bertrend 0.3.2__tar.gz → 0.3.3__tar.gz

{bertrend-0.3.2 → bertrend-0.3.3}/PKG-INFO

@@ -1,72 +1,72 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: bertrend
-Version: 0.3.2
+Version: 0.3.3
 Summary: BERTrend analyses topic evolution over time using state-of-the-art transformer models: topic modelling and LLM
-Home-page: https://github.com/rte-france/BERTrend
 License: LICENSE.md
-Keywords: topics,BERTopic,transformers,weak signals
+Keywords: topics,BERTopic,transformers,weak signals,LLM
 Author: Jérôme Picault
 Author-email: jerome.picault@rte-france.com
+Maintainer: Jérôme Picault
+Maintainer-email: jerome.picault@rte-france.com
 Requires-Python: >=3.12,<4.0
-Classifier: License :: Other/Proprietary License
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Provides-Extra: apps
-Provides-Extra: tests
 Requires-Dist: Pyqtree (==1.0.0)
-Requires-Dist: arxiv (>=2.2.0,<3.0.0) ; extra == "apps"
+Requires-Dist: arxiv (>=2.2.0) ; extra == "apps"
 Requires-Dist: bertopic (==0.16.2)
-Requires-Dist: black (>=24.10.0,<25.0.0)
-Requires-Dist: coverage (>=7.6.9,<8.0.0) ; extra == "tests"
-Requires-Dist: cron-descriptor (>=1.4.5,<2.0.0)
+Requires-Dist: black (>=24.10.0)
+Requires-Dist: coverage (>=7.6.9)
+Requires-Dist: cron-descriptor (>=1.4.5)
 Requires-Dist: dask (==2024.12.0)
 Requires-Dist: datamapplot (==0.3.0)
-Requires-Dist: dateparser (>=1.2.0,<2.0.0)
-Requires-Dist: dill (>=0.4.0,<0.5.0)
-Requires-Dist: feedparser (>=6.0.11,<7.0.0) ; extra == "apps"
-Requires-Dist: gensim (==4.3.2)
-Requires-Dist: google-api-python-client (>=2.148.0,<3.0.0) ; extra == "apps"
-Requires-Dist: google-auth-oauthlib (>=1.2.1,<2.0.0) ; extra == "apps"
-Requires-Dist: googlenewsdecoder (>=0.1.7,<0.2.0) ; extra == "apps"
-Requires-Dist: goose3 (>=3.1.19,<4.0.0) ; extra == "apps"
-Requires-Dist: hdbscan (>=0.8.40,<0.9.0)
-Requires-Dist: ipython (>=8.28.0,<9.0.0)
-Requires-Dist: joblib (>=1.4.2,<2.0.0)
-Requires-Dist: jsonlines (>=4.0.0,<5.0.0)
-Requires-Dist: langchain-chroma (>=0.2.2,<0.3.0)
-Requires-Dist: langchain-community (>=0.3.21,<0.4.0)
-Requires-Dist: langchain-openai (>=0.3.12,<0.4.0)
-Requires-Dist: langdetect (>=1.0.9,<2.0.0)
-Requires-Dist: loguru (>=0.7.3,<0.8.0)
-Requires-Dist: lxml-html-clean (>=0.2.2,<0.3.0)
-Requires-Dist: markdown (>=3.7,<4.0)
-Requires-Dist: newscatcherapi (>=0.7.3,<0.8.0) ; extra == "apps"
-Requires-Dist: newspaper4k (>=0.9.3.1,<0.10.0.0) ; extra == "apps"
-Requires-Dist: nltk (>=3.9.1,<4.0.0)
+Requires-Dist: dateparser (>=1.2.0)
+Requires-Dist: dill (>=0.4.0)
+Requires-Dist: feedparser (>=6.0.11) ; extra == "apps"
+Requires-Dist: gensim (>=4.3.3)
+Requires-Dist: google-api-python-client (>=2.148.0) ; extra == "apps"
