{ "aboutHtml": "

Mistral Embed 2312 — ma’noni raqamli ifodalash uchun Mistral AI’ning matn embedding modeli. U matn satri yoki satrlar ro‘yxatini qabul qiladi va har bir kirish uchun embedding qaytaradi. Natija suhbat izohi emas, ilova o‘xshashlik, qidiruv, tasniflash yoki klasterlash uchun ishlatadigan vektordir. Ishlab chiqaruvchining modelga xos sahifasi mistral-embed-2312’ni ko‘rsatadi.

Kirish, kontekst va vektor shakli

Aynan model sahifasi 8k kontekst yorlig‘ini hujjatlashtiradi. Har bir matn elementini qo‘llanadigan kirish sig‘imi doirasida tayyorlang va element identifikatsiyasini vektor bilan saqlang. Uzun manba hujjatini foydali parchalarga bo‘lish mumkin; keyin to‘g‘ri materialni qaytarish uchun kerakli hujjat sarlavhasi, bo‘lim va manba joyini saqlang.

Ishlab chiqaruvchining Mistral Embed qo‘llanmasi kirishning ko‘rinadigan uzunligidan qat’i nazar, har matn embeddingi uchun 1 024 o‘lchamni belgilaydi. Demak, qisqa savol va uzunroq parcha mazmuni hamda token soni farqli bo‘lsa ham bir xil vektor shakliga ega. Bu javob tokenlari budjeti yoki manbaning nechta so‘zi saqlanishi o‘lchovi emas, chiqish ifodasining o‘lchamidir.

Hujjatlashtirilgan javob embeddinglar va token ishlatilishi ma’lumotini saqlaydi; endpoint misoli har bir vektorni kirish indeksiga bog‘laydi. Bir nechta matnni qayta ishlashda shu bog‘liqlikni saqlang. Foydali qidiruv natijasini ko‘rsatish yoki keyingi bosqichga manba materiali berish uchun ilovaga raqamli natija bilan birga asl matn va identifikatorlari ham kerak.

Semantik o‘xshashlik

Qo‘llanma bog‘liq matnlar embedding makonida yaqin bo‘lishga moyilligini tushuntiradi. Bu bir mavzu yoki talabni turli so‘zlar bilan ifodalagan parchalarni topishni qo‘llab-quvvatlaydi. Bilim bazasi so‘rovi misoli kirishni qanday tiklashni so‘rashi, tegishli tartib esa ayni amal uchun boshqa iboradan foydalanishi mumkin. Ilova faqat aniq so‘z mosligiga tayanmasdan, so‘rov vektorini saqlangan parcha vektorlari bilan taqqoslashi mumkin.

Ishlab chiqaruvchi misollari birlik uzunlikka normallangan embeddinglardan foydalanadi. Bunday vektorlarda kosinus o‘xshashligi, skalyar ko‘paytma va Yevklid masofasi raqamli qiymatlari bir xil bo‘lmasa ham izchil o‘xshashlik reytinglarini beradi. Bitta mos taqqoslash usulini tanlang va so‘rov hamda hujjat ifodalarida izchil qo‘llang.

O‘xshashlik ikki bayonot o‘zaro almashtirilishini isbotlamaydi. Manba matnini saqlang va savol uchun muhim shart, sana yoki identifikatorni tekshiring. Ikki parcha bir mavzuga oid bo‘lib, turli tartib-taomil yoki istisnolarni tavsiflashi mumkin. Embedding qidiruv signalini beradi; tanlangan parchani talqin qilish vazifaning alohida qismidir.

Qidiruv va manbaga asoslangan javoblar

Amaliy hujjat jarayoni bilim bazasi parchalari uchun vektorlar tayyorlaydi, ularning identifikatorlari va asl matnini saqlaydi, keyin yangi savolni shu to‘plam bilan taqqoslaydi. Tegishli parchalarni manba joylari bilan qaytaring. Ilova bu parchalarni bevosita ko‘rsatishi yoki topilgan materialga asoslangan javob yozadigan matn yaratish modeliga berishi mumkin.

Foydali qidiruv natijasi uchun hujjat sarlavhasi, bo‘lim, parcha va uni topishga ishlatilgan identifikatorni saqlang. Qo‘llab-quvvatlash yordamchisi keyin foydalanuvchi savoliga tegishli tartibni topib, javob yozish bosqichiga yuborishi mumkin. Mistral Embed raqamli ifodalash bosqichini bajaradi; o‘zi yakuniy izoh yozmaydi yoki tashqi amalni bajarmaydi.

Boshqa hujjatlashtirilgan foydalanishlar

Ishlab chiqaruvchi embedding jarayonlari orasida qayta ifodalarni aniqlash, tasniflash, klasterlash va batch qayta ishlashni ham ko‘rsatadi. Taqqoslash vazifasi tekshirish uchun ma’nosi bog‘liq parchalarni topishi mumkin. Tasniflash jarayoni kirishni yorliqli misollar bilan taqqoslashi yoki vektorlarni alohida tasniflagichga xususiyat sifatida berishi mumkin. Klasterlash jarayoni o‘xshash elementlarni keyingi inson yoki ilova darajasidagi tavsif uchun guruhlashi mumkin.

Ma’lumot tayyorlashdan oldin ifoda maqsadini belgilang. Semantik qidiruv parchasi topilgandan keyin odamga kerak bo‘ladigan ma’lumotni saqlashi, tasniflash misoli esa sinfni farqlaydigan ifodani o‘z ichiga olishi kerak. So‘rov va saqlangan element taqqoslanadigan materialni ifodalashi uchun tayyorlash izchil bo‘lsin.

Nashr va chiqish chegaralari

Hujjatlar va so‘rovlari uchun bir xil model nashri hamda mos ifodadan foydalaning. Boshqa modeldan olingan, koordinatalari soni bir xil vektor avtomatik ravishda ayni semantik makonda bo‘lmaydi. Model yoki ifodani almashtirishda saqlangan elementlar va so‘rovlar mos qolishi kerak.

Bu yozuv ishlab chiqaruvchining 8k konteksti va Mistral Embed’ning hujjatlashtirilgan 1 024 o‘lchamli ifodasi bilan matnli kirish va raqamli vektor chiqishini tavsiflaydi. Codestral Embed’ning sozlanadigan o‘lchamlari va kvantlangan formatlari alohida nomlangan kod modeliga tegishli; ularni bu yerda taxmin qilmaslik kerak. Rasm, audio, yaratilgan nasriy matn va vosita bajarilishi bu matn embedding natijasidan tashqaridagi alohida imkoniyatlardir.

