Upgrade to Pro — share decks privately, control downloads, hide ads and more …

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...

Sponsored · Ship Features Fearlessly Turn features on and off without deploys. Used by thousands of Ruby developers. →

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

sugoikondo 近藤 豊峰

September 18, 2024

Transcript

65 slides
  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. • 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
  4. • 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
  5. • 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
  6. • ࿩୊ੑ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.
  7. • 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?
  8. • ࿈݁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
  9. 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.
  10. 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.
  11. ͔͠͠ɺEmbedding API ʹ͍ͭͯ࿩͢લʹɺ ·ͣ͸จষϕΫτϧ / ෼ࢄදݱʹֶ͍ͭͯͼ·͠ΐ͏ɻ But before we talk

    about the Embedding API, Let's first learn about Text vector / Embedding representation.
  12. • 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’
  13. 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
  14. 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
  15. 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
  16. • 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
  17. 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
  18. 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
  19. 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/
  20. 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
  21. 1. ϕΫτϧಉ࢜ͷྨࣅ౓ΛଌΔ͜ͱ͕Ͱ͖Δ ࣮͸ݕࡧϫʔυ͝ͱʹɺϝχϡʔͷฒͼॱ͕มΘΔ The order of the menu changes for

    each search term. Can calculate similarity between vectors Ref: https://www.google.com/
  22. • 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
  23. 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
  24. 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
  25. 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
  26. 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
  27. 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
  28. • (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
  29. • 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
  30. • ͔͠΋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.
  31. • 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
  32. 1SFSFWJFXFENPEFM 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
  33. • 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
  34. • 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
  35. • ͕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.
  36. 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.
  37. 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
  38. 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
  39. 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
  40. 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
  41. 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.
  42. • 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
  43. 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

More Decks by sugoikondo 近藤 豊峰

Other Decks in Technology