bertrend 0.3.2__tar.gz → 0.3.4__tar.gz

{bertrend-0.3.2 → bertrend-0.3.4}/PKG-INFO

@@ -1,72 +1,73 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: bertrend
-Version: 0.3.2
+Version: 0.3.4
 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: openpyxl (>=3.1.5)
 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
 
@@ -78,7 +79,7 @@ Description-Content-Type: text/markdown
 [![issues - BERTrend](https://img.shields.io/github/issues/rte-france/BERTrend)](https://github.com/rte-france/BERTrend/issues)
 [![Downloads](https://pepy.tech/badge/bertrend)](https://pepy.tech/project/bertrend)
 [![PyPi_Version](https://img.shields.io/pypi/v/bertrend.svg)](https://pypi.org/project/bertrend/)
-[![PyPi_Compat](https://img.shields.io/pypi/pyversions/bertrend.svg)](https://pypi.org/project/bertrend/)
+![Static Badge](https://img.shields.io/badge/python-%3E%3D3.12-blue)
 ![GitHub License](https://img.shields.io/github/license/rte-france/BERTrend)
 
 ![BERTrend pipeline](./BERTrend_overview.png)
@@ -137,7 +138,7 @@ 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 +175,14 @@ 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 +228,7 @@ 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 +255,13 @@ 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 +280,7 @@ 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 +298,7 @@ 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 +347,8 @@ 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 +376,7 @@ 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-0.3.4}/README.md

@@ -6,7 +6,7 @@
 [![issues - BERTrend](https://img.shields.io/github/issues/rte-france/BERTrend)](https://github.com/rte-france/BERTrend/issues)
 [![Downloads](https://pepy.tech/badge/bertrend)](https://pepy.tech/project/bertrend)
 [![PyPi_Version](https://img.shields.io/pypi/v/bertrend.svg)](https://pypi.org/project/bertrend/)
-[![PyPi_Compat](https://img.shields.io/pypi/pyversions/bertrend.svg)](https://pypi.org/project/bertrend/)
+![Static Badge](https://img.shields.io/badge/python-%3E%3D3.12-blue)
 ![GitHub License](https://img.shields.io/github/license/rte-france/BERTrend)
 
 ![BERTrend pipeline](./BERTrend_overview.png)
@@ -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-0.3.4}/bertrend/demos/demos_utils/data_loading_component.py

@@ -11,6 +11,10 @@ import streamlit as st
 from streamlit.runtime.uploaded_file_manager import UploadedFile
 
 from bertrend import DATA_PATH
+from bertrend.demos.demos_utils.i18n import (
+    translate,
+    get_current_internationalization_language,
+)
 from bertrend.demos.demos_utils.icons import (
     WARNING_ICON,
     JSON_ICON,
@@ -20,7 +24,6 @@ from bertrend.demos.demos_utils.icons import (
     CLIENT_STORAGE_ICON,
     SERVER_STORAGE_ICON,
 )
-from bertrend.demos.demos_utils.messages import NO_DATA_AFTER_PREPROCESSING_MESSAGE
 from bertrend.demos.demos_utils.state_utils import (
     save_widget_state,
     register_widget,
@@ -33,9 +36,9 @@ from bertrend.utils.data_loading import (
     load_data,
     split_data,
     TIMESTAMP_COLUMN,
+    DataLoadingError,
 )
 
-NO_DATASET_WARNING = "Please select at least one dataset to proceed."
 FORMAT_ICONS = {
     "xlsx": XLSX_ICON,
     "csv": CSV_ICON,
@@ -47,6 +50,7 @@ FORMAT_ICONS = {
 }
 
 
+@st.cache_data(ttl=60 * 60 * 24)
 def _process_uploaded_files(
     files: list[UploadedFile],
 ) -> list[pd.DataFrame]:
@@ -57,15 +61,25 @@ def _process_uploaded_files(
             with open(tmpdir + "/" + f.name, "wb") as tmp_file:
                 tmp_file.write(f.getvalue())
             if tmp_file is not None:
-                df = load_data(
-                    Path(tmp_file.name),
-                    SessionStateManager.get("language", "French"),
-                )
+                try:
+                    df = load_data(
+                        Path(tmp_file.name),
+                        SessionStateManager.get("language", "French"),
+                    )
+                except DataLoadingError as dle:
+                    st.warning(
+                        translate("error_loading_file").format(
+                            file_name=f.name, error=dle
+                        ),
+                        icon=WARNING_ICON,
+                    )
+                    df = None
                 if df is not None:
                     dataframes.append(df)
         return dataframes
 