", "aboutText": "Mistral Embed 2312 — ma’noni raqamli ifodalash uchun Mistral AI’ning matn embedding modeli. U matn satri yoki satrlar ro‘yxatini qabul qiladi va har bir kirish uchun embedding qaytaradi. Natija suhbat izohi emas, ilova o‘xshashlik, qidiruv, tasniflash yoki klasterlash uchun ishlatadigan vektordir. Ishlab chiqaruvchining modelga xos sahifasi mistral-embed-2312’ni ko‘rsatadi.\n\nKirish, kontekst va vektor shakli\n\nAynan model sahifasi 8k kontekst yorlig‘ini hujjatlashtiradi. Har bir matn elementini qo‘llanadigan kirish sig‘imi doirasida tayyorlang va element identifikatsiyasini vektor bilan saqlang. Uzun manba hujjatini foydali parchalarga bo‘lish mumkin; keyin to‘g‘ri materialni qaytarish uchun kerakli hujjat sarlavhasi, bo‘lim va manba joyini saqlang.\n\nIshlab chiqaruvchining Mistral Embed qo‘llanmasi kirishning ko‘rinadigan uzunligidan qat’i nazar, har matn embeddingi uchun 1 024 o‘lchamni belgilaydi. Demak, qisqa savol va uzunroq parcha mazmuni hamda token soni farqli bo‘lsa ham bir xil vektor shakliga ega. Bu javob tokenlari budjeti yoki manbaning nechta so‘zi saqlanishi o‘lchovi emas, chiqish ifodasining o‘lchamidir.\n\nHujjatlashtirilgan javob embeddinglar va token ishlatilishi ma’lumotini saqlaydi; endpoint misoli har bir vektorni kirish indeksiga bog‘laydi. Bir nechta matnni qayta ishlashda shu bog‘liqlikni saqlang. Foydali qidiruv natijasini ko‘rsatish yoki keyingi bosqichga manba materiali berish uchun ilovaga raqamli natija bilan birga asl matn va identifikatorlari ham kerak.\n\nSemantik o‘xshashlik\n\nQo‘llanma bog‘liq matnlar embedding makonida yaqin bo‘lishga moyilligini tushuntiradi. Bu bir mavzu yoki talabni turli so‘zlar bilan ifodalagan parchalarni topishni qo‘llab-quvvatlaydi. Bilim bazasi so‘rovi misoli kirishni qanday tiklashni so‘rashi, tegishli tartib esa ayni amal uchun boshqa iboradan foydalanishi mumkin. Ilova faqat aniq so‘z mosligiga tayanmasdan, so‘rov vektorini saqlangan parcha vektorlari bilan taqqoslashi mumkin.\n\nIshlab chiqaruvchi misollari birlik uzunlikka normallangan embeddinglardan foydalanadi. Bunday vektorlarda kosinus o‘xshashligi, skalyar ko‘paytma va Yevklid masofasi raqamli qiymatlari bir xil bo‘lmasa ham izchil o‘xshashlik reytinglarini beradi. Bitta mos taqqoslash usulini tanlang va so‘rov hamda hujjat ifodalarida izchil qo‘llang.\n\nO‘xshashlik ikki bayonot o‘zaro almashtirilishini isbotlamaydi. Manba matnini saqlang va savol uchun muhim shart, sana yoki identifikatorni tekshiring. Ikki parcha bir mavzuga oid bo‘lib, turli tartib-taomil yoki istisnolarni tavsiflashi mumkin. Embedding qidiruv signalini beradi; tanlangan parchani talqin qilish vazifaning alohida qismidir.\n\nQidiruv va manbaga asoslangan javoblar\n\nAmaliy hujjat jarayoni bilim bazasi parchalari uchun vektorlar tayyorlaydi, ularning identifikatorlari va asl matnini saqlaydi, keyin yangi savolni shu to‘plam bilan taqqoslaydi. Tegishli parchalarni manba joylari bilan qaytaring. Ilova bu parchalarni bevosita ko‘rsatishi yoki topilgan materialga asoslangan javob yozadigan matn yaratish modeliga berishi mumkin.\n\nFoydali qidiruv natijasi uchun hujjat sarlavhasi, bo‘lim, parcha va uni topishga ishlatilgan identifikatorni saqlang. Qo‘llab-quvvatlash yordamchisi keyin foydalanuvchi savoliga tegishli tartibni topib, javob yozish bosqichiga yuborishi mumkin. Mistral Embed raqamli ifodalash bosqichini bajaradi; o‘zi yakuniy izoh yozmaydi yoki tashqi amalni bajarmaydi.\n\nBoshqa hujjatlashtirilgan foydalanishlar\n\nIshlab chiqaruvchi embedding jarayonlari orasida qayta ifodalarni aniqlash, tasniflash, klasterlash va batch qayta ishlashni ham ko‘rsatadi. Taqqoslash vazifasi tekshirish uchun ma’nosi bog‘liq parchalarni topishi mumkin. Tasniflash jarayoni kirishni yorliqli misollar bilan taqqoslashi yoki vektorlarni alohida tasniflagichga xususiyat sifatida berishi mumkin. Klasterlash jarayoni o‘xshash elementlarni keyingi inson yoki ilova darajasidagi tavsif uchun guruhlashi mumkin.\n\nMa’lumot tayyorlashdan oldin ifoda maqsadini belgilang. Semantik qidiruv parchasi topilgandan keyin odamga kerak bo‘ladigan ma’lumotni saqlashi, tasniflash misoli esa sinfni farqlaydigan ifodani o‘z ichiga olishi kerak. So‘rov va saqlangan element taqqoslanadigan materialni ifodalashi uchun tayyorlash izchil bo‘lsin.\n\nNashr va chiqish chegaralari\n\nHujjatlar va so‘rovlari uchun bir xil model nashri hamda mos ifodadan foydalaning. Boshqa modeldan olingan, koordinatalari soni bir xil vektor avtomatik ravishda ayni semantik makonda bo‘lmaydi. Model yoki ifodani almashtirishda saqlangan elementlar va so‘rovlar mos qolishi kerak.\n\nBu yozuv ishlab chiqaruvchining 8k konteksti va Mistral Embed’ning hujjatlashtirilgan 1 024 o‘lchamli ifodasi bilan matnli kirish va raqamli vektor chiqishini tavsiflaydi. Codestral Embed’ning sozlanadigan o‘lchamlari va kvantlangan formatlari alohida nomlangan kod modeliga tegishli; ularni bu yerda taxmin qilmaslik kerak. Rasm, audio, yaratilgan nasriy matn va vosita bajarilishi bu matn embedding natijasidan tashqaridagi alohida imkoniyatlardir.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "c78cf2a17c9b7f1008a1797c6fa92c3378d758b45513ce8af65b72f593cef448", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "uz", "methods": [ { "html": "
•

