Models
Overview
ML model options for each method
When using the mixpeek methods, you provide the model
in each request regardless of method: extract
, embed
, and generate
.
For instance mixpeek.extract()
, mixpeek.embed()
or mixpeek.generate()
The list below are all the embedding models currently supported in the SDK. For embed, use the dimensions to create your DB index.
We add models regularly, so if we’re missing any reach out.
Models
Embedding
Name | Modality | Dimensions | URL |
---|---|---|---|
sentence-transformers/all-MiniLM-L6-v2 | Text | 384 | Sentence Transformers |
nomic-ai/nomic-embed-text-v1 | Text | 768 | Nomic AI |
jinaai/jina-embeddings-v2-base-en | Text | 768 | Jina AI |
google-bert/bert-base-multilingual-uncased | Text | 768 | Google BERT |
mixedbread-ai/mxbai-embed-large-v1 | Text | 1024 | MixedBread AI |
openai/clip-vit-base-patch32 | Text, Image | 512 | OpenAI Clip |
mixpeek/vuse-generic-v1 | Text, Video | 768 | Mixpeek |
Generation
Name | Modality | URL |
---|---|---|
openai/gpt-3.5-turbo | Text | GPT-3.5 Turbo |
openai/gpt-4-turbo-preview | Text | GPT-4 Turbo Preview |
openai/gpt-4-turbo | Text | GPT-4 Turbo |
Extraction
Work in progress
Was this page helpful?