 
+@st.cache_data(ttl=60 * 60 * 24)
 def _load_files(
     files: list[Path],
 ) -> list[pd.DataFrame]:
@@ -73,10 +87,19 @@ def _load_files(
     dfs = []
     for selected_file in files:
         file_path = DATA_PATH / selected_file
-        df = load_data(
-            file_path,
-            SessionStateManager.get("language", "French"),
-        )
+        try:
+            df = load_data(
+                file_path,
+                SessionStateManager.get("language", "French"),
+            )
+        except DataLoadingError as dle:
+            st.warning(
+                translate("error_loading_file").format(
+                    file_name=file_path.name, error=dle
+                ),
+                icon=WARNING_ICON,
+            )
+            df = None
         if df is not None:
             dfs.append(df)
     return dfs
@@ -85,7 +108,7 @@ def _load_files(
 # TODO: if loaded data column names do not match our default values, show a popup for column data mapping
 def display_data_loading_component():
     """
-    Component for a streamlit app about topic modelling. It allows to choose data to load and preprocess data.
+    Component for a streamlit app about topic modeling. It allows choosing data to load and preprocess data.
     Preprocessing of data includes:
     - concatenation of data from different files
     - adding potentially missing columns to make all datasets homogeneous
@@ -100,23 +123,23 @@ def display_data_loading_component():
     state variable "time_filtered_df".
     """
     # Data loading section
-    st.header("Data loading")
+    st.header(translate("data_loading"))
 
     # Find files in the current directory and subdirectories
     tab1, tab2 = st.tabs(
         [
-            CLIENT_STORAGE_ICON + " Data from local storage",
-            SERVER_STORAGE_ICON + " Data from server data",
+            CLIENT_STORAGE_ICON + " " + translate("local_data"),
+            SERVER_STORAGE_ICON + " " + translate("remote_data"),
         ]
     )
     compatible_extensions = FORMAT_ICONS.keys()
 
     with tab1:
         st.file_uploader(
-            label="Select dataset from local storage (.xlsx, .csv, .json, .jsonl, .parquet)",
+            label=translate("select_from_local_storage"),
             type=compatible_extensions,
             accept_multiple_files=True,
-            help="Drag and drop files to be used as dataset in this area",
+            help=translate("drag_drop_help"),
             on_change=save_widget_state,
             key="uploaded_files",
         )
@@ -124,7 +147,7 @@ def display_data_loading_component():
     with tab2:
         register_widget("selected_files")
         st.multiselect(
-            label="Select one or more datasets from the server data",
+            label=translate("select_from_remote_storage"),
             options=find_compatible_files(DATA_PATH, compatible_extensions),
             default=SessionStateManager.get("selected_files", []),
             key="selected_files",
@@ -137,7 +160,7 @@ def display_data_loading_component():
         and not SessionStateManager.get("selected_files")
         and "initial_df" not in st.session_state
     ):
-        st.warning(NO_DATASET_WARNING, icon=WARNING_ICON)
+        st.warning(translate("no_dataset_warning"), icon=WARNING_ICON)
         st.stop()
 
     # Load each selected file, then concatenate them
@@ -159,10 +182,10 @@ def display_data_loading_component():
 
         # Save state of initial DF (before split and data selection)
         st.session_state["initial_df"] = df.copy()
-    # If dfs is None and there is no 'initial_df' in session_state, show warining
+    # If dfs is None and there is no 'initial_df' in session_state, show a warning
     elif "initial_df" not in st.session_state:
         st.warning(
-            NO_DATA_AFTER_PREPROCESSING_MESSAGE,
+            translate("no_data_after_preprocessing_message"),
             icon=WARNING_ICON,
         )
         st.stop()
@@ -172,54 +195,69 @@ def display_data_loading_component():
 
     # Show raw data info
     st.write(
-        f"Number of documents in raw data: **{len(st.session_state['initial_df'])}**"
+        translate("raw_documents_count").format(
+            count=len(st.session_state["initial_df"])
+        )
     )
 