+Requires-Dist: google-auth-oauthlib (>=1.2.1) ; extra == "apps"
+Requires-Dist: googlenewsdecoder (>=0.1.7) ; extra == "apps"
+Requires-Dist: goose3 (>=3.1.19) ; extra == "apps"
+Requires-Dist: hdbscan (>=0.8.40)
+Requires-Dist: ipython (>=8.28.0)
+Requires-Dist: joblib (>=1.4.2)
+Requires-Dist: jsonlines (>=4.0.0)
+Requires-Dist: langchain-core (>=0.3.59)
+Requires-Dist: langdetect (>=1.0.9)
+Requires-Dist: loguru (>=0.7.3)
+Requires-Dist: lxml-html-clean (>=0.2.2)
+Requires-Dist: markdown (>=3.7)
+Requires-Dist: newscatcherapi (>=0.7.3) ; extra == "apps"
+Requires-Dist: newspaper4k (>=0.9.3.1) ; extra == "apps"
+Requires-Dist: nltk (>=3.9.1)
 Requires-Dist: numpy (<2)
-Requires-Dist: openai (>=1.77.0,<2.0.0)
+Requires-Dist: openai (>=1.77.0)
 Requires-Dist: opentelemetry-exporter-otlp-proto-grpc (==1.25.0)
-Requires-Dist: pandas (>=2.2.2,<3.0.0)
-Requires-Dist: plotly (>=5.24.1,<6.0.0)
-Requires-Dist: plotly-resampler (>=0.10.0,<0.11.0)
-Requires-Dist: pygooglenews (>=0.1.3,<0.2.0) ; extra == "apps"
+Requires-Dist: pandas (>=2.2.2)
+Requires-Dist: plotly (>=5.24.1)
+Requires-Dist: plotly-resampler (>=0.10.0)
+Requires-Dist: pygooglenews (>=0.1.3) ; extra == "apps"
 Requires-Dist: pylabeladjust (==0.1.13)
-Requires-Dist: pytest (>=8.3.3,<9.0.0) ; extra == "tests"
-Requires-Dist: requests (>=2.32.3,<3.0.0)
-Requires-Dist: scikit-learn (>=1.5.2,<2.0.0)
+Requires-Dist: pytest (>=8.3.3)
+Requires-Dist: requests (>=2.32.3)
+Requires-Dist: scikit-learn (>=1.5.2)
 Requires-Dist: scipy (==1.12)
-Requires-Dist: seaborn (>=0.13.2,<0.14.0)
+Requires-Dist: seaborn (>=0.13.2)
 Requires-Dist: sentence-transformers (==3.0.1)
-Requires-Dist: sentencepiece (>=0.2.0,<0.3.0)
-Requires-Dist: streamlit (>=1.45.0,<2.0.0)
-Requires-Dist: streamlit-code-editor (>=0.1.22,<0.2.0)
-Requires-Dist: thefuzz (>=0.22.1,<0.23.0)
-Requires-Dist: tiktoken (>=0.8.0,<0.9.0)
+Requires-Dist: sentencepiece (>=0.2.0)
+Requires-Dist: starlette (>=0.46.2)
+Requires-Dist: streamlit (>=1.45.0)
+Requires-Dist: streamlit-code-editor (>=0.1.22)
+Requires-Dist: thefuzz (>=0.22.1)
+Requires-Dist: tiktoken (>=0.8.0)
 Requires-Dist: tldextract (>=2.0.1)
 Requires-Dist: tokenizers (<0.20.0)
-Requires-Dist: torch (==2.7.0)
-Requires-Dist: tqdm (>=4.67.1,<5.0.0)
-Requires-Dist: umap-learn (>=0.5.7,<0.6.0)
+Requires-Dist: torch (>=2.7.0)
+Requires-Dist: tqdm (>=4.67.1)
+Requires-Dist: umap-learn (>=0.5.7)
+Project-URL: Bug Tracker, https://github.com/rte-france/BERTrend/issues
+Project-URL: Documentation, https://github.com/rte-france/BERTrend
+Project-URL: Homepage, https://github.com/rte-france/BERTrend
 Project-URL: Repository, https://github.com/rte-france/BERTrend
 Description-Content-Type: text/markdown
 
