mxbai-embed-large-v1
Free.ai (self-hosted)
·
embeddings
·
~100 Ama-token ngalinye call
mxbai-embed-large-v1 yi an embedding model eyenziwe ngu mixedbread.ai. Onamandla kakhulu ku-Semantic search, clustering, similarity.. I-self-hosted ku-Free.ai GPUs - isebenza ngokukhululekile ngaphezu kwe-token pool yakho yansuku zonke (100 tokens nganoma yisiphi isikhalazo). Kukhishwa ngaphansi kwe-Apache 2.0 - ukusetshenziswa kokuthengiswayo kuvunyelwe ku-Free.ai.
Imibuzo ebuzwa kaningi
mxbai-embed-large-v1 iguqula umbhalo ube yi-vector eqinile (uhlu lwezibalo ezihambayo) ethatha uphawu. Sebenzisa ukusesha okunezincazelo, ukuqoqa, ukucebisa, ukukhishwa-ukuthuthukiswa kokukhiqizwa (RAG), nanoma iyiphi imisebenzi lapho "ikhona le mbhalo ofana nalo mbhalo" ibalulekile.
Izilinganiso ezijwayelekile yi-384, 768, 1024, noma 1536 ngokuya ngemodeli. BGE-M3 ikhipha 1024-dim; OpenAI Ada ikhipha 1536. Umbuzo we-API ufaka ubukhulu ukuze i-vector DB yakho ikhethe isibalo esifanele.
Amamodeli amanje okungenisa (kufaka phakathi izinketho eziningi ze-Free.ai) aqeqeshwa ku-100+ izilimi. Ukuthola ulwimi oluphakathi kusebenza - khangela ngesiNgisi, hlanganisa amadokhumende ngesiSpanishi.
512 kuya ku 8,192 amathokheni ngokuya ngemodeli. Izingeniso ezide zicutshungulwa - qoqa amadokhumende ade zibe ngamapharamitha ngaphambi kokufaka.
mxbai-embed-large-v1 ihamba ku-GPU yethu futhi iyingxenye yezinto ezibiza kakhulu - mayelana nama-token angama-100 nganoma yisiphi isikhalazo esithathwe epulazini lakho elimahhala. $5 = ama-token angama-200K.
Yebo - ITHOLA uhlu lwama-strings ku /v1/embeddings/ futhi mxbai-embed-large-v1 ibuyisela uhlu lwama-vectors ngokulandelana okufanayo. Ubukhulu be-batch kuya ku-2,048 ngesicelo ngasinye.
L2-ijwayelekile ngokuzenzakalela — i-cosine efana = i-dot product. Phatha `ijwayelekile = ayiqiniso` uma ufuna ama-vectors amnyama nge-metric yokuhamba okuhlukile.
Noma yini - Pinecone, Weaviate, Qdrant, Chroma, pgvector, FAISS, LanceDB. mxbai-embed-large-v1 ibuyisela i-JSON elula ehambayo; i-DB ayibonanga imodeli.
Yebo - POST ku /v1/embeddings/ ngemodeli "mxbai-embed-large-v1". OpenAI-ihambisana nesimo sokubuyiselwa, ngakho ama-library akhona asebenza ngokungaguquki. /api/ unesixhumanisi esigcwele.
Amamodeli ahlala ahlala agcina umbhalo wakho ku-GPUs ethu futhi asuse ngemuva kokubuyela kocingo. I-Premium idlula nge-DPA. Asiqeqeshi ngemingeniso yakho.
Sub-100ms for short text on self-hosted, 100–500ms on premium. Izingcingo ze-batch zilinganiselwa ngokuqondile — 1,000 chunks ziqediwe emaminithini angama-2–10.
Yebo - Free.ai inikeza ukusetshenziswa komphakathi kwezinhlanganisela. Yakha ucwaningo lokukhishwa, amapayipi we-RAG, ama-systems wokucebisa ngaphandle kwe-per-vector royalty.