Pipelines supported models
This section provides details of the supported models in EDB Postgres AI - AI Accelerator Pipelines and their capabilities.
- T5.
- Embeddings, including
openai-embeddingsandnim-embeddings. - Completions, including
openai-completionsandnim-completions. - BERT.
- CLIP.
- NIM_CLIP.
- NIM_RERANKING.
T5
T5 is a text-to-text transformer model that converts input text to output text.
BERT
BERT is a transformer-based model used for natural language processing tasks such as text classification, text generation, and text completion.
CLIP
CLIP (Contrastive Language-Image Pre-training) is a model that learns visual concepts from natural language supervision.
Completions
Completions is a text completion model that enables use of any OpenAI API-compatible text-generation model.
Embeddings
Embeddings is a text-embedding model that enables use of any OpenAI API-compatible text-embedding model.
NIM_CLIP
NIM_CLIP (Contrastive Language-Image Pre-training) is a model that learns visual concepts from natural language supervision on NVIDIA NIM.
Reranking
Reranking is a method in text search that sorts results by relevance to make them more accurate.
Could this page be better? Report a problem or suggest an addition!