Spaces:
Paused
Paused
File size: 1,772 Bytes
7fb6157 314e663 7fb6157 f78379c 314e663 7fb6157 cd61c85 f78379c 7fb6157 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 |
import json
import numpy as np
import httpx
import os
from constants import MUBERT_TAGS, MUBERT_MODE, MUBERT_LICENSE, MUBERT_TOKEN
def get_mubert_tags_embeddings(w2v_model):
return w2v_model.encode(MUBERT_TAGS)
def get_pat(email: str):
r = httpx.post('https://api-b2b.mubert.com/v2/GetServiceAccess',
json={
"method": "GetServiceAccess",
"params": {
"email":"mail@mail.com",
"phone":"+11234567890",
"license": MUBERT_LICENSE,
"token": MUBERT_TOKEN,
"mode": MUBERT_MODE,
}
})
rdata = json.loads(r.text)
print(rdata)
#assert rdata['status'] == 1, "probably incorrect e-mail"
pat = rdata['data']['pat']
return pat
def find_similar(em, embeddings, method='cosine'):
scores = []
for ref in embeddings:
if method == 'cosine':
scores.append(1 - np.dot(ref, em) / (np.linalg.norm(ref) * np.linalg.norm(em)))
if method == 'norm':
scores.append(np.linalg.norm(ref - em))
return np.array(scores), np.argsort(scores)
def get_tags_for_prompts(w2v_model, mubert_tags_embeddings, prompts, top_n=3, debug=False):
prompts_embeddings = w2v_model.encode(prompts)
ret = []
for i, pe in enumerate(prompts_embeddings):
scores, idxs = find_similar(pe, mubert_tags_embeddings)
top_tags = MUBERT_TAGS[idxs[:top_n]]
top_prob = 1 - scores[idxs[:top_n]]
if debug:
print(f"Prompt: {prompts[i]}\nTags: {', '.join(top_tags)}\nScores: {top_prob}\n\n\n")
ret.append((prompts[i], list(top_tags)))
return ret |