@@ -137,7 +137,7 @@ https://github.com/user-attachments/assets/d79368d9-d4e0-4324-8a98-a888f0ab3b65
 - Categorization of signals into three different dataframes: noise, weak and strong signals
   (each dataframe contains useful information about the signals)
 - Interpretation of these signals using LLMs
-- Inspection of topic merging process using Sankey diagram
+- Inspection of the topic merging process using Sankey diagram
 
 ## Installation
 
@@ -174,19 +174,14 @@ BERTrend requires the following environment variables to be set:
   # Basic installation with core dependencies
   pip install .  # or poetry install
 
-  # Installation with test dependencies
-  pip install ".[tests]"  # or poetry install --with test
+    # Installation with apps dependencies
+  pip install ".[apps]"  # or poetry install --extras apps
 
-  # Installation with apps dependencies
-  pip install ".[apps]"  # or poetry install --with apps
-
-  # Installation with all optional dependencies
-  pip install ".[tests,apps]"  # or poetry install --with test,apps
   ```
 
 - (Use `pip install -e .` for a local installation)
 
-NB. Due to the number of dependencies, the installation may take some time on an empty environement.
+NB. Due to the number of dependencies, the installation may take some time on an empty environment.
 
 ### Dependency Management
 
@@ -232,7 +227,7 @@ For custom dataset creation, please refer to the documentation page about [data
 
 In order to use the provided demos, datasets :
 - can be stored on the server in: `$BERTREND_BASE_DIR/data/bertrend/`
-- or can be uploaded from the client device on which is displayed the Streamlit apps.
+- or can be uploaded from the client device on which are displayed the Streamlit apps.
 
 #### Dataset Format
 Required columns:
@@ -259,6 +254,13 @@ CUDA_VISIBLE_DEVICES=<gpu_number> streamlit run app.py
 - `Parameters`: Include all BERTopic parameters. Choose the embedding model carefully based on your data language.
 The embedding model can run locally (a GPU is recommended); it is also possible to use a remote embedding service.
 
+We recommend using a remote embedding service (this is now the default config) as it simplifies the computing.
+
+The change of configuration can be done in: [services_default_config.toml](bertrend/config/services_default_config.toml).
+
+An example of a very simple implementation to deploy a separate embedding service can be found here: https://github.com/rte-france/wattelse/tree/main/wattelse/api/embedding. (this implementation is compatible with our code)
+
+
 ![parameters](docs/images/parameters.png)
 
 Please refer to the [BERTopic documentation](https://maartengr.github.io/BERTopic/algorithm/algorithm.html) for parameter details.
@@ -277,7 +279,7 @@ The application is split into several pages:
   - Computes topics over time
   ![exploration_over_time](./docs/images/explore1.png)
 
-  - Allow to select sources and generate short descriptions for each theme
+  - Allow selecting sources and generating short descriptions for each theme
   ![topic_exploration](./docs/images/explore2.png)
 
 - `Topic visualization`: Several visualization types available:
@@ -295,7 +297,7 @@ The application is split into several pages:
   ![temptopic_metrics](./docs/images/temptopic_metrics.png)  
 
 - `Generate Newsletters`
-  - This is an example of application combining topic analysis and LLMs
+  - This is an example of an application combining topic analysis and LLMs
   - Generates newsletters based on prominent topics
   - Uses LLMs to generate topic descriptions and summarize representative documents
 
@@ -344,8 +346,8 @@ Provides various statistics about topics:
 - As topics are hard to interprete by humans, we showcase how it can be
 done using LLMs.
 - Choose a specific topic and click on the button to generate an interpretation
-- LLM-based in-depth signal analysis is done using predefined templates for example:
-  - describe what happens since last timestamp (summary of main events)
+- LLM-based in-depth signal analysis is done using predefined templates, for example:
+  - describe what's happened since the last timestamp (summary of main events)
   - present through a multi-faceted description info about key developments, foreseen changes, potential impact, etc.
 
 
@@ -373,7 +375,7 @@ See [AUTHORS](./AUTHORS.txt) for the full list of contributors.
 
 ## License Information
 
-Copyright 2023-2025 RTE France RTE: http://www.rte-france.com
+Copyright 2023–2025 RTE France RTE: http://www.rte-france.com
 
 This Source Code is subject to the terms of the Mozilla Public License (MPL) v2 also available here: https://www.mozilla.org/en-US/MPL/2.0/
 

{bertrend-0.3.2 → bertrend-0.3.3}/README.md

@@ -65,7 +65,7 @@ https://github.com/user-attachments/assets/d79368d9-d4e0-4324-8a98-a888f0ab3b65
 - Categorization of signals into three different dataframes: noise, weak and strong signals
   (each dataframe contains useful information about the signals)
 - Interpretation of these signals using LLMs
-- Inspection of topic merging process using Sankey diagram
+- Inspection of the topic merging process using Sankey diagram
 
 ## Installation
 
@@ -102,19 +102,14 @@ BERTrend requires the following environment variables to be set:
   # Basic installation with core dependencies
   pip install .  # or poetry install
 
-  # Installation with test dependencies
-  pip install ".[tests]"  # or poetry install --with test
+    # Installation with apps dependencies
+  pip install ".[apps]"  # or poetry install --extras apps
 
-  # Installation with apps dependencies
-  pip install ".[apps]"  # or poetry install --with apps
-
-  # Installation with all optional dependencies
-  pip install ".[tests,apps]"  # or poetry install --with test,apps
   ```
 
