PyCafe - Solara - Text Sentence Embeddings Visualizer

app.py
requirements.txt

app.py

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
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
import pandas as pd
import umap
print(dir(umap))
print(umap.__path__)
from umap import UMAP
from sklearn.pipeline import make_pipeline 

# seems impossible to install
# pip install "embetter[text]"
# from embetter.text import SentenceEncoder

# Build a sentence encoder pipeline with UMAP at the end.


# print(SentenceEncoder)
# enc = SentenceEncoder('all-MiniLM-L6-v2')
umap = UMAP()

text_emb_pipeline = make_pipeline(
   umap
)

# Load sentences
sentences = list(pd.read_csv("text.csv")['text'])

# Calculate embeddings 
X_tfm = text_emb_pipeline.fit_transform(sentences)

# Write to disk. Note! Text column must be named "text"
df = pd.DataFrame({"text": sentences})
df['x'] = X_tfm[:, 0]
df['y'] = X_tfm[:, 1]

from bulk.widgets import BaseTextExplorer

widget = BaseTextExplorer(df)
page = widget


## can we use the following for the SentenceEncoder
# import solara
# import numpy as np

# clicks = solara.reactive(0)
# input = solara.reactive("I love transformers")

# from transformers_js_py import import_transformers_js

# @solara.lab.task
# async def run(input):

#     transformers = await import_transformers_js()
#     pipeline = transformers.pipeline

#     # Allocate a pipeline for sentiment-analysis
#     pipe = await pipeline("feature-extraction")

#     out = await pipe(input)
#     # [{'label': 'POSITIVE', 'score': 0.999817686}]
#     return np.array(out.tolist()).shape

# @solara.component
# def Page():
#     if run.error:
#         solara.Error(repr(run.exception))
#     with solara.Card("Sentiment analysis"):
#         solara.ProgressLinear(run.pending)
#         with solara.Div():
#             solara.InputText(label="Input", value=input)
#             solara.Button(label=f"Analyze sentiment", on_click=lambda: run(input.value), color="primary", filled=True)
#         if run.finished:
#             solara.Text(repr(run.value))

numba/__init__.py

1
Could not load content

Py.Cafe

text-embeddings-visualizer

Text Sentence Embeddings Visualizer