Mistral: Mistral Embed 2312

Mistral /mistralai/mistral-embed-2312

Boshlash

Mistral Embed 2312 matnni semantik qidiruv, topish va bog‘liq matnni tahlil qilish uchun 1 024 o‘lchamli vektorlarga aylantiradi. Ishlab chiqaruvchi sahifasi 8k kontekstni hujjatlashtiradi; natija yaratilgan javob emas, har bir kirishga bog‘langan raqamli ifodadir.

Qabul qilinadigan kirish ma’lumotlari
Matn · token_ids
Natijalar
embedding
Model haqida

Bu tavsif model imkoniyatlarini yoritadi. Ailoot da tanlangan usul uchun mavjud kirish, chiqish va parametrlar quyida keltirilgan.

Mistral Embed 2312 — ma’noni raqamli ifodalash uchun Mistral AI’ning matn embedding modeli. U matn satri yoki satrlar ro‘yxatini qabul qiladi va har bir kirish uchun embedding qaytaradi. Natija suhbat izohi emas, ilova o‘xshashlik, qidiruv, tasniflash yoki klasterlash uchun ishlatadigan vektordir. Ishlab chiqaruvchining modelga xos sahifasi mistral-embed-2312’ni ko‘rsatadi.

Kirish, kontekst va vektor shakli

Aynan model sahifasi 8k kontekst yorlig‘ini hujjatlashtiradi. Har bir matn elementini qo‘llanadigan kirish sig‘imi doirasida tayyorlang va element identifikatsiyasini vektor bilan saqlang. Uzun manba hujjatini foydali parchalarga bo‘lish mumkin; keyin to‘g‘ri materialni qaytarish uchun kerakli hujjat sarlavhasi, bo‘lim va manba joyini saqlang.

Ishlab chiqaruvchining Mistral Embed qo‘llanmasi kirishning ko‘rinadigan uzunligidan qat’i nazar, har matn embeddingi uchun 1 024 o‘lchamni belgilaydi. Demak, qisqa savol va uzunroq parcha mazmuni hamda token soni farqli bo‘lsa ham bir xil vektor shakliga ega. Bu javob tokenlari budjeti yoki manbaning nechta so‘zi saqlanishi o‘lchovi emas, chiqish ifodasining o‘lchamidir.

Hujjatlashtirilgan javob embeddinglar va token ishlatilishi ma’lumotini saqlaydi; endpoint misoli har bir vektorni kirish indeksiga bog‘laydi. Bir nechta matnni qayta ishlashda shu bog‘liqlikni saqlang. Foydali qidiruv natijasini ko‘rsatish yoki keyingi bosqichga manba materiali berish uchun ilovaga raqamli natija bilan birga asl matn va identifikatorlari ham kerak.

Semantik o‘xshashlik

Qo‘llanma bog‘liq matnlar embedding makonida yaqin bo‘lishga moyilligini tushuntiradi. Bu bir mavzu yoki talabni turli so‘zlar bilan ifodalagan parchalarni topishni qo‘llab-quvvatlaydi. Bilim bazasi so‘rovi misoli kirishni qanday tiklashni so‘rashi, tegishli tartib esa ayni amal uchun boshqa iboradan foydalanishi mumkin. Ilova faqat aniq so‘z mosligiga tayanmasdan, so‘rov vektorini saqlangan parcha vektorlari bilan taqqoslashi mumkin.

Ishlab chiqaruvchi misollari birlik uzunlikka normallangan embeddinglardan foydalanadi. Bunday vektorlarda kosinus o‘xshashligi, skalyar ko‘paytma va Yevklid masofasi raqamli qiymatlari bir xil bo‘lmasa ham izchil o‘xshashlik reytinglarini beradi. Bitta mos taqqoslash usulini tanlang va so‘rov hamda hujjat ifodalarida izchil qo‘llang.

O‘xshashlik ikki bayonot o‘zaro almashtirilishini isbotlamaydi. Manba matnini saqlang va savol uchun muhim shart, sana yoki identifikatorni tekshiring. Ikki parcha bir mavzuga oid bo‘lib, turli tartib-taomil yoki istisnolarni tavsiflashi mumkin. Embedding qidiruv signalini beradi; tanlangan parchani talqin qilish vazifaning alohida qismidir.

Qidiruv va manbaga asoslangan javoblar

Amaliy hujjat jarayoni bilim bazasi parchalari uchun vektorlar tayyorlaydi, ularning identifikatorlari va asl matnini saqlaydi, keyin yangi savolni shu to‘plam bilan taqqoslaydi. Tegishli parchalarni manba joylari bilan qaytaring. Ilova bu parchalarni bevosita ko‘rsatishi yoki topilgan materialga asoslangan javob yozadigan matn yaratish modeliga berishi mumkin.

Foydali qidiruv natijasi uchun hujjat sarlavhasi, bo‘lim, parcha va uni topishga ishlatilgan identifikatorni saqlang. Qo‘llab-quvvatlash yordamchisi keyin foydalanuvchi savoliga tegishli tartibni topib, javob yozish bosqichiga yuborishi mumkin. Mistral Embed raqamli ifodalash bosqichini bajaradi; o‘zi yakuniy izoh yozmaydi yoki tashqi amalni bajarmaydi.

Boshqa hujjatlashtirilgan foydalanishlar

Ishlab chiqaruvchi embedding jarayonlari orasida qayta ifodalarni aniqlash, tasniflash, klasterlash va batch qayta ishlashni ham ko‘rsatadi. Taqqoslash vazifasi tekshirish uchun ma’nosi bog‘liq parchalarni topishi mumkin. Tasniflash jarayoni kirishni yorliqli misollar bilan taqqoslashi yoki vektorlarni alohida tasniflagichga xususiyat sifatida berishi mumkin. Klasterlash jarayoni o‘xshash elementlarni keyingi inson yoki ilova darajasidagi tavsif uchun guruhlashi mumkin.

