view debug info

.gitignore

@@ -0,0 +1,181 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor  
+#  Cursor is an AI-powered code editor.`.cursorignore` specifies files/directories to 
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore

app.py

@@ -51,7 +51,7 @@ def extract_wikipedia_content(wiki_url, api_key, model_id, base_url, target_lang
     )
 
 def translate_content(content, article_title, artice_summary, content_format, 
-                      target_lang, api_key, model_id, base_url):
+                      target_lang, api_key, model_id, base_url, debug_mode=False):
 
     llm_client = init_llm_client(api_key, base_url=base_url)
 
@@ -76,17 +76,37 @@ def translate_content(content, article_title, artice_summary, content_format,
     )
 
     decoded_object = json_repair.loads(response.choices[0].message.content)
+    
+    # Return translation and debug info if debug mode is enabled
+    if debug_mode:
+        debug_info = {
+            "prompt": translation_prompt,
+            "response": response.choices[0].message.content,
+            "usage": {
+                "prompt_tokens": response.usage.prompt_tokens,
+                "completion_tokens": response.usage.completion_tokens,
+                "total_tokens": response.usage.total_tokens
+            },
+            "model": model_id
+        }
+        
+        if 'output_content' in decoded_object:
+            return decoded_object['output_content'], debug_info
+        return "Error: Translation output not found in the response.", debug_info
+    
+    # Regular return when debug mode is disabled
     if 'output_content' in decoded_object:
         return decoded_object['output_content']
 
     return "Error: Translation output not found in the response."
 
-def translate_section(section_content, article_title, article_summary, content_format, target_lang, custom_lang, api_key, model_id, base_url):
+def translate_section(section_content, article_title, article_summary, content_format, 
+                      target_lang, custom_lang, api_key, model_id, base_url, debug_mode=False):
     """
     Translates a single section of the Wikipedia article
     """
     if not section_content or not api_key:
-        return "Please provide content and API key for translation."
+        return "Please provide content and API key for translation.", None if debug_mode else None
     
     # Use custom language if selected
     if target_lang == "custom" and custom_lang:
@@ -94,7 +114,7 @@ def translate_section(section_content, article_title, article_summary, content_f
     else:
         actual_lang = target_lang
     
-    return translate_content(
+    result = translate_content(
         content=section_content,
         article_title=article_title,
         artice_summary=article_summary,
@@ -102,58 +122,77 @@ def translate_section(section_content, article_title, article_summary, content_f
         target_lang=actual_lang,
         api_key=api_key,
         model_id=model_id,
-        base_url=base_url
+        base_url=base_url,
+        debug_mode=debug_mode
     )
+    
+    if debug_mode:
+        translation, debug_info = result
+        return translation, debug_info
+    return result, None
 
-def update_ui_with_sections(sections_dict):
-    """
-    Creates a list of components to display in the sections area
+def format_debug_info(debug_info):
+    """Format debug information as markdown for display in modal"""
+    if not debug_info:
+        return "No debug information available."
+    
+    # Format the debug information as markdown
+    markdown = "## LLM Debug Information\n\n"
+    
+    # Add model and usage info
+    markdown += f"### Model: {debug_info['model']}\n\n"
+    markdown += "### Usage\n"
+    markdown += f"- Prompt tokens: {debug_info['usage']['prompt_tokens']}\n"
+    markdown += f"- Completion tokens: {debug_info['usage']['completion_tokens']}\n"
+    markdown += f"- Total tokens: {debug_info['usage']['total_tokens']}\n\n"
+    
+    # Add prompt
+    markdown += "### Prompt\n"
+    markdown += f"```\n{debug_info['prompt'].replace('```','')}\n```\n\n"
+    
+    # Add raw response
+    markdown += "### Raw Response\n"
+    markdown += f"```json\n{debug_info['response']}\n```\n"
+    
+    return markdown
+
+# Add this function to update UI with sections from Wikipedia content
+def update_ui_with_sections(sections):
     """
-    components = []
+    Updates the UI to display sections from the Wikipedia article
     
