mxbai-embed-large-v1

Free.ai (self-hosted) · embeddings · ~100 tokens per call

mxbai-embed-large-v1 ni an Ìṣàmúlò-ètò tí mixedbread.ai kọ̀. Ó ní ìmọ́ nínú Semantic search, clustering, similarity.. Ààyè àìṣàfilọ́lẹ̀ fún ara rẹ̀ ní àwọn GPUs Free.ai — láàyè láti pàtó àwọn ààyè àìṣàfilọ́lẹ̀ rẹ̀ ní ọjọ́ (100 ààyè Àwọn àgbéwọlé). Ti fi silẹ labẹ Apache 2.0 — lilo iṣowo ti gba laaye lori Free.ai.

Lò nípa API

API REST tí a bá fẹ́ OpenAI. Ṣẹ̀dá bọ́tìnì náà láti pé ìṣàmúlò-ètò yìí nínú àwọn ìsàlẹ̀-ètò.

curl -X POST https://api.free.ai/v1/image/generate/ \
  -H "Authorization: Bearer sk-free-..." \
  -H "Content-Type: application/json" \
  -d '{"model":"mxbai-embed-large-v1","prompt":"your prompt here"}'

Àwọn Àkọsílẹ̀ Gba àwọn àwọn àmì-ìwé API

Àwọn Àtòjọ-ẹ̀yàn

mxbai-embed-large-v1 converts text into a dense vector (a list of floats) that captures meaning. Use it for semantic search, clustering, recommendation, retrieval-augmented generation (RAG), and any task where "is this text similar to that text" matters.

Àwọn ìṣàfarawégbègbè jẹ́ 384, 768, 1024, tàbí 1536 nípa ìpéwọ̀n. BGE-M3 fi 1024-dim pamọ́; OpenAI Ada fi 1536 pamọ́. Àwọn ìṣàfilọ́lẹ̀ API ní àwọn ìṣàfilọ́lẹ̀ láti jẹ́ pé vector DB rẹ̀ tí wọ́n yan ińdírẹ̀sì tó yẹ.

Modern embedding models (including most options on Free.ai) are trained on 100+ languages. Cross-language retrieval works — search in English, match documents in Spanish.

512 si 8,192 token ní pàtó nípa ìṣàmúlò-ètò náà. Àwọn ìṣàfihàn tí o jú lọ ní pàtó - àwọn àkọsílẹ̀ ìgbà nínú àwọn àpáríǹtì láti fi pamọ́.

mxbai-embed-large-v1 n ṣiṣẹ lori awọn GPUs wa ati pe o wa laarin awọn irinṣẹ ti o dara julọ - nipa ~100 awọn tokeni fun ipe kan ti a ṣe lati pool ọfẹ ọjọgbọn rẹ. $5 = 200K awọn tokeni.

Yes — POST a list of strings to /v1/embeddings/ and mxbai-embed-large-v1 returns a list of vectors in the same order. Batch size up to 2,048 per request.

L2-àṣàfilọ́lẹ̀ láti inú ìpéwọ̀n - àkóónú àkóónú = àwọn

Àwọn mìíràn — Pinecone, Weaviate, Qdrant, Chroma, pgvector, FAISS, LanceDB. mxbai-embed-large-v1 yí àwọn ààyè JSON àìdálẹ̀ padà; DB kò rí àwọn módè́lì.

Ya — POST si /v1/embeddings/ pẹlú módè́lọ̀ọ̀kan="mxbai-embed-large-v1". Ìṣàfihàn àwọn àgbékalẹ̀ tí a gbọ́dọ̀ kọ̀ọ̀kan, láti jẹ́ pé àwọn láíbùrẹ́dì klìǹtì tí wà tí n ṣiṣẹ́ láìfilọ́lẹ̀. /api/ ní àgbèkalẹ̀ ìparí.

Self-hosted models keep your text on our GPUs and discard it after the call returns. Premium pass through with a DPA. We do not train on your inputs.

Sub-100ms fun àkọlé àkókó nípa ààyè-ara-ẹni-nípa, 100-500ms nípa àwọn. Agbègbè àwọn ayẹyẹ́ tí a fi pọ̀ jú lọ nípa àwọn - 1,000 chunks tí a tí pari nínú àwọn ìsàlẹ̀-ilà 2-10.

Ya — Free.ai gba ìlòòrò àwọn ìṣàfihàn àwọn ìṣàfihàn. Ṣẹ̀dá ìṣàfihàn ìṣàfihàn, àwọn ìṣàfihàn RAG, àwọn ìṣàfihàn àwọn ìṣàfihàn àwọn ìṣàfihàn àti àwọn ìṣàfihàn àwọn ìṣàfihàn àwọn ìṣàfihàn.

mxbai-embed-large-v1

Lò nípa API

Àwọn Àtòjọ-ẹ̀yàn

Àwọn àṣẹ mxbai-embed-large-v1 wo ní?

Ìwọ̀n wo ní àwọn àgbékalẹ̀ mxbai-embed-large-v1 ní?

Àwọn àwọn ìṣàmúlò-ètò mxbai-embed-large-v1

Àwọn àwọn ààtò àwọn ààtò àwọn ààtò àwọn ààtò àwọn ààtò àwọn ààtò àwọn ààtò àwọn ààtò àwọn ààtò àwọn ààtò àwọn ààtò

Ìgbà wo ní mxbai-embed-large-v1 náà ló?

Can I batch embed with mxbai-embed-large-v1?

Àwọn àwọn àgbékalẹ̀ àwọn bètórí

Àwọn DB vector wo ní n ṣiṣẹ́ láti mxbai-embed-large-v1?

Àwọn ààyè-iṣẹ́ fún mxbai-embed-large-v1

Kini nipa ìdàjọ́ àwọn àkọlé tí mo bá fi àwọn àkọlé àìdálẹ̀ pamọ́ láti mxbai-embed-large-v1?

Ìgbà wo ní mxbai-embed-large-v1 gba nígbà kan?

Ń lè ló àwọn ààtòjọ-ẹ̀yàn mxbai-embed-large-v1 nípa ìtàn àwọn iṣẹ́?

Gba 10,000 Free Tokens

Wá - Gba 10K Free Tokens!

Tí o fẹ́ láti mú diẹ̀ sii?