bertrend 0.3.3__tar.gz → 0.3.5__tar.gz

{bertrend-0.3.3 → bertrend-0.3.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: bertrend
-Version: 0.3.3
+Version: 0.3.5
 Summary: BERTrend analyses topic evolution over time using state-of-the-art transformer models: topic modelling and LLM
 License: LICENSE.md
 Keywords: topics,BERTopic,transformers,weak signals,LLM
@@ -11,6 +11,7 @@ Maintainer-email: jerome.picault@rte-france.com
 Requires-Python: >=3.12,<4.0
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Provides-Extra: apps
+Requires-Dist: PyJWT (>=2.10.1)
 Requires-Dist: Pyqtree (==1.0.0)
 Requires-Dist: arxiv (>=2.2.0) ; extra == "apps"
 Requires-Dist: bertopic (==0.16.2)
@@ -41,13 +42,14 @@ 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)
+Requires-Dist: openpyxl (>=3.1.5)
 Requires-Dist: opentelemetry-exporter-otlp-proto-grpc (==1.25.0)
 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)
+Requires-Dist: pytest (>=8.4.0)
 Requires-Dist: requests (>=2.32.3)
 Requires-Dist: scikit-learn (>=1.5.2)
 Requires-Dist: scipy (==1.12)
@@ -55,7 +57,7 @@ Requires-Dist: seaborn (>=0.13.2)
 Requires-Dist: sentence-transformers (==3.0.1)
 Requires-Dist: sentencepiece (>=0.2.0)
 Requires-Dist: starlette (>=0.46.2)
-Requires-Dist: streamlit (>=1.45.0)
+Requires-Dist: streamlit (>=1.45.1)
 Requires-Dist: streamlit-code-editor (>=0.1.22)
 Requires-Dist: thefuzz (>=0.22.1)
 Requires-Dist: tiktoken (>=0.8.0)
@@ -78,7 +80,7 @@ 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)
@@ -258,7 +260,7 @@ We recommend using a remote embedding service (this is now the default config) a
 
 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)
+An example of a very simple implementation to deploy a separate embedding service can be found here: `bertrend/services/embedding_server`
 
 
 ![parameters](docs/images/parameters.png)

{bertrend-0.3.3 → bertrend-0.3.5}/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)
@@ -186,7 +186,7 @@ We recommend using a remote embedding service (this is now the default config) a
 
 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)
+An example of a very simple implementation to deploy a separate embedding service can be found here: `bertrend/services/embedding_server`
 
 
 ![parameters](docs/images/parameters.png)

{bertrend-0.3.3 → bertrend-0.3.5}/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-0.3.3 → bertrend-0.3.5}/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)

