Upgraded Gradio version to 5.6.0 in Readme. Upgraded pyarrow version

README.md

@@ -4,7 +4,7 @@ emoji: 🔍
 colorFrom: purple
 colorTo: green
 sdk: gradio
-sdk_version: 4.36.0
+sdk_version: 5.6.0
 app_file: app.py
 pinned: false
 license: apache-2.0

requirements.txt

@@ -1,6 +1,6 @@
 pandas==2.2.3
 polars==0.20.3
-pyarrow==17.0.0
+pyarrow==18.1.0
 openpyxl==3.1.3
 torch==2.5.1 --index-url https://download.pytorch.org/whl/cpu
 spacy==3.8.0

requirements_aws.txt

@@ -1,6 +1,6 @@
 pandas==2.2.3
 polars==0.20.3
-pyarrow==17.0.0
+pyarrow==18.1.0
 openpyxl==3.1.3
 spacy==3.8.0
 en_core_web_sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.8.0/en_core_web_sm-3.8.0.tar.gz

requirements_gpu.txt

@@ -1,6 +1,6 @@
 pandas==2.2.3
 polars==0.20.3
-pyarrow==17.0.0
+pyarrow==18.1.0
 openpyxl==3.1.3
 torch==2.5.1 --index-url https://download.pytorch.org/whl/nightly/cu121
 spacy==3.8.0

requirements_keyword_only.txt

@@ -1,6 +1,6 @@
 pandas==2.2.3
 polars==0.20.3
-pyarrow==17.0.0
+pyarrow==18.1.0
 openpyxl==3.1.3
 #torch==2.5.1 --index-url https://download.pytorch.org/whl/cpu
 spacy==3.8.0

requirements_no_semantic.txt

@@ -1,9 +0,0 @@
-pandas==2.2.2
-polars==0.20.3
-pyarrow==14.0.2
-openpyxl==3.1.2
-spacy
-en_core_web_sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.7.1/en_core_web_sm-3.7.1.tar.gz
-gradio
-lxml==5.1.0
-boto3==1.34.103

search_funcs/spacy_search_funcs.py

@@ -131,7 +131,7 @@ def spacy_fuzzy_search(string_query:str, tokenised_data: List[List[str]], origin
     # Out file
     query_str_file = "_".join(tokenised_query).replace(" ", "_")  # Replace spaces with underscores
     query_str_file = re.sub(r'[<>:"/\\|?*]', '', query_str_file)  # Remove invalid characters
-    query_str_file = query_str_file[:30]  # Limit to 30 characters
+    query_str_file = query_str_file[:100]  # Limit to 100 characters
         
     results_df_name = output_folder + "fuzzy_keyword_search_result_" + today_rev + "_" +  query_str_file + ".xlsx"
 
@@ -140,8 +140,8 @@ def spacy_fuzzy_search(string_query:str, tokenised_data: List[List[str]], origin
 
     #results_df_out.to_excel(results_df_name, index= None)
 
-    print("string_query:", string_query)
-    print(results_df_out)
+    #print("string_query:", string_query)
+    #print(results_df_out)
 
     # Highlight found text and save to file
     results_df_out_wb = create_highlighted_excel_wb(results_df_out, string_query, "search_text")