Modernize: latest deps, py3.12, cache_data/cache_resource, fix empty seed_keywords IndexError

README.md

@@ -4,8 +4,10 @@ emoji: 🔑
 colorFrom: purple
 colorTo: green
 sdk: streamlit
+python_version: "3.12"
 app_file: app.py
 pinned: false
+license: mit
 ---
 
 # Configuration

app.py

@@ -40,15 +40,15 @@ form.caption("See the list of pre-trained models that are available here! https:
 form.form_submit_button("Submit")
 
 
-@st.cache
-def load_and_process_data(path, name, streaming, split_name, number_of_records):
-    dataset = load_dataset(path = path, name = name, streaming=streaming)
+@st.cache_data
+def load_and_process_data(path, name, streaming, split_name, number_of_records, column_name):
+    dataset = load_dataset(path = path, name = name or None, streaming=streaming)
     #return list(dataset)
     dataset_head = dataset[split_name].take(number_of_records)
     df = pd.DataFrame.from_dict(dataset_head)
     return df[column_name]
 
-@st.cache(allow_output_mutation=True)
+@st.cache_resource
 def load_model(model_name):
     kw_model = KeyBERT(model=model_name)
     return kw_model
@@ -57,7 +57,7 @@ model = load_model(model_name=model_name)
 
 if custom_doc:
     st.header("Original Dataset")
-    df = load_and_process_data(dataset_name, dataset_name_2, True, split_name, number_of_records)
+    df = load_and_process_data(dataset_name, dataset_name_2, True, split_name, number_of_records, column_name)
     doc = list(df[index_to_analyze_start:index_to_analyze_end])
     st.write(df)
 st.header("Indexed Documents")
@@ -86,7 +86,10 @@ form2.caption("Due to the implementation details of this in KeyBERT, this doesn'
 
 form2.form_submit_button("Submit")
 
-keywords = model.extract_keywords(doc, keyphrase_ngram_range=(keyphrase_min, keyphrase_max), use_maxsum = use_maxsum, use_mmr = use_mmr, diversity = diversity, top_n = top_n, min_df = min_df, nr_candidates = nr_candidates, seed_keywords = seed_keywords.split())
+## KeyBERT indexes seed_keywords[0] directly, so an empty list raises IndexError - pass None instead
+seed_keywords_list = seed_keywords.split() or None
+
+keywords = model.extract_keywords(doc, keyphrase_ngram_range=(keyphrase_min, keyphrase_max), use_maxsum = use_maxsum, use_mmr = use_mmr, diversity = diversity, top_n = top_n, min_df = min_df, nr_candidates = nr_candidates, seed_keywords = seed_keywords_list)
 
 st.header("Extracted Keywords/Keyphrases")
 st.caption("Output is sorted in reverse order (so the final element is the strongest keyphrase and the first element is the nth strongest)")

requirements.txt

@@ -1,5 +1,5 @@
-keybert
 streamlit
+keybert
+sentence-transformers
 pandas
 datasets
-altair<5