誰でもできる！OpenAI Embedding API を活用して高度なレコメンド機能を実現してみよう - A story about implementing an advanced recommendation function using the OpenAI Embedding API

Transcript

1. ୭Ͱ΋Ͱ͖Δʂ0QFO"* Embedding API Λ׆༻ͯ͠ɺ ߴ౓ͳϨίϝϯυػೳΛ࣮ݱͯ͠ΈΑ͏ 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. ͔͠΋ɺ͜ΕΛղܾ͢Δʹ͸·ͩͨ͘͞Μͷน͕… And there are still many barriers to solving this...
14. צఆՊ໨໊Ϩίϝϯυ࣮ݱʹཱͪ͸͔ͩΔน Barriers to achieving account recommendation • ϦϦʔε͔Β೔͕ઙ͘ɺֶशʹ࢖͑Δσʔλ͕े෼ʹू·͍ͬͯͳ͍ • Պ໨ม׵ͷ࣮੷͸ɺ͍͍ͤͥ਺ඦ ~ ઍ݅͋Δ͔Ͳ͏͔ • ֶशʹ࢖͏ͳΒ࠷௿Ͱ΋਺ສ ~ ਺ेສఔ౓͸΄͍͠ • At the moment there was still little data available for training. • At most, there are a few hundred ~ a thousand account conversion data • Training the model may require tens or hundreds of thousands of data. • ML Ϟσϧͷϝϯςίετ΍ਓࡐͷ֬อ͕ࠔ೉ • ໰୊ൃੜ࣌ʹରԠͰ͖Δਓͷ༻ҙ͔ΒɺϞσϧ࠶ֶशͳͲͷίετ΋ແࢹͰ͖ͳ͍ • Difficulty in securing maintenance costs and human resources for ML models • Preparing people who can respond to problems when they occur is difficult, and the cost of re-training models cannot be ignored.
15. ͦ͜Ͱௐ΂͍ͯͯग़ձͬͨ΋ͷ͕… So I was researching and came across…
16. OpenAI Embedding API
17. ͔͠͠ɺEmbedding API ʹ͍ͭͯ࿩͢લʹɺ ·ͣ͸จষϕΫτϧ / ෼ࢄදݱʹֶ͍ͭͯͼ·͠ΐ͏ɻ But before we talk about the Embedding API, Let's first learn about Text vector / Embedding representation.
18. About Embedding / Word2Vec
19. • 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’
20. 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
21. ਺஋Խ/ϕΫτϧԽ͢ΔͱԿ͕خ͍͠ͷ͔ʁ What can be done by quantifying/vectorizing ?
22. 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
23. 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
24. 1. ϕΫτϧಉ࢜ͷྨࣅ౓ΛଌΔ͜ͱ͕Ͱ͖Δ Can calculate similarity between vectors
25. • 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
26. 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
27. 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
28. 1. ϕΫτϧಉ࢜ͷྨࣅ౓ΛଌΔ͜ͱ͕Ͱ͖Δ ฤूڑ཭΍ LIKE ݕࡧͰ͸΄΅ແཧͳϨίϝϯυ΋… Recommendations that are almost impossible with edit distance or LIKE search… Can calculate similarity between vectors
29. 1. ϕΫτϧಉ࢜ͷྨࣅ౓ΛଌΔ͜ͱ͕Ͱ͖Δ ϕΫτϧൺֱͳΒͰ͖Δɻ - But vector comparisons can. Can calculate similarity between vectors
30. 1. ϕΫτϧಉ࢜ͷྨࣅ౓ΛଌΔ͜ͱ͕Ͱ͖Δ Google ݕࡧͷϝχϡʔͷྫ΋ྫߟ͑ͯΈΑ͏ Let's think about an example of a Google search menu one as well Can calculate similarity between vectors Ref: https://www.google.com/
