Upgraded to Gradio 4.16.0. Guide for converting to exe added.

.gitignore

@@ -11,7 +11,12 @@
 *.json
 *.html
 *.log
+*.spec
 .ipynb_checkpoints/*
 old_code/*
 model/*
-output_model/*
+output_model/*
+data/*
+build_deps/*
+dist/*
+build/*

README.md

@@ -4,7 +4,7 @@ emoji: 🚀
 colorFrom: red
 colorTo: yellow
 sdk: gradio
-sdk_version: 3.50.0
+sdk_version: 4.16.0
 app_file: app.py
 pinned: true
 license: apache-2.0

app.py

@@ -1,5 +1,6 @@
-# Dendrograms will not work with the latest version of scipy (1.12.0), so installing the version prior to be safe
-#os.system("pip install scipy==1.11.4")
+# Dendrograms will not work with the latest version of scipy (1.12.0), so run the following here/in your environment if you come across issues
+# import os
+# os.system("pip install scipy==1.11.4")
 
 import gradio as gr
 import pandas as pd
@@ -42,7 +43,7 @@ with block:
         with gr.Accordion("Clean data", open = False):
             with gr.Row():
                 clean_text = gr.Dropdown(value = "No", choices=["Yes", "No"], multiselect=False, label="Clean data - remove html, numbers with > 2 digits, emails, postcodes (UK).")
-                drop_duplicate_text = gr.Dropdown(value = "No", choices=["Yes", "No"], multiselect=False, label="Remove duplicate text, drop < 10 char strings. May make previous embedding files incompatible due to differing lengths.")
+                drop_duplicate_text = gr.Dropdown(value = "No", choices=["Yes", "No"], multiselect=False, label="Remove duplicate text, drop < 10 char strings. May make old embedding files incompatible due to differing lengths.")
                 anonymise_drop = gr.Dropdown(value = "No", choices=["Yes", "No"], multiselect=False, label="Anonymise data on file load. Personal details are redacted - not 100% effective. This is slow!")                
             clean_btn = gr.Button("Clean data")
 

funcs/helper_functions.py

@@ -30,12 +30,12 @@ class Logger:
     def isatty(self):
         return False    
 
-sys.stdout = Logger("output.log")
+#sys.stdout = Logger("output.log")
 
-def read_logs():
-    sys.stdout.flush()
-    with open("output.log", "r") as f:
-        return f.read()
+# def read_logs():
+#     sys.stdout.flush()
+#     with open("output.log", "r") as f:
+#         return f.read()
 
 
 def detect_file_type(filename):

how_to_create_exe_dist.txt

@@ -0,0 +1,35 @@
+1. Create minimal environment to run the app in conda. E.g. 'conda create --name new_env'
+
+2. Activate the environment 'conda activate new_env'
+
+3. cd to this folder. Install packages from requirements.txt using 'pip install -r requirements.txt' 
+
+NOTE: for ensuring that spaCy models are loaded into the program correctly in requirements.txt, follow this guide: https://spacy.io/usage/models#models-download
+
+6. If necessary, create hook- files to tell pyinstaller to include specific packages in the exe build. Examples are provided for gradio and en_core_web_sm (a spaCy model). Put these in the build_deps\ subfolder
+
+7. pip install pyinstaller
+
+8. In command line, cd to the folder that contains app.py. 
+
+9.Run the following, assuming you want to make one single .exe file (This helped me: https://github.com/pyinstaller/pyinstaller/issues/8108):
+
+a) In command line: pyi-makespec --additional-hooks-dir="build_deps\\" --collect-data=gradio_client --collect-data=gradio --hidden-import pyarrow.vendored.version --onefile --name Bertopic_app_0.1 app.py
+
+b) Open the created spec file in Notepad. Add the following to the end of the Analysis section then save:
+
+a = Analysis(
+    ...
+    module_collection_mode={
+        'gradio': 'py',  # Collect gradio package as source .py files
+    }
+)
+
+c) Back in command line, run this: pyinstaller --clean --noconfirm Bertopic_app_0.1.spec
+
+
+9. A 'dist' folder will be created with the executable inside along with all dependencies('dist\data_text_search'). 
+
+10. In 'dist\data_text_search' try double clicking on the .exe file. After a short delay, the command prompt should inform you about the IP address of the app that is now running. Copy the IP address. **Do not close this window!**
+
+11. In an Internet browser, navigate to the indicated IP address. The app should now be running in your browser window.

requirements.txt

@@ -1,4 +1,4 @@
-gradio==3.50.0
+gradio==4.16.0
 transformers==4.37.1
 accelerate==0.26.1
 torch==2.1.2