bertrend 0.3.6__tar.gz → 0.3.7__tar.gz

{bertrend-0.3.6 → bertrend-0.3.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: bertrend
-Version: 0.3.6
+Version: 0.3.7
 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

{bertrend-0.3.6 → bertrend-0.3.7}/bertrend/BERTopicModel.py

@@ -237,6 +237,7 @@ class BERTopicModel:
             Precomputed document embeddings.
         embedding_model : SentenceTransformer or str or None, optional
             Sentence transformer (or associated model name) model for embeddings.
+            NB. Important: if not set, the keywords describing the topics may not be correct (e.g. accents strip); therefore, it is recommended to set this parameter.
         zeroshot_topic_list : list[str] or None, optional
             List of topics used for zeroshot classification.
         zeroshot_min_similarity : float or None, optional

{bertrend-0.3.6 → bertrend-0.3.7}/bertrend/demos/demos_utils/embed_documents_component.py

@@ -31,6 +31,9 @@ def display_embed_documents_component():
                     local=False,
                     url=SessionStateManager.get("embedding_service_url"),
                 )
+                SessionStateManager.set(
+                    "embedding_model_name", embedding_service.embedding_model_name
+                )
 
             texts = SessionStateManager.get_dataframe("time_filtered_df")[
                 TEXT_COLUMN

{bertrend-0.3.6 → bertrend-0.3.7}/bertrend/demos/topic_analysis/demo_pages/explore_topics.py

@@ -292,7 +292,7 @@ def _display_topic_description(filtered_df: pd.DataFrame):
         with st.spinner(translate("generating_description")):
             language_code = (
                 "fr"
-                if SessionStateManager.get("internationalization_language") == "French"
+                if SessionStateManager.get("internationalization_language") == "fr"
                 else "en"
             )
             gpt_description = generate_topic_description(

{bertrend-0.3.6 → bertrend-0.3.7}/bertrend/demos/topic_analysis/demo_pages/newsletters_generation.py

@@ -51,7 +51,7 @@ def generate_newsletter_wrapper(
 
     language_code = (
         "fr"
-        if SessionStateManager.get("internationalization_language") == "French"
+        if SessionStateManager.get("internationalization_language") == "fr"
         else "en"
     )
 

{bertrend-0.3.6 → bertrend-0.3.7}/bertrend/demos/topic_analysis/demo_pages/training_page.py

@@ -127,6 +127,7 @@ def train_model():
         topic_model_output = topic_model.fit(
             docs=dataset,
             embeddings=embeddings,
+            embedding_model=SessionStateManager.get("embedding_model_name"),
         )
         bertopic = topic_model_output.topic_model
 

{bertrend-0.3.6 → bertrend-0.3.7}/bertrend/llm_utils/newsletter_features.py

@@ -50,7 +50,7 @@ def generate_newsletter(
     openai_model_name: str = None,
     nb_sentences: int = 3,
 ) -> tuple[str, str, str]:
-    """Generates a newsletters based on a trained BERTopic model.
+    """Generates a newsletter based on a trained BERTopic model.
 
     Args:
         topic_model (BERTopic): trained BERTopic model

{bertrend-0.3.6 → bertrend-0.3.7}/bertrend_apps/exploration/curebot/app_utils.py

@@ -131,6 +131,7 @@ def fit_bertopic(
     topic_model_output = topic_model.fit(
         docs=docs,
         embeddings=embeddings,
+        embedding_model=EMBEDDING_SERVICE.embedding_model_name,
         zeroshot_topic_list=zeroshot_topic_list,
         zeroshot_min_similarity=0.65,
     )

{bertrend-0.3.6 → bertrend-0.3.7}/bertrend_apps/exploration/curebot/tabs/tab1.py

@@ -130,9 +130,9 @@ def train_model() -> None:
 
     # Train topic model
     bertopic, topics = fit_bertopic(
-        texts_list,
-        embeddings,
-        st.session_state["min_articles_per_topic"],
+        docs=texts_list,
+        embeddings=embeddings,
+        min_articles_per_topic=st.session_state["min_articles_per_topic"],
         zeroshot_topic_list=zeroshot_topic_list,
     )
 

{bertrend-0.3.6 → bertrend-0.3.7}/bertrend_apps/newsletters/__main__.py

@@ -216,6 +216,7 @@ if __name__ == "__main__":
         output = topic_model.fit(
             docs=dataset[TEXT_COLUMN],
             embeddings=embeddings,
+            embedding_model=embedding_model,
         )
         return output.topics, output.topic_model
 

{bertrend-0.3.6 → bertrend-0.3.7}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "bertrend"
-version = "0.3.6"
+version = "0.3.7"
 description = "BERTrend analyses topic evolution over time using state-of-the-art transformer models: topic modelling and LLM"
 license = "LICENSE.md"
 readme = "README.md"