 - (Use `pip install -e .` for a local installation)
 
-NB. Due to the number of dependencies, the installation may take some time on an empty environement.
+NB. Due to the number of dependencies, the installation may take some time on an empty environment.
 
 ### Dependency Management
 
@@ -160,7 +155,7 @@ For custom dataset creation, please refer to the documentation page about [data
 
 In order to use the provided demos, datasets :
 - can be stored on the server in: `$BERTREND_BASE_DIR/data/bertrend/`
-- or can be uploaded from the client device on which is displayed the Streamlit apps.
+- or can be uploaded from the client device on which are displayed the Streamlit apps.
 
 #### Dataset Format
 Required columns:
@@ -187,6 +182,13 @@ CUDA_VISIBLE_DEVICES=<gpu_number> streamlit run app.py
 - `Parameters`: Include all BERTopic parameters. Choose the embedding model carefully based on your data language.
 The embedding model can run locally (a GPU is recommended); it is also possible to use a remote embedding service.
 
+We recommend using a remote embedding service (this is now the default config) as it simplifies the computing.
+
+The change of configuration can be done in: [services_default_config.toml](bertrend/config/services_default_config.toml).
+
+An example of a very simple implementation to deploy a separate embedding service can be found here: https://github.com/rte-france/wattelse/tree/main/wattelse/api/embedding. (this implementation is compatible with our code)
+
+
 ![parameters](docs/images/parameters.png)
 
 Please refer to the [BERTopic documentation](https://maartengr.github.io/BERTopic/algorithm/algorithm.html) for parameter details.
@@ -205,7 +207,7 @@ The application is split into several pages:
   - Computes topics over time
   ![exploration_over_time](./docs/images/explore1.png)
 
-  - Allow to select sources and generate short descriptions for each theme
+  - Allow selecting sources and generating short descriptions for each theme
   ![topic_exploration](./docs/images/explore2.png)
 
 - `Topic visualization`: Several visualization types available:
@@ -223,7 +225,7 @@ The application is split into several pages:
   ![temptopic_metrics](./docs/images/temptopic_metrics.png)  
 
 - `Generate Newsletters`
-  - This is an example of application combining topic analysis and LLMs
+  - This is an example of an application combining topic analysis and LLMs
   - Generates newsletters based on prominent topics
   - Uses LLMs to generate topic descriptions and summarize representative documents
 
@@ -272,8 +274,8 @@ Provides various statistics about topics:
 - As topics are hard to interprete by humans, we showcase how it can be
 done using LLMs.
 - Choose a specific topic and click on the button to generate an interpretation
-- LLM-based in-depth signal analysis is done using predefined templates for example:
-  - describe what happens since last timestamp (summary of main events)
+- LLM-based in-depth signal analysis is done using predefined templates, for example:
+  - describe what's happened since the last timestamp (summary of main events)
   - present through a multi-faceted description info about key developments, foreseen changes, potential impact, etc.
 
