Skip to main content

​
Overview

HuggingFace provides access to thousands of open-source embedding models through their Inference API.

​
Quick Start

from praisonaiagents import embedding

result = embedding(
    input="Hello world",
    model="huggingface/BAAI/bge-large-en-v1.5"
)
print(f"Dimensions: {len(result.embeddings[0])}")

​
CLI Usage

praisonai embed "Hello world" --model huggingface/BAAI/bge-large-en-v1.5

​
Setup

export HUGGINGFACE_API_KEY="hf_..."
ModelDimensionsUse Case
huggingface/BAAI/bge-large-en-v1.51024High quality English
huggingface/BAAI/bge-base-en-v1.5768Balanced
huggingface/BAAI/bge-small-en-v1.5384Fast
huggingface/sentence-transformers/all-MiniLM-L6-v2384Fast, general
huggingface/sentence-transformers/all-mpnet-base-v2768High quality
huggingface/intfloat/e5-large-v21024E5 model

​
Batch Embeddings

from praisonaiagents import embedding

texts = ["Document 1", "Document 2", "Document 3"]
result = embedding(
    input=texts,
    model="huggingface/BAAI/bge-large-en-v1.5"
)
print(f"Generated {len(result.embeddings)} embeddings")