mxbai-embed-large-v1
Free.ai (self-hosted)
·
embeddings
·
~100 tokens per call
mxbai-embed-large-v1 is an embedding model built by mixedbread.ai. Strongest at Semantic search, clustering, similarity.. Self-inotarisirwa pa Free.ai GPUs - inofamba zvakasununguka pazuva rako re token pool (100 tokens per call). Yakaburitswa pasi pe Apache 2.0 — kushandiswa kwekutengesa kwakabvumirwa pa Free.ai.
Usati washandisa
OpenAI-inowirirana REST API. Kugadzira chiratidzo uye kukumbira iyi model mumasekondi.
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"}'Zvimwe zvinobvunzwa kakawanda
mxbai-embed-large-v1 inoshandura mazita emashoko kuita mazita akasimba (mazita ane zviratidzo zvinofamba) ayo anowana mashoko. Usaishandisa pakutsvaka mazita emashoko, kuunganidza mazita, kukurudzira, kutsvaka-kuwedzera kuumbwa (RAG), uye chero basa rine "izvi mazita akafanana neaya mazita" zvinhu.
Zvimwe zvinodiwa zvinonzi 384, 768, 1024, kana 1536 zvichienderana nechigadzirwa. BGE-M3 inoburitsa 1024-dim; OpenAI Ada inoburitsa 1536. API mhedzisiro inosanganisira chimiro kuti vector DB yako iite iyo yakakodzera index.
Mamodheru ezvino (kusanganisira akawanda mamodheru paFree.ai) anoshanda pa100+ mazita. Cross-language retrieval works — tsvaga muChirungu, tarisa mapepa muChirungu.
512 kusvika 8,192 tokens zvichienderana nemhando. Yakareba zvinyorwa zvinovharwa — chunk refu mapepa mumaparagiramu pamberi embedding.
mxbai-embed-large-v1 inofamba paGPU yedu uye inosanganisira yemahara michina — pamusoro pe100 tokens pafoni yakagadzirwa kubva pazuva nezuva yemahara pool. $5 = 200K tokens.
Yeah — 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-normalized by default — cosine similarity = dot product. Pass `normalize=false` kana iwe uchida raw vectors yeimwe distance metric.
Any — Pinecone, Weaviate, Qdrant, Chroma, pgvector, FAISS, LanceDB. mxbai-embed-large-v1 anodzokera plain JSON floats; DB kamwe haasi kuona chifananidzo.
Yeah — POST to /v1/embeddings/ with model="mxbai-embed-large-v1". OpenAI-inowirirana mashoko fomu, saka zviripo client mabhuku mabasa pasina kuchinja. /api/ ane yakazara reference.
Self-hosted mamodheru anochengeta yako tenzi paGPU yedu uye anobvisa mushure mekudzoka kwechikumbiro. Premium inoenda kuburikidza neDPA. Hatina kudzidzisa pane yako yekupinda.
Sub-100ms yenguva pfupi yekunyora pane self-hosted, 100-500ms papremiyumu. Batch kufona kukwira zvakaenzana - 1,000 mabhureki akazara mu 2-10 masekondi.
Yeah — Free.ai grants commercial use of embeddings. Build production search, RAG pipelines, recommendation systems without no per-vector royalty.