Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

* feat(embedding.py): add support for v1.5 models #25

Merged
merged 1 commit into from
Oct 16, 2023
Merged

* feat(embedding.py): add support for v1.5 models #25

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 13 additions & 3 deletions fastembed/embedding.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,10 +6,10 @@
from pathlib import Path
from typing import Dict, Iterable, List, Union

import onnxruntime as ort
import numpy as np
import onnxruntime as ort
import requests
from tokenizers import Tokenizer, AddedToken
from tokenizers import AddedToken, Tokenizer
from tqdm import tqdm


Expand Down Expand Up @@ -54,13 +54,23 @@ def list_supported_models(cls) -> List[Dict[str, Union[str, int]]]:
{
"model": "BAAI/bge-small-en",
"dim": 384,
"description": "Fast English model",
},
{
"model": "BAAI/bge-small-en-v1.5",
"dim": 384,
"description": "Fast and Default English model",
},
{
"model": "BAAI/bge-base-en",
"dim": 768,
"description": "Base English model",
},
{
"model": "BAAI/bge-base-en-v1.5",
"dim": 768,
"description": "Base English model, v1.5",
},
{
"model": "sentence-transformers/all-MiniLM-L6-v2",
"dim": 384,
Expand Down Expand Up @@ -385,7 +395,7 @@ class DefaultEmbedding(FlagEmbedding):

def __init__(
self,
model_name: str = "BAAI/bge-small-en",
model_name: str = "BAAI/bge-small-en-v1.5",
max_length: int = 512,
cache_dir: str = None,
):
Expand Down
5 changes: 3 additions & 2 deletions tests/test_onnx_embeddings.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,10 +2,11 @@

from fastembed.embedding import DefaultEmbedding, Embedding


CANONICAL_VECTOR_VALUES = {
"BAAI/bge-small-en": np.array([-0.0232, -0.0255, 0.0174, -0.0639, -0.0006]),
"BAAI/bge-small-en-v1.5": np.array([0.01522374, -0.02271799, 0.00860278, -0.07424029, 0.00386434]),
"BAAI/bge-base-en": np.array([0.0115, 0.0372, 0.0295, 0.0121, 0.0346]),
"BAAI/bge-base-en-v1.5": np.array([0.01129394, 0.05493144, 0.02615099, 0.00328772, 0.02996045]),
"sentence-transformers/all-MiniLM-L6-v2": np.array([0.0259, 0.0058, 0.0114, 0.0380, -0.0233]),
"intfloat/multilingual-e5-large": np.array([0.0098, 0.0045, 0.0066, -0.0354, 0.0070]),
}
Expand All @@ -22,7 +23,7 @@ def test_default_embedding():
assert embeddings.shape == (2, dim)

canonical_vector = CANONICAL_VECTOR_VALUES[model_desc["model"]]
assert np.allclose(embeddings[0, :canonical_vector.shape[0]], canonical_vector, atol=1e-3)
assert np.allclose(embeddings[0, :canonical_vector.shape[0]], canonical_vector, atol=1e-3), model_desc["model"]


def test_batch_embedding():
Expand Down
Loading