     # Data filtering section
-    st.header("Data filtering")
+    st.header(translate("data_filtering"))
 
     # Display number input and checkbox for preprocessing options
     col1, col2, col3 = st.columns(3)
     with col1:
         register_widget("min_chars")
         st.number_input(
-            "Minimum Characters",
+            translate("minimum_characters"),
             value=MIN_CHARS_DEFAULT,
             min_value=0,
             max_value=1000,
             key="min_chars",
             on_change=save_widget_state,
-            help="Minimum number of characters each document must contain.",
+            help=translate("minimum_characters_help"),
         )
     with col2:
         register_widget("sample_size")
         sample_size = st.number_input(
-            "Sample ratio",
+            translate("sample_ratio"),
             value=SAMPLE_SIZE_DEFAULT,
             min_value=0.0,
             max_value=1.0,
             key="sample_size",
             on_change=save_widget_state,
-            help="Fraction of raw data to use for computing topics. Randomly samples documents from raw data.",
+            help=translate("sample_ratio_help"),
         )
     with col3:
         register_widget("split_by_paragraph")
         SessionStateManager.get_or_set("split_by_paragraph", "no")
         st.segmented_control(
-            "Split text by paragraphs",
+            translate("split_by_paragraph"),
             key="split_by_paragraph",
-            options=["no", "yes", "enhanced"],
+            options=["yes", "no", "enhanced"],
             selection_mode="single",
-            help="'No split': No splitting on the documents ; 'Split by paragraphs': Split documents into paragraphs ; "
-            "'Enhanced split': uses a more advanced but slower method for splitting that considers the embedding "
-            "model's maximum input length.",
+            help=translate("split_help"),
             on_change=save_widget_state,
+            format_func=lambda x: translate("split_option_" + x),
+        )
+
+    if get_current_internationalization_language() == "en":
+        split_by_paragraph_param = SessionStateManager.get("split_by_paragraph")
+    else:
+        # option has been translated
+        split_by_paragraph_param = (
+            "no"
+            if SessionStateManager.get("split_by_paragraph") == "non"
+            else (
+                "enhanced"
+                if SessionStateManager.get("split_by_paragraph") == "amélioré"
+                else "yes"
+            )
         )
 
     df = split_data(
-        df,
-        SessionStateManager.get("min_chars"),
-        SessionStateManager.get("split_by_paragraph"),
+        df=df,
+        min_chars=SessionStateManager.get("min_chars"),
+        split_by_paragraph=SessionStateManager.get("split_by_paragraph"),
         embedding_model_name=SessionStateManager.get("embedding_model_name"),
     )
 
@@ -235,7 +273,7 @@ def display_data_loading_component():
     )
     register_widget("timeframe_slider")
     start_date, end_date = st.slider(
-        "Select Timeframe",
+        translate("select_timeframe"),
         min_value=min_date,
         max_value=max_date,
         value=(min_date, max_date),
@@ -257,7 +295,9 @@ def display_data_loading_component():
 
     SessionStateManager.set("time_filtered_df", df_filtered)
     st.write(
-        f"Number of documents in filtered data: **{len(SessionStateManager.get_dataframe('time_filtered_df'))}**"
+        translate("filtered_documents_count").format(
+            count=len(SessionStateManager.get_dataframe("time_filtered_df"))
+        )
     )
     st.dataframe(
         SessionStateManager.get_dataframe("time_filtered_df")[

{bertrend-0.3.2 → bertrend-0.3.4}/bertrend/demos/demos_utils/embed_documents_component.py

@@ -4,8 +4,8 @@
 #  This file is part of BERTrend.
 import streamlit as st
 
+from bertrend.demos.demos_utils.i18n import translate
 from bertrend.demos.demos_utils.icons import SUCCESS_ICON
-from bertrend.demos.demos_utils.messages import EMBEDDINGS_CALCULATED_MESSAGE
 from bertrend.demos.demos_utils.state_utils import SessionStateManager
 from bertrend.services.embedding_service import EmbeddingService
 from bertrend.utils.data_loading import TEXT_COLUMN
@@ -16,8 +16,8 @@ def display_embed_documents_component():
     Common Streamlit UI component for embedding documents.
     """
     # Embed documents
-    if st.button("Embed Documents"):
-        with st.spinner("Embedding documents..."):
+    if st.button(translate("embed_documents")):
+        with st.spinner(translate("embedding_documents")):
             embedding_dtype = SessionStateManager.get("embedding_dtype")
             embedding_model_name = SessionStateManager.get("embedding_model_name")
             if SessionStateManager.get("embedding_service_type", "remote") == "local":
@@ -49,4 +49,4 @@ def display_embed_documents_component():
 
             SessionStateManager.set("data_embedded", True)
 
-            st.success(EMBEDDINGS_CALCULATED_MESSAGE, icon=SUCCESS_ICON)
+            st.success(translate("embeddings_calculated_message"), icon=SUCCESS_ICON)