text-generation-webui/extensions/openai/moderations.py

70 lines
2.1 KiB
Python
Raw Normal View History

import time
2023-09-16 05:11:16 +02:00
import numpy as np
2023-09-16 05:11:16 +02:00
from numpy.linalg import norm
2023-11-17 03:03:06 +01:00
from extensions.openai.embeddings import get_embeddings
2023-07-12 20:33:25 +02:00
moderations_disabled = False # return 0/false
category_embeddings = None
antonym_embeddings = None
2023-07-12 20:33:25 +02:00
categories = ["sexual", "hate", "harassment", "self-harm", "sexual/minors", "hate/threatening", "violence/graphic", "self-harm/intent", "self-harm/instructions", "harassment/threatening", "violence"]
flag_threshold = 0.5
def get_category_embeddings() -> dict:
global category_embeddings, categories
if category_embeddings is None:
embeddings = get_embeddings(categories).tolist()
category_embeddings = dict(zip(categories, embeddings))
return category_embeddings
def cosine_similarity(a: np.ndarray, b: np.ndarray) -> float:
return np.dot(a, b) / (norm(a) * norm(b))
# seems most openai like with all-mpnet-base-v2
def mod_score(a: np.ndarray, b: np.ndarray) -> float:
return 2.0 * np.dot(a, b)
def moderations(input):
global category_embeddings, categories, flag_threshold, moderations_disabled
results = {
"id": f"modr-{int(time.time()*1e9)}",
"model": "text-moderation-001",
"results": [],
}
if moderations_disabled:
results['results'] = [{
2023-07-12 20:33:25 +02:00
'categories': dict([(C, False) for C in categories]),
'category_scores': dict([(C, 0.0) for C in categories]),
'flagged': False,
}]
return results
category_embeddings = get_category_embeddings()
# input, string or array
if isinstance(input, str):
input = [input]
for in_str in input:
for ine in get_embeddings([in_str]):
2023-07-12 20:33:25 +02:00
category_scores = dict([(C, mod_score(category_embeddings[C], ine)) for C in categories])
category_flags = dict([(C, bool(category_scores[C] > flag_threshold)) for C in categories])
flagged = any(category_flags.values())
results['results'].extend([{
'flagged': flagged,
'categories': category_flags,
'category_scores': category_scores,
}])
print(results)
2023-07-12 20:33:25 +02:00
return results