -Fintech -Orange
32. จষϕΫτϧΛ׆༻ͯ͠Ͱ͖Δ͜ͱ What you can do with document vector
33. ࣄྫ1: Պ໨ಉ࢜ͰͷϨίϝϯυ Example 1:Recommendation between accounts • Redis ΛϕΫτϧΩϟογϡอଘ༻ʹར༻ • ͜ͷ࢓૊ΈͰඅ༻Λ཈͑ΒΕ͓ͯΓɺ OpenAI ʹ͸·ͩҰԁ΋෷͍ͬͯͳ͍ɻ • Use Redis as vector cache storage • Thanks to this mechanism, we are now using the API without paying a penny to OpenAI. • Embedding API ͕࢖͓͔͑ͨ͛ͰɺGPU ΍େྔ ͷCPU/ϝϞϦΛ٧ΜͩߴՁͳϚγϯ͕ෆཁʹ • Embedding API eliminates the need for expensive machines packed with GPUs and lots of CPU/ memory
34. ࣄྫ2: ྖऩॻͷϑϦʔϫʔυݕࡧ Example 2: Free word search for receipts Vector DB Receipt.pdf, jpg, etc… [[-0.03455162],[-0.01306203],…, [ 0.00694819],[-0.01055199]] User • Vectorize the text of the contents of the receipt • OCR, use ChatGPT, etc… • Then store it in Vector DB, etc • ྖऩॻͷத਎ͷςΩετΛ༧ΊϕΫτϧԽ • OCR, ChatGPT ʹ౤͛Δ etc… • ͦΕΛ Vector DB ͳͲʹอଘ͓ͯ͘͠ Vectorization Upload
35. ࣄྫ2: ྖऩॻͷϑϦʔϫʔυݕࡧ Example 2: Free word search for receipts Vector DB • Ϣʔβ͕ೖྗͨ͠ݕࡧϫʔυΛϕΫτϧԽɺ DB ্ͷ஋͔Β͍ۙ͠΋ͷΛϐοΫ User • Vectorize search words entered by the user, and pick the closest ones from the values on the DB. 12/1ͷ1ສԁͷྖऩॻ A receipt of10,000 yen on December 1. [[-0.03455162],[-0.01306203],…, [ 0.00694819],[-0.01055199]] Search Receipt_Dec_1.pdf Vectorization
36. ࣄྫ3: ͱ͋ΔྖऩॻͱྨࣅͷྖऩॻΛ୳͢ Example 3: Find receipts that are similar to a certain receipt. Vector DB • Text to File ͕Ͱ͖Ε͹ɺ΋ͪΖΜ File to File ࣮ͩͬͯ૷Ͱ͖ͪΌ͏ • If Text to File can be implemented, of course File to File can also be implemented. ͜Εͱྨࣅͷྖऩॻ͕΄͍͠ I need a receipt similar to this one. [[-0.03455162],[-0.01306203],…, [ 0.00694819],[-0.01055199]] Text extraction Vectorization Receipt, Dec. 1, … Search
37. ཁ͸… After all…
38. จষϕΫτϧΛੜ੒Ͱ͖Δ͜ͱͰͰ͖Δ͜ͱ What can be done by being able to generate sentence vectors ςΩετʹม׵Ͱ͖Δ΋ͷͳΒɺͳΜͰ΋Ϩίϝϯυ etc Λ࣮૷Ͱ͖Δɻ Anything that can be converted to text can be used to implement recommendations, etc. ͔͠΋ ChatGPT ͷ͓ӄͰɺը૾ etc ΛςΩετʹม׵͢Δෑډ΋௿͘ͳ͍ͬͯΔ Also, thanks to ChatGPT, the difficulty of converting images and other data to text has been reduced. API ͸·͚ͩͩͲ Well, the API is not yet available
39. ·ͱΊ summary
40. • OpenAI ࣾͷ Embedding API Λ׆༻͢Δ͜ͱͰɺML ΤϯδχΞ͕ ډͳ͍νʔϜͰ΋ AI ιϦϡʔγϣϯΛΧϯλϯʹ࣮ݱͰ͖ͨ • OpenAI's Embedding API made it easy to implement an AI solution for a team without an ML engineer • Embedding API Λ׆༻͢Δ͜ͱͰɺϨίϝϯυ΍ҟৗ஋ݕग़ɺςΩ ετ෼ྨͳͲଟ༷ͳιϦϡʔγϣϯΛ࣮ݱͰ͖Δ • Embedding APIs can be used to implement various solutions such as recommendation, outlier detection, text classification, etc. ·ͱΊ - Summary
41. WE’RE HIRING!!
42. ϚωʔϑΥϫʔυ͸ɺҰॹʹ੒ ௕͍͚ͯ͠Δ஥ؒΛืू͓ͯ͠ Γ·͢ɻ We are looking for people who can grow with us. ࠾༻αΠτ͸ͪ͜Β → Scan this QR to visit our recruitment site