31. 1. ϕΫτϧಉ࢜ͷྨࣅ౓ΛଌΔ͜ͱ͕Ͱ͖Δ Can calculate similarity between vectors Ref: https://www.google.com/ Google ݕࡧͷϝχϡʔͷྫ΋ྫߟ͑ͯΈΑ͏ Let's think about an example of a Google search menu one as well
32. 1. ϕΫτϧಉ࢜ͷྨࣅ౓ΛଌΔ͜ͱ͕Ͱ͖Δ ࣮͸ݕࡧϫʔυ͝ͱʹɺϝχϡʔͷฒͼॱ͕มΘΔ The order of the menu changes for each search term. Can calculate similarity between vectors Ref: https://www.google.com/
33. 1. ϕΫτϧಉ࢜ͷྨࣅ౓ΛଌΔ͜ͱ͕Ͱ͖Δ ͱ͍͏Θ͚ͰαΫοͱϨίϝϯυͤͯ͞ΈΔ So let's get a quick recommendation result Can calculate similarity between vectors
34. 1. ϕΫτϧಉ࢜ͷྨࣅ౓ΛଌΔ͜ͱ͕Ͱ͖Δ ͍ͦͦۙ݁͜͜͠Ռ͕औΕΔ - We can retrieve reasonably close results Can calculate similarity between vectors
35. 2. ϕΫτϧಉ࢜ͷՃࢉɾݮࢉͳͲ਺஋ܭࢉ͕Ͱ͖ΔΑ͏ʹͳΔ Can perform numerical operations such as addition and subtraction against vectors
36. • 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
37. 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
38. 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
39. 2. ϕΫτϧಉ࢜ͷՃࢉɾݮࢉͳͲ਺஋ܭࢉ͕Ͱ͖ΔΑ͏ʹͳΔ ϕΫτϧͷ߹੒Λ࢖͏͜ͱͰɺ͜Μͳ͜ͱ͕Ͱ͖Δ Using vector composition, we can do this Can perform numerical operations such as addition and subtraction against vectors 1. target_words ͷϕΫτϧΛܭࢉ͠ɺՃࢉ 2. ͦͯ͠ candidate_words ͷͦΕͧΕͱൺֱ 1. Compute and add vectors of target_words 2. Then compare the vector with each of the candidate_words ones
40. 2. ϕΫτϧಉ࢜ͷՃࢉɾݮࢉͳͲ਺஋ܭࢉ͕Ͱ͖ΔΑ͏ʹͳΔ ݁Ռ͸͜͏ͳΔ - The result is this. Can perform numerical operations such as addition and subtraction against vectors
41. 2. ϕΫτϧಉ࢜ͷՃࢉɾݮࢉͳͲ਺஋ܭࢉ͕Ͱ͖ΔΑ͏ʹͳΔ ͪͳΈʹ ‘Macbook’ Λ ‘Mac’ ʹ͢Δͱ͜͏ͳΔ If I change 'Macbook' to 'Mac', the result becomes like this Can perform numerical operations such as addition and subtraction against vectors
42. 2. ϕΫτϧಉ࢜ͷՃࢉɾݮࢉͳͲ਺஋ܭࢉ͕Ͱ͖ΔΑ͏ʹͳΔ ಉ͡ख๏ͰɺΩϟϥΫλʔ࿈૝ήʔϜ΋࡞ΕΔ The same technique can be used to create character associative games. Can perform numerical operations such as addition and subtraction against vectors
43. 2. ϕΫτϧಉ࢜ͷՃࢉɾݮࢉͳͲ਺஋ܭࢉ͕Ͱ͖ΔΑ͏ʹͳΔ ΋ͪΖΜ౰ͯΒΕΔ - Of course guessable. Can perform numerical operations such as addition and subtraction against vectors
44. OpenAI ͷEmbedding API ʹ͍ͭͯ About OpenAI's Embedding API
45. • (લड़ͷ)ςΩετͷϕΫτϧɾ෼ࢄදݱΛऔಘͰ͖Δ API • ref: https://platform.openai.com/docs/guides/embeddings • API to obtain vector/distributed representation of text • 23೥6݄ʹՁ֨վఆ͞Εɺada ϞσϧͰͦΕ·Ͱͷ 75% Φϑͷ