Ma’lumot tayyorlashdan oldin ifoda maqsadini belgilang. Semantik qidiruv parchasi topilgandan keyin odamga kerak bo‘ladigan ma’lumotni saqlashi, tasniflash misoli esa sinfni farqlaydigan ifodani o‘z ichiga olishi kerak. So‘rov va saqlangan element taqqoslanadigan materialni ifodalashi uchun tayyorlash izchil bo‘lsin.

Nashr va chiqish chegaralari

Hujjatlar va so‘rovlari uchun bir xil model nashri hamda mos ifodadan foydalaning. Boshqa modeldan olingan, koordinatalari soni bir xil vektor avtomatik ravishda ayni semantik makonda bo‘lmaydi. Model yoki ifodani almashtirishda saqlangan elementlar va so‘rovlar mos qolishi kerak.

Bu yozuv ishlab chiqaruvchining 8k konteksti va Mistral Embed’ning hujjatlashtirilgan 1 024 o‘lchamli ifodasi bilan matnli kirish va raqamli vektor chiqishini tavsiflaydi. Codestral Embed’ning sozlanadigan o‘lchamlari va kvantlangan formatlari alohida nomlangan kod modeliga tegishli; ularni bu yerda taxmin qilmaslik kerak. Rasm, audio, yaratilgan nasriy matn va vosita bajarilishi bu matn embedding natijasidan tashqaridagi alohida imkoniyatlardir.

Ailoot da mavjud · kirish ma’lumotlari va usullar

Ailoot Ultra · Embeddinglar POST /v1/embeddings
Kirish
text, token_ids
Chiqish
embedding
Kontekst
8 192 tokens
Chiqish formati
json
MaydonTurTalabQiymatlar va cheklovlarStandart
MaydonmodelTurstringTalabMajburiyQiymatlar va cheklovlar
mistralai/mistral-embed-2312
Standart—
MaydoninputTurstring|string[]|integer[]|integer[][]TalabMajburiyQiymatlar va cheklovlar
Elementlarning eng kam soni: 1
Shartlar: Bo‘sh bo‘lmagan, bir xil turdagi elementlardan iborat paket. Token ID lari manfiy bo‘lmagan butun sonlardir.
Kirish budjeti: Eng ko‘p: 8 192 · Matn birligi: UTF8 baytlari · Token birligi: Tokenlar massivi elementlari
Standart—
Maydonencoding_formatTurstringTalabIxtiyoriyQiymatlar va cheklovlar
float
Standartfloat
MaydondimensionsTurintegerTalabQo‘llab-quvvatlanmaydiQiymatlar va cheklovlar
Eng kam: 1
Standart—
MaydonuserTurjson_valueTalabIxtiyoriyQiymatlar va cheklovlar
Shartlar: Manba ushbu JSON metama’lumot maydoniga ruxsat beradi; uning ta’minotchi xizmatidagi aniq ma’nosi modelga bog‘liq.
Standart—
Maydonsession_idTurjson_valueTalabIxtiyoriyQiymatlar va cheklovlar
Shartlar: Manba ushbu JSON metama’lumot maydoniga ruxsat beradi; uning ta’minotchi xizmatidagi aniq ma’nosi modelga bog‘liq.
Standart—
MaydontraceTurjson_valueTalabIxtiyoriyQiymatlar va cheklovlar
Shartlar: Manba ushbu JSON metama’lumot maydoniga ruxsat beradi; uning ta’minotchi xizmatidagi aniq ma’nosi modelga bog‘liq.
Standart—
MaydonproviderTurobjectTalabIxtiyoriyQiymatlar va cheklovlar
Shartlar: provider.options rad etildi
Standart—
Kirish materiallari birikmalari

text_to_embedding

Usul parametrlari va hayot sikli
ParametrParametr talablari
Parametrcontent_typeParametr talablariapplication/json
ParametrrequiredParametr talablarimodel, input
Parametrinput_shapesParametr talablaristring, string[], nonnegative_integer_token_array, nonnegative_integer_token_array[]
Parametrencoding_formatParametr talablarifloat
Parametrdimensions_overrideParametr talablarifalse
Parametrmax_input_budget_unitsParametr talablari8192
Parametrmultimodal_objectsParametr talablarifalse
Parametrmaterial_typesParametr talablaritext, token_ids

Hayot sikli: synchronous_json

Har bir vektorning indeksi va o‘lchamini saqlang.

Model nomida multimodal deyilgani aynan shu yo‘nalishda rasm obyektlariga ruxsat borligini anglatmaydi.

Tariflar

Tarif ma’lumotlari so‘rov imkoniyatlarini qo‘shmaydi. Qo‘llab-quvvatlanadigan parametrlar tanlangan usulda ko‘rsatilgan.

Tezkor rejim
Standart tarif Tezkor rejim tanlanganda
Flex rejimi
Standart tarif flex rejimi tanlanganda
Maksimal fikrlash darajasi
Standart tarif Maksimal fikrlash darajasi uchun standart (default) tuzatish qo‘llanganda

Ailoot tariflari

Sozlamalar bo‘yicha narxlar

SozlamaTariflar jadvaliTo‘lov
SozlamaTokenlar uchun bazaviy tariflarTariflar jadvaliAsosiy tarifTo‘lov
Kirish · Kirish tokenlari $0.0002 / 1K token
Chiqish · Chiqish tokenlari $0 / 1K token
Kirish · Keshdan o‘qish — / 1K token
Kirish · Keshga yozish — / 1K token
Kirish · Keshga yozish, 1 soat — / 1K token

Ailoot so‘rovdan oldin taxminiy summani band qiladi. Natijadan keyin o‘lchangan sarf asosidagi yakuniy to‘lovni yechadi. Oqimli javob bo‘yicha yakuniy hisob-kitob yakuniy sarf yozuviga asoslanadi. Summani band qilish va to‘lovni hisoblash tartibi →

So‘rov namunalari

Ailoot Ultra · Embeddinglar

set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "mistralai/mistral-embed-2312", "input": ["First document", "Second document"]}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/embeddings \\\n  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("data",[]): print(json.dumps({"index":x.get("index"),"embedding":x.get("embedding")}))\nPY_RESULT\n

Natijalarni olish va saqlash

Ailoot Ultra · Embeddinglar

json

Barcha tayyor natijalarni saqlash

Qaytarilgan har bir to‘liq javob, fayl va kontent qismini saqlang.