 
@@ -301,7 +303,7 @@ See [AUTHORS](./AUTHORS.txt) for the full list of contributors.
 
 ## License Information
 
-Copyright 2023-2025 RTE France RTE: http://www.rte-france.com
+Copyright 2023–2025 RTE France RTE: http://www.rte-france.com
 
 This Source Code is subject to the terms of the Mozilla Public License (MPL) v2 also available here: https://www.mozilla.org/en-US/MPL/2.0/
 

{bertrend-0.3.2 → bertrend-0.3.3}/bertrend/services/authentication.py

@@ -2,7 +2,6 @@
 #  See AUTHORS.txt
 #  SPDX-License-Identifier: MPL-2.0
 #  This file is part of BERTrend.
-import os
 import time
 
 import requests

{bertrend-0.3.2 → bertrend-0.3.3}/bertrend/services/summary/chatgpt_summarizer.py

@@ -35,7 +35,7 @@ class GPTSummarizer(Summarizer):
         prompt_language: str = "fr",
         max_article_length: int = 1500,
         model_name: str = None,
-        **kwargs
+        **kwargs,
     ) -> str:
         # Limit input length in case the text is large
         article_text = keep_first_n_words(article_text, max_article_length)

{bertrend-0.3.2 → bertrend-0.3.3}/bertrend/tests/test_abstractive_summarizer.py

@@ -36,12 +36,15 @@ def mock_model():
 @pytest.fixture
 def mock_abstractive_summarizer(mock_tokenizer, mock_model):
     """Create a mock AbstractiveSummarizer with mocked dependencies."""
-    with patch(
-        "bertrend.services.summary.abstractive_summarizer.AutoTokenizer.from_pretrained",
-        return_value=mock_tokenizer,
-    ), patch(
-        "bertrend.services.summary.abstractive_summarizer.AutoModelForSeq2SeqLM.from_pretrained",
-        return_value=mock_model,
+    with (
+        patch(
+            "bertrend.services.summary.abstractive_summarizer.AutoTokenizer.from_pretrained",
+            return_value=mock_tokenizer,
+        ),
+        patch(
+            "bertrend.services.summary.abstractive_summarizer.AutoModelForSeq2SeqLM.from_pretrained",
+            return_value=mock_model,
+        ),
     ):
         summarizer = AbstractiveSummarizer()
         # Set the mocks directly to ensure they're used
@@ -52,11 +55,14 @@ def mock_abstractive_summarizer(mock_tokenizer, mock_model):
 
 def test_initialization():
     """Test that the AbstractiveSummarizer initializes with the correct model."""
-    with patch(
-        "bertrend.services.summary.abstractive_summarizer.AutoTokenizer.from_pretrained"
-    ) as mock_tokenizer, patch(
-        "bertrend.services.summary.abstractive_summarizer.AutoModelForSeq2SeqLM.from_pretrained"
-    ) as mock_model:
+    with (
+        patch(
+            "bertrend.services.summary.abstractive_summarizer.AutoTokenizer.from_pretrained"
+        ) as mock_tokenizer,
+        patch(
+            "bertrend.services.summary.abstractive_summarizer.AutoModelForSeq2SeqLM.from_pretrained"
+        ) as mock_model,
+    ):
 
         # Mock the to() method to avoid device-related issues
         mock_model.return_value.to.return_value = mock_model.return_value
@@ -124,11 +130,14 @@ def test_custom_model():
     """Test initialization with a custom model."""
     custom_model = "custom/model"
 
-    with patch(
-        "bertrend.services.summary.abstractive_summarizer.AutoTokenizer.from_pretrained"
-    ) as mock_tokenizer, patch(
-        "bertrend.services.summary.abstractive_summarizer.AutoModelForSeq2SeqLM.from_pretrained"
-    ) as mock_model:
+    with (
+        patch(
+            "bertrend.services.summary.abstractive_summarizer.AutoTokenizer.from_pretrained"
+        ) as mock_tokenizer,
+        patch(
+            "bertrend.services.summary.abstractive_summarizer.AutoModelForSeq2SeqLM.from_pretrained"
+        ) as mock_model,
+    ):
 