bertrend-0.3.5/bertrend/demos/demos_utils/i18n.py

@@ -0,0 +1,95 @@
+"""
+Internationalization (i18n) module for the prospective demo application.
+Provides functionality for translating text between French and English.
+"""
+
+#  Copyright (c) 2024, RTE (https://www.rte-france.com)
+#  See AUTHORS.txt
+#  SPDX-License-Identifier: MPL-2.0
+#  This file is part of BERTrend.
+
+import streamlit as st
+from typing import Optional
+
+from bertrend_apps.prospective_demo.i18n_translations import (
+    TRANSLATIONS as PROSPECTIVE_TRANSLATIONS,
+)
+from bertrend.demos.topic_analysis.i18n_translations import (
+    TRANSLATIONS as TOPIC_ANALYSIS_TRANSLATIONS,
+)
+from bertrend.demos.demos_utils.i18n_translations import (
+    TRANSLATIONS as DEMOS_UTILS_TRANSLATIONS,
+)
+from bertrend.demos.weak_signals.i18n_translations import (
+    TRANSLATIONS as WEAK_SIGNALS_TRANSLATIONS,
+)
+
+# Merge all translations
+TRANSLATIONS = {
+    **PROSPECTIVE_TRANSLATIONS,
+    **TOPIC_ANALYSIS_TRANSLATIONS,
+    **DEMOS_UTILS_TRANSLATIONS,
+    **WEAK_SIGNALS_TRANSLATIONS,
+}
+
+# Available languages
+LANGUAGES = {"fr": "Français", "en": "English"}
+
+# Default language
+DEFAULT_LANGUAGE = "en"
+
+
+def set_default_internationalization_language(language: str) -> None:
+    """Set the default language for the application."""
+    global DEFAULT_LANGUAGE
+    DEFAULT_LANGUAGE = language
+
+
+def get_current_internationalization_language() -> str:
+    """Get the currently selected language from the session state."""
+    if "internationalization_language" not in st.session_state:
+        st.session_state.internationalization_language = DEFAULT_LANGUAGE
+    return st.session_state.internationalization_language
+
+
+def set_internationalization_language(language: str) -> None:
+    """Set the current language in the session state."""
+    if language in LANGUAGES:
+        st.session_state.internationalization_language = language
+
+
+def create_internationalization_language_selector() -> None:
+    """Create a language selector widget in the sidebar."""
+    current_lang = get_current_internationalization_language()
+    selected_lang = st.sidebar.selectbox(
+        "Language / Langue",
+        options=list(LANGUAGES.keys()),
+        format_func=lambda x: LANGUAGES[x],
+        index=list(LANGUAGES.keys()).index(current_lang),
+    )
+
+    if selected_lang != current_lang:
+        set_internationalization_language(selected_lang)
+        st.rerun()
+
+
+def translate(key: str, default: Optional[str] = None) -> str:
+    """
+    Translate a text key to the current language.
+
+    Args:
+        key: The translation key to look up
+        default: Default text to return if the key is not found
+
+    Returns:
+        The translated text in the current language
+    """
+    lang = get_current_internationalization_language()
+
+    if key in TRANSLATIONS and lang in TRANSLATIONS[key]:
+        return TRANSLATIONS[key][lang]
+
+    # If the key doesn't exist, or the language is not available for this key
+    if default:
+        return default
+    return key  # Return the key itself as fallback