Har bir vektorni indeksi bilan saqlang. Vektorlar soni kirish elementlari soniga teng bo‘lishi va o‘lchamlar bir xil bo‘lishi kerak.

Asl javobni tekshirish kerak bo‘lsa

Embedding vazifalari uchun endpoint qo‘shilmaydi.

Javob maydonlari
MaydonTur
MaydonobjectTurstring
MaydonmodelTurstring
Maydondata[].indexTurinteger
Maydondata[].embeddingTurfinite float[]
MaydonusageTurobject
Xatolar va keyingi qadamlar
JavobShartKeyingi qadam
Javob400 · invalid_request_errorShartMajburiy maydonlar, material ifodasi yoki parametr qiymati noto‘g‘riKeyingi qadamYangi yaratish so‘rovidan oldin ko‘rsatilgan maydonlarni tuzating.

Taxalluslar

Model taxalluslari

Ailoot Ultra mistralai/mistral-embed-2312

Usul yo‘llari taxalluslari

Yuqorida ko‘rsatilgan usul yo‘llaridan foydalaning.

Chaqirish uchun tegishli ID lar

mistralai/mistral-embed-2312

", "method_identity": { "effective_request_model_id": "mistralai/mistral-embed-2312", "fmt": "embeddings", "http": "POST", "path": "/v1/embeddings", "request_model_id": "mistralai/mistral-embed-2312", "route_label": "Ultra" }, "method_key": "Ultra|embeddings|/v1/embeddings|mistralai%2Fmistral-embed-2312", "ordinal": 0, "rawMethod": { "available": null, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Keep every vector with its index. Vector count must equal input count; dimensions must be consistent.", "errors": [ { "code": null, "condition": "Majburiy maydonlar, material ifodasi yoki parametr qiymati noto‘g‘ri", "http_status": 400, "recovery": "Yangi yaratish so‘rovidan oldin ko‘rsatilgan maydonlarni tuzating.", "type": "invalid_request_error" } ], "hints": [], "ignored_fields": [], "lifecycle": { "create": { "http": "POST", "path": "/v1/embeddings" }, "job_read": null, "mode": "synchronous_json", "unknown": "Embedding vazifalari uchun endpoint qo‘shilmaydi." }, "material_combinations": [ { "alternatives": [ "string", "string[]", "nonnegative_integer_token_array", "nonnegative_integer_token_array[]" ], "mode": "text_to_embedding" } ], "operation_modes": [ "single_embedding", "batched_embeddings" ], "outputs": { "all_results": "Har bir vektorni indeksi bilan saqlang. Vektorlar soni kirish elementlari soniga teng bo‘lishi va o‘lchamlar bir xil bo‘lishi kerak.", "default_dimensions": null, "family": "embedding", "fields": [ { "description": null, "name": "object", "type": "string" }, { "description": null, "name": "model", "type": "string" }, { "description": null, "name": "data[].index", "type": "integer" }, { "description": null, "name": "data[].embedding", "type": "finite float[]" }, { "description": null, "name": "usage", "type": "object" } ], "format": "json" }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "mistralai/mistral-embed-2312" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "budget": { "maximum": 8192, "text_unit": "UTF8 baytlari", "token_unit": "Tokenlar massivi elementlari" }, "conditions": "Bo‘sh bo‘lmagan, bir xil turdagi elementlardan iborat paket. Token ID lari manfiy bo‘lmagan butun sonlardir.", "default": null, "default_known": false, "enum": null, "enum_known": false, "min_items": 1, "name": "input", "required": true, "type": "string|string[]|integer[]|integer[][]" }, { "availability": "source_interface", "default": "float", "default_known": true, "enum": [ "float" ], "enum_known": true, "name": "encoding_format", "required": false, "type": "string" }, { "availability": "unsupported", "default": null, "default_known": false, "enum": null, "enum_known": false, "minimum": 1, "name": "dimensions", "required": false, "type": "integer" }, { "availability": "pass_through_metadata", "conditions": "Manba ushbu JSON metama’lumot maydoniga ruxsat beradi; uning ta’minotchi xizmatidagi aniq ma’nosi modelga bog‘liq.", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "user", "required": false, "type": "json_value" }, { "availability": "pass_through_metadata", "conditions": "Manba ushbu JSON metama’lumot maydoniga ruxsat beradi; uning ta’minotchi xizmatidagi aniq ma’nosi modelga bog‘liq.", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "session_id", "required": false, "type": "json_value" }, { "availability": "pass_through_metadata", "conditions": "Manba ushbu JSON metama’lumot maydoniga ruxsat beradi; uning ta’minotchi xizmatidagi aniq ma’nosi modelga bog‘liq.", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "trace", "required": false, "type": "json_value" }, { "availability": "source_interface", "conditions": "provider.options rad etildi", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "provider", "required": false, "type": "object" } ], "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.", "unsupported": [ "mixed input kinds", "empty input", "image/audio/file objects", "encoding_format=base64", "dimensions override" ] }, "hints": [ "Har bir vektorning indeksi va o‘lchamini saqlang.", "Model nomida multimodal deyilgani aynan shu yo‘nalishda rasm obyektlariga ruxsat borligini anglatmaydi." ], "input": { "content_type": "application/json", "dimensions_override": false, "encoding_format": [ "float" ], "input_shapes": [ "string", "string[]", "nonnegative_integer_token_array", "nonnegative_integer_token_array[]" ], "material_types": [ "text", "token_ids" ], "max_input_budget_units": 8192, "multimodal_objects": false, "required": [ "model", "input" ] }, "lifecycle": { "mode": "synchronous_json", "unknown": "no embedding job endpoint inferred" }, "manufacturer_capability": null, "method": { "http": "POST", "path": "/v1/embeddings" }, "method_aliases": [], "operation_modes": [ "text_to_embedding" ], "output": { "default_dimensions": null, "family": "embedding", "format": "json", "http_success": 200, "vectors": "one dense float vector per input; indices/model/usage validated" } }, "ctx": 8192, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Tokenlar uchun bazaviy tariflar", "units": [ { "amount": "0.0002000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000002", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"mistralai/mistral-embed-2312\", \"input\": [\"First document\", \"Second