|
OpenAI
|
Text embedding models (text-embedding-ada-002, text-embedding-3-small, text-embedding-3-large) |
|
Sentence Transformers
|
BERT-based sentence embedding models with mean pooling |
|
VoyageAI
|
Transformer-based text embedding models (voyage-large-2, voyage-code-2) |
|
IBM
|
BERT-based text embedding models via Watson AI services |
|
Instructor
|
Instruction-tuned BERT models for task-specific embeddings |
|
Jina
|
Multilingual BERT models optimized for semantic similarity |
|
Ollama
|
Local inference of embedding models (nomic-embed-text, all-minilm) |
|
AWS
|
Titan text embedding models via Amazon Bedrock API |
|
Cohere
|
Multilingual text embedding models (embed-english-v3.0, embed-multilingual-v3.0) |
|
Gemini
|
Multimodal embedding models for text and image inputs |
|
Hugging Face
|
Access to transformer-based embedding models from Hugging Face Hub |
|
OpenCLIP
|
CLIP-based multimodal models for text-image embeddings |
|
ImageBind
|
Unified embedding model for text, image, audio, video, depth, and thermal data |