text2vec - pypi Package Compare versions

Comparing version 1.3.3 to 1.3.4

PKG-INFO

@@ -1,4 +0,4 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: text2vec
-Version: 1.3.3
+Version: 1.3.4
 Summary: Text to vector Tool, encode text
@@ -28,2 +28,14 @@ Home-page: https://github.com/shibing624/text2vec
 Requires-Dist: pandas
+Requires-Dist: gensim
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
 
@@ -30,0 +42,0 @@ [**🇨🇳中文**](https://github.com/shibing624/text2vec/blob/master/README.md) | [**🌐English**](https://github.com/shibing624/text2vec/blob/master/README_EN.md) | [**📖文档/Docs**](https://github.com/shibing624/text2vec/wiki) | [**🤖模型/Models**](https://huggingface.co/shibing624)

setup.py

@@ -48,2 +48,3 @@ # -*- coding: utf-8 -*-
         "pandas",
+        "gensim",
     ],
@@ -50,0 +51,0 @@ packages=find_packages(exclude=['tests']),

text2vec.egg-info/PKG-INFO

@@ -1,4 +0,4 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: text2vec
-Version: 1.3.3
+Version: 1.3.4
 Summary: Text to vector Tool, encode text
@@ -28,2 +28,14 @@ Home-page: https://github.com/shibing624/text2vec
 Requires-Dist: pandas
+Requires-Dist: gensim
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
 
@@ -30,0 +42,0 @@ [**🇨🇳中文**](https://github.com/shibing624/text2vec/blob/master/README.md) | [**🌐English**](https://github.com/shibing624/text2vec/blob/master/README_EN.md) | [**📖文档/Docs**](https://github.com/shibing624/text2vec/wiki) | [**🤖模型/Models**](https://huggingface.co/shibing624)

text2vec.egg-info/requires.txt

@@ -8,1 +8,2 @@ jieba
 pandas
+gensim

text2vec/bertmatching_model.py

@@ -14,6 +14,7 @@ # -*- coding: utf-8 -*-
 from torch import nn
+from torch.optim import AdamW
 from torch.utils.data import DataLoader, Dataset, DistributedSampler
 from tqdm import tqdm, trange
 from transformers import BertForSequenceClassification, BertTokenizer
-from transformers.optimization import AdamW, get_linear_schedule_with_warmup
+from transformers.optimization import get_linear_schedule_with_warmup
 
@@ -29,3 +30,3 @@ from text2vec.bertmatching_dataset import (
 
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+device = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
 
@@ -32,0 +33,0 @@

text2vec/bge_model.py

@@ -16,5 +16,6 @@ # -*- coding: utf-8 -*-
 from torch import nn
+from torch.optim import AdamW
 from torch.utils.data import DataLoader, Dataset, DistributedSampler
 from tqdm import tqdm, trange
-from transformers.optimization import AdamW, get_linear_schedule_with_warmup
+from transformers.optimization import get_linear_schedule_with_warmup
 
@@ -21,0 +22,0 @@ from text2vec.bge_dataset import BgeTrainDataset

text2vec/cosent_model.py

@@ -14,5 +14,6 @@ # -*- coding: utf-8 -*-
 from torch import nn
+from torch.optim import AdamW
 from torch.utils.data import DataLoader, Dataset, DistributedSampler
 from tqdm import tqdm, trange
-from transformers.optimization import AdamW, get_linear_schedule_with_warmup
+from transformers.optimization import get_linear_schedule_with_warmup
 
@@ -19,0 +20,0 @@ from text2vec.cosent_dataset import CosentTrainDataset, load_cosent_train_data, HFCosentTrainDataset

text2vec/sentencebert_model.py

@@ -14,5 +14,6 @@ # -*- coding: utf-8 -*-
 from torch import nn
+from torch.optim import AdamW
 from torch.utils.data import DataLoader, Dataset, DistributedSampler
 from tqdm import tqdm, trange
-from transformers.optimization import AdamW, get_linear_schedule_with_warmup
+from transformers.optimization import get_linear_schedule_with_warmup
 
@@ -19,0 +20,0 @@ from text2vec.sentence_model import SentenceModel

text2vec/similarity.py

@@ -20,3 +20,3 @@ # -*- coding: utf-8 -*-
 
-device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+device = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
 
@@ -177,4 +177,4 @@
 
-    :param query_embeddings: A 2 dimensional tensor with the query embeddings.
-    :param corpus_embeddings: A 2 dimensional tensor with the corpus embeddings.
+    :param query_embeddings: Two dim tensor with the query embeddings.
+    :param corpus_embeddings: Two dim tensor with the corpus embeddings.
     :param query_chunk_size: Process 100 queries simultaneously. Increasing that value increases the speed, but requires more memory.
@@ -200,3 +200,2 @@ :param corpus_chunk_size: Scans the corpus 100k entries at a time. Increasing that value increases the speed, but requires more memory.
 
-    # Check that corpus and queries are on the same device
     query_embeddings = query_embeddings.to(device)
@@ -203,0 +202,0 @@ corpus_embeddings = corpus_embeddings.to(device)

text2vec/version.py

@@ -7,2 +7,2 @@ # -*- coding: utf-8 -*-
 
-__version__ = '1.3.3'
+__version__ = '1.3.4'

Alert delta unavailable

Currently unable to show alert delta for PyPI packages.

Improved metrics

Total package byte prevSize

336356

0.18%

Lines of code

3509

0.11%