document\"]}')\n\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/embeddings \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path(\"result.json\").read_text())\nfor x in r.get(\"data\",[]): print(json.dumps({\"index\":x.get(\"index\"),\"embedding\":x.get(\"embedding\")}))\nPY_RESULT\n", "label": "curl · retained exact creation", "language": "bash" }, { "code": "from openai import OpenAI\nimport os\n\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nresult=client.embeddings.create(model='mistralai/mistral-embed-2312',input=[\"First document\",\"Second document\"])\nprint(result)\nfor item in result.data:print(item.index,item.embedding)\n", "label": "Python SDK · all vectors", "language": "python" } ], "family": "openai", "fast_multiplier": 1, "flex_multiplier": 1, "fmt": "embeddings", "hints": [ "Keep every vector index and dimension.", "Multimodal model name does not admit image objects on this exact path." ], "http": "POST", "in": 0.2, "input": [ "text", "token_ids" ], "label": "Эмбеддинги", "max_out": null, "max_reasoning_effort_multiplier": 1, "method_aliases": [], "out": 0, "output": [ "embedding" ], "path": "/v1/embeddings", "price_conditions": [ { "label": "Tezkor rejim", "value": "Standart tarif", "when": "Tezkor rejim tanlanganda" }, { "label": "Flex rejimi", "value": "Standart tarif", "when": "flex rejimi tanlanganda" }, { "label": "Maksimal fikrlash darajasi", "value": "Standart tarif", "when": "Maksimal fikrlash darajasi uchun standart (default) tuzatish qo‘llanganda" } ], "pricing": { "billing_mode": "token", "image_input_price": null, "image_output_price": null, "per_request_price": null }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0.0002000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000002", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "request_model_id": "mistralai/mistral-embed-2312", "route_label": "Ultra", "status_reads": [], "tiers": [], "units": [ { "amount": "0.0002000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000002", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } } ], "model_id": "mistralai/mistral-embed-2312", "nativeProvenance": { "input_facts_canonical_sha256": "ef59bd5da2a43f53fca98ea83bae6d20cda62e04d98d9413c387247c708d29d0", "input_html_sha256": "573037d39030cb80e149c8db0d8682da27dfd97a345e547ac21e9d77199c7138", "private_audit_sha256": "fd0a65f34d2fa4998e7fe724da44da871873ec731933524ff43275211d494d69", "role": "historical-normalized-input-audit-hashes", "schema": "ailoot-native-model-provenance-v2" }, "page": { "canonical": "https://ailoot.ai/models/uz/mistralai-mistral-embed-2312/", "description": "Mistral Embed 2312 matnni semantik qidiruv, topish va bog‘liq matnni tahlil qilish uchun 1 024 o‘lchamli vektorlarga aylantiradi. Ishlab chiqaruvchi sahifasi 8k kontekstni hujjatlashtiradi; natija yaratilgan javob emas, har bir kirishga bog‘langan raqamli ifodadir.", "locale": "uz", "md_url": "https://ailoot.ai/models/uz/mistralai-mistral-embed-2312/index.md", "title": "Mistral: Mistral Embed 2312 — Ailoot", "url": "https://ailoot.ai/models/uz/mistralai-mistral-embed-2312/" }, "rawModel": { "about": "Mistral Embed 2312 — ma’noni raqamli ifodalash uchun Mistral AI’ning matn embedding modeli. U matn satri yoki satrlar ro‘yxatini qabul qiladi va har bir kirish uchun embedding qaytaradi. Natija suhbat izohi emas, ilova o‘xshashlik, qidiruv, tasniflash yoki klasterlash uchun ishlatadigan vektordir. Ishlab chiqaruvchining modelga xos sahifasi mistral-embed-2312’ni ko‘rsatadi.\n\nKirish, kontekst va vektor shakli\n\nAynan model sahifasi 8k kontekst yorlig‘ini hujjatlashtiradi. Har bir matn elementini qo‘llanadigan kirish sig‘imi doirasida tayyorlang va element identifikatsiyasini vektor bilan saqlang. Uzun manba hujjatini foydali parchalarga bo‘lish mumkin; keyin to‘g‘ri materialni qaytarish uchun kerakli hujjat sarlavhasi, bo‘lim va manba joyini saqlang.\n\nIshlab chiqaruvchining Mistral Embed qo‘llanmasi kirishning ko‘rinadigan uzunligidan qat’i nazar, har matn embeddingi uchun 1 024 o‘lchamni belgilaydi. Demak, qisqa savol va uzunroq parcha mazmuni hamda token soni farqli bo‘lsa ham bir xil vektor shakliga ega. Bu javob tokenlari budjeti yoki manbaning nechta so‘zi saqlanishi o‘lchovi emas, chiqish ifodasining o‘lchamidir.\n\nHujjatlashtirilgan javob embeddinglar va token ishlatilishi ma’lumotini saqlaydi; endpoint misoli har bir vektorni kirish indeksiga bog‘laydi. Bir nechta matnni qayta ishlashda shu bog‘liqlikni saqlang. Foydali qidiruv natijasini ko‘rsatish yoki keyingi bosqichga manba materiali berish uchun ilovaga raqamli natija bilan birga asl matn va identifikatorlari ham kerak.\n\nSemantik o‘xshashlik\n\nQo‘llanma bog‘liq matnlar embedding makonida yaqin bo‘lishga moyilligini tushuntiradi. Bu bir mavzu yoki talabni turli so‘zlar bilan ifodalagan parchalarni topishni qo‘llab-quvvatlaydi. Bilim bazasi so‘rovi misoli kirishni qanday tiklashni so‘rashi, tegishli tartib esa ayni amal uchun boshqa iboradan foydalanishi mumkin. Ilova faqat aniq so‘z mosligiga tayanmasdan, so‘rov vektorini saqlangan parcha vektorlari bilan taqqoslashi mumkin.\n\nIshlab chiqaruvchi misollari birlik uzunlikka normallangan embeddinglardan foydalanadi. Bunday vektorlarda kosinus o‘xshashligi, skalyar ko‘paytma va Yevklid masofasi raqamli qiymatlari bir xil bo‘lmasa ham izchil o‘xshashlik reytinglarini beradi. Bitta mos taqqoslash usulini tanlang va so‘rov hamda hujjat ifodalarida izchil qo‘llang.\n\nO‘xshashlik ikki bayonot o‘zaro almashtirilishini isbotlamaydi. Manba matnini saqlang va savol uchun muhim shart, sana yoki identifikatorni tekshiring. Ikki parcha bir mavzuga oid bo‘lib, turli tartib-taomil yoki istisnolarni tavsiflashi mumkin. Embedding qidiruv signalini beradi; tanlangan parchani talqin qilish vazifaning alohida qismidir.\n\nQidiruv va manbaga asoslangan javoblar\n\nAmaliy hujjat jarayoni bilim bazasi parchalari uchun vektorlar tayyorlaydi, ularning identifikatorlari va asl matnini saqlaydi, keyin yangi savolni shu to‘plam bilan taqqoslaydi. Tegishli parchalarni manba joylari bilan qaytaring. Ilova bu parchalarni bevosita ko‘rsatishi yoki topilgan materialga asoslangan javob yozadigan matn yaratish modeliga berishi mumkin.