         # Mock the to() method to avoid device-related issues
         mock_model.return_value.to.return_value = mock_model.return_value

{bertrend-0.3.2 → bertrend-0.3.3}/bertrend/tests/test_extractive_summarizer.py

@@ -55,12 +55,15 @@ def mock_openai_client():
 @pytest.fixture
 def mock_enhanced_summarizer(mock_sentence_transformer, mock_openai_client):
     """Create a mock EnhancedExtractiveSummarizer with mocked dependencies."""
-    with patch(
-        "bertrend.services.summary.extractive_summarizer.SentenceTransformer",
-        return_value=mock_sentence_transformer,
-    ), patch(
-        "bertrend.services.summary.extractive_summarizer.OpenAI_Client",
-        return_value=mock_openai_client,
+    with (
+        patch(
+            "bertrend.services.summary.extractive_summarizer.SentenceTransformer",
+            return_value=mock_sentence_transformer,
+        ),
+        patch(
+            "bertrend.services.summary.extractive_summarizer.OpenAI_Client",
+            return_value=mock_openai_client,
+        ),
     ):
         summarizer = EnhancedExtractiveSummarizer(
             api_key="test_key", endpoint="test_endpoint"
@@ -82,11 +85,14 @@ def test_extractive_summarizer_initialization():
 
 def test_enhanced_summarizer_initialization():
     """Test that the EnhancedExtractiveSummarizer initializes correctly."""
-    with patch(
-        "bertrend.services.summary.extractive_summarizer.SentenceTransformer"
-    ) as mock_transformer, patch(
-        "bertrend.services.summary.extractive_summarizer.OpenAI_Client"
-    ) as mock_client:
+    with (
+        patch(
+            "bertrend.services.summary.extractive_summarizer.SentenceTransformer"
+        ) as mock_transformer,
+        patch(
+            "bertrend.services.summary.extractive_summarizer.OpenAI_Client"
+        ) as mock_client,
+    ):
         summarizer = EnhancedExtractiveSummarizer(
             api_key="test_key", endpoint="test_endpoint"
         )
@@ -128,13 +134,17 @@ def test_get_sentences_embeddings(
 def test_summarize_text(mock_extractive_summarizer):
     """Test the summarize_text method."""
     # Mock the necessary methods
-    with patch.object(
-        mock_extractive_summarizer,
-        "get_sentences",
-        return_value=["Sentence 1.", "Sentence 2.", "Sentence 3."],
-    ), patch.object(mock_extractive_summarizer, "get_sentences_embeddings"), patch(
-        "bertrend.services.summary.extractive_summarizer.summarize_embeddings",
-        return_value=[0, 2],
+    with (
+        patch.object(
+            mock_extractive_summarizer,
+            "get_sentences",
+            return_value=["Sentence 1.", "Sentence 2.", "Sentence 3."],
+        ),
+        patch.object(mock_extractive_summarizer, "get_sentences_embeddings"),
+        patch(
+            "bertrend.services.summary.extractive_summarizer.summarize_embeddings",
+            return_value=[0, 2],
+        ),
     ):
 
         summary = mock_extractive_summarizer.summarize_text("This is a test text.")
@@ -207,9 +217,12 @@ def test_summarize_embeddings():
 def test_summarize_chunks(mock_extractive_summarizer):
     """Test the summarize_chunks method."""
     # Mock the necessary methods
-    with patch.object(mock_extractive_summarizer, "get_chunks_embeddings"), patch(
-        "bertrend.services.summary.extractive_summarizer.summarize_embeddings",
-        return_value=np.array([0, 2]),
+    with (
+        patch.object(mock_extractive_summarizer, "get_chunks_embeddings"),
+        patch(
+            "bertrend.services.summary.extractive_summarizer.summarize_embeddings",
+            return_value=np.array([0, 2]),
+        ),
     ):
 
         chunks = ["Chunk 1", "Chunk 2", "Chunk 3", "Chunk 4", "Chunk 5"]