 $ 0.0001/ 1K token ʹͳͬͨ • Prices were revised in June 2023 to $ 0.0001/ 1K tokens, 75% off the previous price for the ada model. OpenAI ͷ Embedding API ʹ͍ͭͯ About OpenAI’s Embedding API
46. • 24೥1݄ʹߋʹ҆ՁͳϞσϧ text-embedding-3-small ͕ొ৔͠ɺߋʹ 80% Φϑʹ • લͷϞσϧ (ada) ΑΓ΋ߴਫ਼౓ͳϞσϧ text-embedding-3-large ΋ొ৔ • In January 2012, an even less expensive model, text-embedding-3-small, became available at an additional 80% off! • A model text-embedding-3-large, which is more accurate than the previous model (ada), also became available • ߋʹ࣍ݩ਺ͷ࡟ݮΛެࣜͰαϙʔτɻϕΫτϧܭࢉͷߴ଎Խ΍ετϨʔδ༰ྔͷ࡟ݮ͕ݟࠐΊΔ • Furthermore, the reduction of the number of dimensions is supported by the formula, which is expected to speed up vector calculations and reduce storage capacity. OpenAI ͷ Embedding API ʹ͍ͭͯ About OpenAI’s Embedding API
47. • ͔͠΋ΑΓ҆Ձʹར༻Ͱ͖Δ Batch API ΋ར༻Մೳ • Ϩεϙϯε͕஗͘ͳΔ(24 ࣌ؒҎ಺)୅ΘΓʹɺ൒ֹͰར༻Մೳ • Batch API is also available for an even lower cost. • Slow response (within 24 hours), but available at half price OpenAI ͷ Embedding API ʹ͍ͭͯ About OpenAI’s Embedding API • ϦΞϧλΠϜੑͷཁٻ͕௿͍Ϟϊ΍ɺॳظσʔλߏஙͳͲʹద͍ͯ͠Δ • Suitable for low real-time objects, initial data construction, etc.
48. • τʔΫϯͷ໨҆͸ҎԼ͔Βௐ΂Δ͜ͱ͕Ͱ ͖Δɻ • If you are concerned about the tokens, you can find out more about them below. • https://platform.openai.com/tokenizer • $1 ࢖͏ͷʹ 100 ສ ~ 5,000 ສจࣈ͘Β͍ ౤͛Δඞཁ͕͋ΔͷͰɺίετ΋ͦ͜·Ͱ ؾʹͳΒͳ͍ • You need to send about 1 ~ 50 million letters to spend $1, so the cost is not much of a concern. OpenAI ͷ Embedding API ʹ͍ͭͯ About OpenAI’s Embedding API
49. 1SFSFWJFXFE
    NPEFM Ґਖ਼౴཰ ҐἬਖ਼౴཰ ̍Ґਖ਼౴཰
    XJUIPVU
    &OHMJTI ҐἬਖ਼౴཰
    XJUIPVU
    &OHMJTI     Պ໨ϨίϝϯυͰ΋ࣄલݕ౼Ϟσϧͱൺ΂ͯɺਫ਼౓͕େ͖͘޲্ Significantly improved accuracy in account recommendations compared to pre-reviewed model 0QFO"*
    UFYUFNCFEEJOHMBSHF Ґਖ਼౴཰ ҐἬਖ਼౴཰ ̍Ґਖ਼౴཰
    XJUIPVU
    &OHMJTI ҐἬਖ਼౴཰
    XJUIPVU
    &OHMJTI     OpenAI ͷ Embedding API ʹ͍ͭͯ About OpenAI’s Embedding API
50. • ಉ͡ςΩετΛૹͬͨࡍͷϨεϙϯε͸ৗʹҰఆͳͷͰɺ ϕΫτϧΩϟογϡͷػߏΛ࡞ΔͱϦΫΤετΛݮΒͤΔɻ • Since the response is always constant when the same text is sent, a vector cache mechanism can be created to reduce requests. • OpenAI ͷϨεϙϯε͸ (ϦΫΤετʹΑΔ͕) ਺ඵ͔͔Δͱ ͖΋͋ΔͷͰɺϨεϙϯελΠϜվળͷͨΊʹ΋ϕΫτϧ Ωϟογϡ͸͋ͬͨํ͕Α͍ • API’s response can take several seconds (depending on the request), so vector caching is recommended to improve response time. OpenAI ͷ Embedding API ʹ͍ͭͯ About OpenAI’s Embedding API