\n\nFoydali qidiruv natijasi uchun hujjat sarlavhasi, bo‘lim, parcha va uni topishga ishlatilgan identifikatorni saqlang. Qo‘llab-quvvatlash yordamchisi keyin foydalanuvchi savoliga tegishli tartibni topib, javob yozish bosqichiga yuborishi mumkin. Mistral Embed raqamli ifodalash bosqichini bajaradi; o‘zi yakuniy izoh yozmaydi yoki tashqi amalni bajarmaydi.\n\nBoshqa hujjatlashtirilgan foydalanishlar\n\nIshlab chiqaruvchi embedding jarayonlari orasida qayta ifodalarni aniqlash, tasniflash, klasterlash va batch qayta ishlashni ham ko‘rsatadi. Taqqoslash vazifasi tekshirish uchun ma’nosi bog‘liq parchalarni topishi mumkin. Tasniflash jarayoni kirishni yorliqli misollar bilan taqqoslashi yoki vektorlarni alohida tasniflagichga xususiyat sifatida berishi mumkin. Klasterlash jarayoni o‘xshash elementlarni keyingi inson yoki ilova darajasidagi tavsif uchun guruhlashi mumkin.\n\nMa’lumot tayyorlashdan oldin ifoda maqsadini belgilang. Semantik qidiruv parchasi topilgandan keyin odamga kerak bo‘ladigan ma’lumotni saqlashi, tasniflash misoli esa sinfni farqlaydigan ifodani o‘z ichiga olishi kerak. So‘rov va saqlangan element taqqoslanadigan materialni ifodalashi uchun tayyorlash izchil bo‘lsin.\n\nNashr va chiqish chegaralari\n\nHujjatlar va so‘rovlari uchun bir xil model nashri hamda mos ifodadan foydalaning. Boshqa modeldan olingan, koordinatalari soni bir xil vektor avtomatik ravishda ayni semantik makonda bo‘lmaydi. Model yoki ifodani almashtirishda saqlangan elementlar va so‘rovlar mos qolishi kerak.\n\nBu yozuv ishlab chiqaruvchining 8k konteksti va Mistral Embed’ning hujjatlashtirilgan 1 024 o‘lchamli ifodasi bilan matnli kirish va raqamli vektor chiqishini tavsiflaydi. Codestral Embed’ning sozlanadigan o‘lchamlari va kvantlangan formatlari alohida nomlangan kod modeliga tegishli; ularni bu yerda taxmin qilmaslik kerak. Rasm, audio, yaratilgan nasriy matn va vosita bajarilishi bu matn embedding natijasidan tashqaridagi alohida imkoniyatlardir.", "alias_of": null, "aliases": [], "author": "Mistral", "available": null, "canonical_model": "mistralai/mistral-embed-2312", "capabilities": { "context_length": 8192, "manufacturer_input": [ "text" ], "manufacturer_output": [ "embeddings" ] }, "card_routes": [ { "label": "Ultra", "rates": [ { "amount": "0.0002000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000002", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" } ], "summary": "Konfiguratsiya narxlari tafsilotlarda to‘liq ko‘rsatilgan." } ], "ctx": 8192, "entity_type": "model", "formats": [ "embeddings" ], "id": "mistralai/mistral-embed-2312", "input": [ "text", "token_ids" ], "kind": "embedding", "max_out": null, "methods": [ { "available": null, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Keep every vector with its index. Vector count must equal input count; dimensions must be consistent.", "errors": [ { "code": null, "condition": "Majburiy maydonlar, material ifodasi yoki parametr qiymati noto‘g‘ri", "http_status": 400, "recovery": "Yangi yaratish so‘rovidan oldin ko‘rsatilgan maydonlarni tuzating.", "type": "invalid_request_error" } ], "hints": [], "ignored_fields": [], "lifecycle": { "create": { "http": "POST", "path": "/v1/embeddings" }, "job_read": null, "mode": "synchronous_json", "unknown": "Embedding vazifalari uchun endpoint qo‘shilmaydi." }, "material_combinations": [ { "alternatives": [ "string", "string[]", "nonnegative_integer_token_array", "nonnegative_integer_token_array[]" ], "mode": "text_to_embedding" } ], "operation_modes": [ "single_embedding", "batched_embeddings" ], "outputs": { "all_results": "Har bir vektorni indeksi bilan saqlang. Vektorlar soni kirish elementlari soniga teng bo‘lishi va o‘lchamlar bir xil bo‘lishi kerak.", "default_dimensions": null, "family": "embedding", "fields": [ { "description": null, "name": "object", "type": "string" }, { "description": null, "name": "model", "type": "string" }, { "description": null, "name": "data[].index", "type": "integer" }, { "description": null, "name": "data[].embedding", "type": "finite float[]" }, { "description": null, "name": "usage", "type": "object" } ], "format": "json" }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "mistralai/mistral-embed-2312" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "budget": { "maximum": 8192, "text_unit": "UTF8 baytlari", "token_unit": "Tokenlar massivi elementlari" }, "conditions": "Bo‘sh bo‘lmagan, bir xil turdagi elementlardan iborat paket. Token ID lari manfiy bo‘lmagan butun sonlardir.", "default": null, "default_known": false, "enum": null, "enum_known": false, "min_items": 1, "name": "input", "required": true, "type": "string|string[]|integer[]|integer[][]" }, { "availability": "source_interface", "default": "float", "default_known": true, "enum": [ "float" ], "enum_known": true, "name": "encoding_format", "required": false, "type": "string" }, { "availability": "unsupported", "default": null, "default_known": false, "enum": null, "enum_known": false, "minimum": 1, "name": "dimensions", "required": false, "type": "integer" }, { "availability": "pass_through_metadata", "conditions": "Manba ushbu JSON metama’lumot maydoniga ruxsat beradi; uning ta’minotchi xizmatidagi aniq ma’nosi modelga bog‘liq.", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "user", "required": false, "type": "json_value" }, { "availability": "pass_through_metadata", "conditions": "Manba ushbu JSON metama’lumot maydoniga ruxsat beradi; uning ta’minotchi xizmatidagi aniq ma’nosi modelga bog‘liq.", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "session_id", "required": false, "type": "json_value" }, { "availability": "pass_through_metadata", "conditions": "Manba ushbu JSON metama’lumot maydoniga ruxsat beradi; uning ta’minotchi xizmatidagi aniq ma’nosi modelga bog‘liq.", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "trace", "required": false, "type": "json_value" }, { "availability": "source_interface", "conditions": "provider.options rad