bertrend-0.3.5/bertrend/demos/demos_utils/i18n_translations.py

@@ -0,0 +1,140 @@
+#  Copyright (c) 2024, RTE (https://www.rte-france.com)
+#  See AUTHORS.txt
+#  SPDX-License-Identifier: MPL-2.0
+#  This file is part of BERTrend.
+
+# Translation dictionaries for demos_utils
+TRANSLATIONS = {
+    "ctrl_enter": {
+        "fr": "CTRL + Entrée pour mettre à jour",
+        "en": "CTRL + Enter to update",
+    },
+    "select_language": {"fr": "Choisir une langue", "en": "Select Language"},
+    "embedding_model": {"fr": "Modèle d'embedding", "en": "Embedding Model"},
+    "embedding_service_url": {
+        "fr": "URL du service d'embedding",
+        "en": "Embedding service URL",
+    },
+    "embedding_hyperparameters": {
+        "fr": "Paramètres d'embedding",
+        "en": "Embedding settings",
+    },
+    "embedding_service": {
+        "fr": "Service d'embedding",
+        "en": "Embedding Service",
+    },
+    "bertopic_hyperparameters": {
+        "fr": "Hyperparamètres BERTopic",
+        "en": "BERTopic Hyperparameters",
+    },
+    "bertrend_hyperparameters": {
+        "fr": "Hyperparamètres BERTrend",
+        "en": "BERTrend Hyperparameters",
+    },
+    "embeddings_calculated_message": {
+        "fr": "Embeddings calculés avec succès !",
+        "en": "Embeddings calculated successfully!",
+    },
+    "no_embeddings_warning_message": {
+        "fr": "Veuillez vectoriser les données et entraîner les modèles avant de procéder à l'analyse.",
+        "en": "Please embed data and train models before proceeding to analysis.",
+    },
+    "model_training_complete_message": {
+        "fr": "Entraînement du modèle terminé !",
+        "en": "Model training complete!",
+    },
+    "no_data_after_preprocessing_message": {
+        "fr": "Aucune donnée disponible après prétraitement. Veuillez vérifier les fichiers sélectionnés et les options de prétraitement.",
+        "en": "No data available after preprocessing. Please check the selected files and preprocessing options.",
+    },
+    "select_from_local_storage": {
+        "fr": "Selection de jeux de données à partir du stockage local (.xlsx, .csv, .json, .jsonl, .parquet)",
+        "en": "Select dataset from local storage (.xlsx, .csv, .json, .jsonl, .parquet)",
+    },
+    "select_from_remote_storage": {
+        "fr": "Selection de jeux de données sur le serveur",
+        "en": "Select one or more datasets from the server data",
+    },
+    "data_loading": {
+        "fr": "Chargement des données",
+        "en": "Data loading",
+    },
+    "local_data": {
+        "fr": "Données locales",
+        "en": "Data from local storage",
+    },
+    "remote_data": {"fr": "Données sur le serveur", "en": "Data from server"},
+    "data_filtering": {"fr": "Filtrage des données", "en": "Data filtering"},
+    "embed_documents": {
+        "fr": "Vectoriser les documents",
+        "en": "Embed Documents",
+    },
+    "embedding_documents": {
+        "fr": "Vectorisation des documents...",
+        "en": "Embedding documents...",
+    },
+    "no_dataset_warning": {
+        "fr": "Veuillez sélectionner au moins un jeu de données pour continuer.",
+        "en": "Please select at least one dataset to proceed.",
+    },
+    "error_loading_file": {
+        "fr": "Erreur lors du chargement du fichier '{file_name}': {error}",
+        "en": "Error while loading file '{file_name}': {error}",
+    },
+    "drag_drop_help": {
+        "fr": "Glissez et déposez les fichiers à utiliser comme jeu de données dans cette zone",
+        "en": "Drag and drop files to be used as dataset in this area",
+    },
+    "raw_documents_count": {
+        "fr": "Nombre de documents dans les données brutes: **{count}**",
+        "en": "Number of documents in raw data: **{count}**",
+    },
+    "minimum_characters": {
+        "fr": "Nombre minimum de caractères",
+        "en": "Minimum Characters",
+    },
+    "minimum_characters_help": {
+        "fr": "Nombre minimum de caractères que chaque document doit contenir.",
+        "en": "Minimum number of characters each document must contain.",
+    },
+    "sample_ratio": {
+        "fr": "Ratio d'échantillonnage",
+        "en": "Sample ratio",
+    },
+    "sample_ratio_help": {
+        "fr": "Fraction des données brutes à utiliser pour calculer les sujets. Échantillonne aléatoirement les documents à partir des données brutes.",
+        "en": "Fraction of raw data to use for computing topics. Randomly samples documents from raw data.",
+    },
+    "split_by_paragraphs": {
+        "fr": "Diviser le texte par paragraphes",
+        "en": "Split text by paragraphs",
+    },
+    "split_option_yes": {
+        "fr": "oui",
+        "en": "yes",
+    },
+    "split_option_no": {
+        "fr": "non",
+        "en": "no",
+    },
+    "split_option_enhanced": {
+        "fr": "amélioré",
+        "en": "enhanced",
+    },
+    "split_help": {
+        "fr": "'Pas de division': Pas de division sur les documents ; 'Division par paragraphes': Divise les documents en paragraphes ; 'Division améliorée': utilise une méthode plus avancée mais plus lente pour la division qui prend en compte la longueur d'entrée maximale du modèle d'embedding.",
+        "en": "'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.",
+    },
+    "select_timeframe": {
+        "fr": "Sélectionner la période",
+        "en": "Select Timeframe",
+    },
+    "filtered_documents_count": {
+        "fr": "Nombre de documents dans les données filtrées: **{count}**",
+        "en": "Number of documents in filtered data: **{count}**",
+    },
+    "settings_and_controls": {
+        "fr": "Paramètres et contrôles",
+        "en": "Settings and Controls",
+    },
+}