{bertrend-0.3.2 → bertrend-0.3.3}/bertrend/tests/test_installation.py

@@ -47,9 +47,7 @@ def test_nlp_dependencies():
 def test_llm_dependencies():
     """Test that LLM integration dependencies are installed correctly."""
     try:
-        import langchain_community
-        import langchain_chroma
-        import langchain_openai
+        import langchain_core
         import openai
         import tiktoken
 

{bertrend-0.3.2 → bertrend-0.3.3}/bertrend/tests/test_topic_metrics.py

@@ -166,13 +166,15 @@ def test_get_diversity_value_invalid_type(mock_bertopic, sample_data):
 
 def test_compute_cluster_metrics(mock_bertopic, sample_data):
     """Test the compute_cluster_metrics function."""
-    with patch(
-        "bertrend.metrics.topic_metrics.get_coherence_value", return_value=0.75
-    ) as mock_coherence, patch(
-        "bertrend.metrics.topic_metrics.get_diversity_value", return_value=0.6
-    ) as mock_diversity, patch(
-        "bertrend.metrics.topic_metrics.logger"
-    ) as mock_logger:
+    with (
+        patch(
+            "bertrend.metrics.topic_metrics.get_coherence_value", return_value=0.75
+        ) as mock_coherence,
+        patch(
+            "bertrend.metrics.topic_metrics.get_diversity_value", return_value=0.6
+        ) as mock_diversity,
+        patch("bertrend.metrics.topic_metrics.logger") as mock_logger,
+    ):
 
         compute_cluster_metrics(
             mock_bertopic, sample_data["topics"], sample_data["docs"]
@@ -197,14 +199,16 @@ def test_compute_cluster_metrics(mock_bertopic, sample_data):
 
 def test_compute_cluster_metrics_coherence_error(mock_bertopic, sample_data):
     """Test the compute_cluster_metrics function when coherence calculation raises an error."""
-    with patch(
-        "bertrend.metrics.topic_metrics.get_coherence_value",
-        side_effect=IndexError("Test error"),
-    ) as mock_coherence, patch(
-        "bertrend.metrics.topic_metrics.get_diversity_value", return_value=0.6
-    ) as mock_diversity, patch(
-        "bertrend.metrics.topic_metrics.logger"
-    ) as mock_logger:
+    with (
+        patch(
+            "bertrend.metrics.topic_metrics.get_coherence_value",
+            side_effect=IndexError("Test error"),
+        ) as mock_coherence,
+        patch(
+            "bertrend.metrics.topic_metrics.get_diversity_value", return_value=0.6
+        ) as mock_diversity,
+        patch("bertrend.metrics.topic_metrics.logger") as mock_logger,
+    ):
 
         compute_cluster_metrics(
             mock_bertopic, sample_data["topics"], sample_data["docs"]
@@ -216,14 +220,16 @@ def test_compute_cluster_metrics_coherence_error(mock_bertopic, sample_data):
 
 def test_compute_cluster_metrics_diversity_error(mock_bertopic, sample_data):
     """Test the compute_cluster_metrics function when diversity calculation raises an error."""
-    with patch(
-        "bertrend.metrics.topic_metrics.get_coherence_value", return_value=0.75
-    ) as mock_coherence, patch(
-        "bertrend.metrics.topic_metrics.get_diversity_value",
-        side_effect=IndexError("Test error"),
-    ) as mock_diversity, patch(
-        "bertrend.metrics.topic_metrics.logger"
-    ) as mock_logger:
+    with (
+        patch(
+            "bertrend.metrics.topic_metrics.get_coherence_value", return_value=0.75
+        ) as mock_coherence,
+        patch(
+            "bertrend.metrics.topic_metrics.get_diversity_value",
+            side_effect=IndexError("Test error"),
+        ) as mock_diversity,
+        patch("bertrend.metrics.topic_metrics.logger") as mock_logger,
+    ):
 
         compute_cluster_metrics(
             mock_bertopic, sample_data["topics"], sample_data["docs"]