etildi", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "provider", "required": false, "type": "object" } ], "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.", "unsupported": [ "mixed input kinds", "empty input", "image/audio/file objects", "encoding_format=base64", "dimensions override" ] }, "hints": [ "Har bir vektorning indeksi va o‘lchamini saqlang.", "Model nomida multimodal deyilgani aynan shu yo‘nalishda rasm obyektlariga ruxsat borligini anglatmaydi." ], "input": { "content_type": "application/json", "dimensions_override": false, "encoding_format": [ "float" ], "input_shapes": [ "string", "string[]", "nonnegative_integer_token_array", "nonnegative_integer_token_array[]" ], "material_types": [ "text", "token_ids" ], "max_input_budget_units": 8192, "multimodal_objects": false, "required": [ "model", "input" ] }, "lifecycle": { "mode": "synchronous_json", "unknown": "no embedding job endpoint inferred" }, "manufacturer_capability": null, "method": { "http": "POST", "path": "/v1/embeddings" }, "method_aliases": [], "operation_modes": [ "text_to_embedding" ], "output": { "default_dimensions": null, "family": "embedding", "format": "json", "http_success": 200, "vectors": "one dense float vector per input; indices/model/usage validated" } }, "ctx": 8192, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Tokenlar uchun bazaviy tariflar", "units": [ { "amount": "0.0002000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000002", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"mistralai/mistral-embed-2312\", \"input\": [\"First document\", \"Second document\"]}')\n\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/embeddings \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path(\"result.json\").read_text())\nfor x in r.get(\"data\",[]): print(json.dumps({\"index\":x.get(\"index\"),\"embedding\":x.get(\"embedding\")}))\nPY_RESULT\n", "label": "curl · retained exact creation", "language": "bash" }, { "code": "from openai import OpenAI\nimport os\n\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nresult=client.embeddings.create(model='mistralai/mistral-embed-2312',input=[\"First document\",\"Second document\"])\nprint(result)\nfor item in result.data:print(item.index,item.embedding)\n", "label": "Python SDK · all vectors", "language": "python" } ], "family": "openai", "fast_multiplier": 1, "flex_multiplier": 1, "fmt": "embeddings", "hints": [ "Keep every vector index and dimension.", "Multimodal model name does not admit image objects on this exact path." ], "http": "POST", "in": 0.2, "input": [ "text", "token_ids" ], "label": "Эмбеддинги", "max_out": null, "max_reasoning_effort_multiplier": 1, "method_aliases": [], "out": 0, "output": [ "embedding" ], "path": "/v1/embeddings", "price_conditions": [ { "label": "Tezkor rejim", "value": "Standart tarif", "when": "Tezkor rejim tanlanganda" }, { "label": "Flex rejimi", "value": "Standart tarif", "when": "flex rejimi tanlanganda" }, { "label": "Maksimal fikrlash darajasi", "value": "Standart tarif", "when": "Maksimal fikrlash darajasi uchun standart (default) tuzatish qo‘llanganda" } ], "pricing": { "billing_mode": "token", "image_input_price": null, "image_output_price": null, "per_request_price": null }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0.0002000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000002", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "request_model_id": "mistralai/mistral-embed-2312", "route_label": "Ultra", "status_reads": [], "tiers": [], "units": [ { "amount": "0.0002000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000002", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "model_aliases": [ { "canonical_model_id": "mistralai/mistral-embed-2312", "request_model_id": "mistralai/mistral-embed-2312", "route_label": "Ultra" } ], "name": "Mistral: Mistral Embed 2312", "price": { "in": 0.2, "in_label": null, "out": 0, "out_label": null, "scope_label": "Token rates", "sort_in": 0.2, "sort_out": 0, "varies": false }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Эмбеддинги · Base token rates", "units": [ { "amount": "0.0002000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000002", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "public_id": "mistralai/mistral-embed-2312", "short": "Mistral Embed 2312 matnni semantik qidiruv, topish va bog‘liq matnni tahlil qilish uchun 1 024 o‘lchamli vektorlarga aylantiradi. Ishlab chiqaruvchi sahifasi 8k kontekstni hujjatlashtiradi; natija yaratilgan javob emas, har bir kirishga bog‘langan raqamli ifodadir." }, "renderer_schema": { "method_order": "Original DTO methods order; every exact route/format/path/caller survives.", "prices": "Original public DTO fields and original native display HTML; no flattened or normalized offers." }, "representation": "exact-public-dto-and-native-renderer-html", "representationNotes": { "current_reference": { "about_json_pointer": "/aboutHtml", "methods": [ { "contract_json_pointer": "/methods/0/rawMethod/contract", "html_json_pointer": "/methods/0/html", "method_ordinal": 0 } ], "role": "current-semantic-reference" }, "raw_input": { "examples_role": "historical-input-not-current-ready-examples", "json_pointers": [ "/rawModel", "/methods/0/rawMethod" ], "role": "historical-owner-input" }, "schema": "ailoot-native-model-representations-v1" }, "schema": "ailoot-static-model-facts-v1", "schema_version": 1, "shortText": "Mistral Embed 2312 matnni semantik qidiruv, topish va bog‘liq matnni tahlil qilish uchun 1 024 o‘lchamli vektorlarga aylantiradi. Ishlab chiqaruvchi sahifasi 8k kontekstni hujjatlashtiradi; natija yaratilgan javob emas, har bir kirishga bog‘langan raqamli ifodadir.", "source": { "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1", "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036", "raw_model_json_sha256": "f5c2d975f163d31221f74c5c5ab79dba2bf69ecbe3211c5c374bf2d94eb0b9d0", "renderer_sha256": "aa8a0fca1bd770c042b64987512b6187fca2067aea3ddc877f68b163d80e7df6" }, "sourceRevision": "6862925cdaca558be255775450ebcaf87f3380867f119683d64c5865e29331ab" }