51. • API ʹ͸ҰൠతͳϨʔτϦϛοτ͕ઃఆ͞Ε͍ͯΔ • ݱࡏ͸ Tier ʹΑͬͯมΘΔ • API has a general rate limit • Currently varies depending on Tier • ϦΫΤετ਺ʹ΋ΑΔ͕ɺΩϟογϡػߏ΋ ͋Ε͹ֻ͔Δ͜ͱ͸͋·Γແ͍ • Depends on the number of requests, but with a cache mechanism, there is little to worry about. Embedding API ࢖༻࣌ͷϝϞɾ஫ҙ఺ Notes on using Embedding API
52. • ͕ɺͦΕͱ͸ผͰγεςϜશମϨϕϧͰ͔ ͔ΔϨʔτϦϛοτͷΑ͏ͳ΋ͷ͕Ͳ͏΍ Βଘࡏ͢Δ • But apart from that, there is apparently some kind of rate limit that is applied at the system-wide level. 1. ϨʔτϦϛοτ͕2छྨଘࡏ͢Δ • ଟ͍࣌͸਺ճʹ̍ճ͘Β͍ͷස౓Ͱ͜ͷϦϛοτʹ఍৮͢Δ • I encounter this rate limit error about once every few times at most.
53. ղܾ๏: ϦτϥΠػߏΛಋೖ͢Δ - Solution: Implement a retry mechanism ϨʔτϦϛοτͷରॲ๏ • OpenAI ΋Exponential Backoff Λਪ঑ɺPython ͸ ͍͔ͭ͘ϥΠϒϥϦͷαϯϓϧ΋ࡌ͍ͤͯΔɻ • Ref: https://platform.openai.com/docs/guides/ rate-limits/retrying-with-exponential-backoff • OpenAI also recommends Exponential Backoff and some Python sample code is also provided Rate Limit ΁ͷରॲ๏ͱͯ͠͸ඍົʹ΋ࢥ͑Δ͕ɺಋೖҎ߱Ͱൃੜ݅਺͸΄΅θϩʹɻ Although this may seem like a subtle way to deal with the Rate Limit, the number of occurrences has dropped to almost zero since its introduction.
54. จষϕΫτϧΛ׆༻ͯ͠Ͱ͖Δ͜ͱ What you can achieve with text vector
55. ࣄྫ1: Պ໨ಉ࢜ͰͷϨίϝϯυ Example 1:Recommendation between accounts • Redis ΛϕΫτϧΩϟογϡอଘ༻ʹར༻ • ͜ͷ࢓૊ΈͰඅ༻Λ཈͑ΒΕ͓ͯΓɺྦྷܭͰ ਺ ઍສՊ໨ఔ౓ΛϕΫτϧԽ͕ͨ͠ɺඅ༻͸΄ͱ ΜͲֻ͔͍ͬͯͳ͍ • Use Redis as vector cache storage • Thanks to this mechanism, a total of about tens of millions of accounts have been vectorized so far, but at little or almost no cost. • Embedding API ͕࢖͓͔͑ͨ͛ͰɺGPU ΍େྔͷ CPU/ϝϞϦΛ٧ΜͩߴՁͳϚγϯ͕ෆཁʹ Embedding API eliminates the need for expensive machines packed with GPUs and lots of CPU/memory
56. 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
57. 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
58. 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
59. ཁ͸… After all…
60. 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.
61. ·ͱΊ summary
62. • OpenAI ࣾͷ Embedding API Λ׆༻͢Δ͜ͱͰɺML ΤϯδχΞ͕ ډͳ͍νʔϜͰ΋ AI ιϦϡʔγϣϯΛ؆୯͔ͭ҆Ձʹ࣮ݱͰ͖ͨ • OpenAI's Embedding API made implementing an AI solution for a team without an ML engineer easy and inexpensive. • 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
63. WE’RE HIRING!!
64. 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