bertrend-0.3.3/pyproject.toml

@@ -0,0 +1,96 @@
+[project]
+name = "bertrend"
+version = "0.3.3"
+description = "BERTrend analyses topic evolution over time using state-of-the-art transformer models: topic modelling and LLM"
+license = "LICENSE.md"
+readme = "README.md"
+requires-python = ">=3.12,<4.0"
+authors = [
+    { name = "Jérôme Picault", email = "jerome.picault@rte-france.com" },
+    { name="Guillaume Grosjean", email="guillaume.grosjean@rte-france.com>" },
+    { name="Allaa Boutaleb", email="allaa.boutaleb@lip6.fr>"}
+]
+maintainers = [
+    { name = "Jérôme Picault", email = "jerome.picault@rte-france.com" },
+    { name="Guillaume Grosjean", email="guillaume.grosjean@rte-france.com>" },
+]
+keywords = ["topics", "BERTopic", "transformers", "weak signals", "LLM"]
+classifiers = [ "Topic :: Scientific/Engineering :: Artificial Intelligence"]
+
+dependencies = [
+    "ipython (>=8.28.0)",
+    "bertopic (==0.16.2)", # not fully tested with more recent versions
+    "black (>=24.10.0)",
+    "coverage>=7.6.9",
+    "cron-descriptor (>=1.4.5)",
+    "datamapplot (==0.3.0)",
+    "dateparser (>=1.2.0)",
+    "dask (==2024.12.0)", # issues with >=2025.x (https://github.com/dask/dask/issues/11678)
+    "dill (>=0.4.0)",
+    "gensim (>=4.3.3)",
+    "hdbscan (>=0.8.40)",
+    "joblib (>=1.4.2)",
+    "jsonlines (>=4.0.0)",
+    "langdetect (>=1.0.9)",
+    "langchain-core (>=0.3.59)",
+    "loguru (>=0.7.3)",
+    "lxml-html-clean (>=0.2.2)",
+    "markdown (>=3.7)",
+    "nltk (>=3.9.1)",
+    "numpy (<2)",
+    "openai (>=1.77.0)",
+    "opentelemetry-exporter-otlp-proto-grpc (==1.25.0)",  # to avoid error chroma with protobuf
+    "pandas (>=2.2.2)",
+    "plotly (>=5.24.1)",
+    "plotly-resampler (>=0.10.0)",
+    "pylabeladjust (==0.1.13)",
+    "Pyqtree (==1.0.0)",
+    "pytest>=8.3.3",
+    "scipy (==1.12)",
+    "scikit-learn (>=1.5.2)",
+    "sentence-transformers (==3.0.1)",
+    "starlette (>=0.46.2)",
+    "requests (>=2.32.3)",
+    "seaborn (>=0.13.2)",
+    "sentencepiece (>=0.2.0)",
+    "streamlit (>=1.45.0)",
+    "streamlit-code-editor (>=0.1.22)",
+    "tldextract (>=2.0.1)",
+    "thefuzz (>=0.22.1)",
+    "torch (>=2.7.0)",
+    "tqdm (>=4.67.1)",
+    "tiktoken (>=0.8.0)",
+    "tokenizers (<0.20.0)",
+    "umap-learn (>=0.5.7)"
+]
+
+[project.optional-dependencies]
+apps = [
+    "arxiv>=2.2.0",
+    "feedparser>=6.0.11",
+    "googlenewsdecoder>=0.1.7",
+    "google-api-python-client>=2.148.0",
+    "google-auth-oauthlib>=1.2.1",
+    "goose3>=3.1.19",
+    "newscatcherapi>=0.7.3",
+    "newspaper4k>=0.9.3.1",
+    "pygooglenews>=0.1.3"
+]
+
+[project.urls]
+homepage = "https://github.com/rte-france/BERTrend"
+repository = "https://github.com/rte-france/BERTrend"
+documentation = "https://github.com/rte-france/BERTrend"
+"Bug Tracker" = "https://github.com/rte-france/BERTrend/issues"
+
+[tool.poetry]
+packages = [
+    { include = "bertrend" },
+    { include = "bertrend_apps" },
+]
+exclude = [ "data" ]
+requires-poetry = ">=2.0"
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"