-    if not sections_dict:
-        # Return updates for all components (input, button, output)
-        empty_updates = []
-        for _ in range(100):  # Assuming max 100 sections
-            empty_updates.extend([
-                gr.update(visible=False),  # section textbox
-                gr.update(visible=False),  # translate button
-                gr.update(visible=False)   # translation output
-            ])
-        return empty_updates
+    Args:
+        sections: Dictionary of section titles and content
     
-    # Create visible components for available sections
-    for section_name, section_content in sections_dict.items():
-        # Update for section content textbox
-        components.append(gr.update(
-            value=section_content,
-            label=f"Section: {section_name}",
-            visible=True
-        ))
-        
-        # Update for translate button
-        components.append(gr.update(
-            visible=True,
-            value=f"Translate {section_name}"
-        ))
-        
-        # Update for translation output
-        components.append(gr.update(
-            visible=True,
-            value="",
-            label=f"Translation: {section_name}"
-        ))
+    Returns:
+        List of updates for all section components
+    """
+    results = []
     
-    # Hide any unused components
-    remaining = 100 - len(sections_dict)  # Assuming max 100 sections
-    for _ in range(remaining):
-        components.extend([
-            gr.update(visible=False),  # section textbox
-            gr.update(visible=False),  # translate button
-            gr.update(visible=False)   # translation output
-        ])
+    # Prepare updates for up to 100 sections (400 components - 4 per section)
+    for i in range(100):
+        if i < len(sections):
+            # Get section title and content
+            section_title = list(sections.keys())[i]
+            section_content = sections[section_title]
+            
+            # Make section textbox visible with content and label
+            results.extend([
+                gr.update(visible=True, value=section_content, label=f"Section: {section_title}"),
+                gr.update(visible=True),  # Translate button
+                gr.update(visible=True, value="", label=f"Translation: {section_title}"),  # Translation output
+                gr.update(visible=False)  # Debug button (hidden by default)
+            ])
+        else:
+            # Hide unused components
+            results.extend([
+                gr.update(visible=False),
+                gr.update(visible=False),
+                gr.update(visible=False),
+                gr.update(visible=False)
+            ])
     
-    return components
+    return results
 
 # Create Gradio app
 with gr.Blocks(theme=gr.themes.Monochrome()) as demo:
@@ -232,6 +271,13 @@ with gr.Blocks(theme=gr.themes.Monochrome()) as demo:
                     label="Content Format",
                     info="Choose how to display article content"
                 )
+                
+                # Debug mode toggle
+                debug_mode = gr.Checkbox(
+                    label="Debug Mode",
+                    value=False,
+                    info="Show detailed information about LLM calls"
+                )
             
             gr.Markdown("### About")
             gr.Markdown("""
@@ -286,6 +332,12 @@ with gr.Blocks(theme=gr.themes.Monochrome()) as demo:
                 visible=False  # Hidden by default as it's usually large
             )
             
+            # Debug info state and modal components
+            debug_info_state = gr.State(None)
+            
+            with gr.Blocks() as debug_modal:
+                debug_markdown = gr.Markdown("Debug information will appear here.")
+            
             # Pre-define section textboxes and related components
             gr.Markdown("### Article Sections")
             with gr.Column() as sections_container:
@@ -295,10 +347,11 @@ with gr.Blocks(theme=gr.themes.Monochrome()) as demo:
                         section_textbox = gr.Textbox(visible=False, lines=4)
                         translate_btn = gr.Button("Translate", visible=False)
                         translation_output = gr.Textbox(visible=False, lines=4)
-                        section_components.extend([section_textbox, translate_btn, translation_output])
+                        debug_btn = gr.Button("View Debug Info", visible=False)
+                        section_components.extend([section_textbox, translate_btn, translation_output, debug_btn])
             
                         # Connect the translate button to the translation function
-                        translate_btn.click(
+                        result = translate_btn.click(
                             fn=translate_section,
                             inputs=[
                                 section_textbox,
@@ -309,9 +362,27 @@ with gr.Blocks(theme=gr.themes.Monochrome()) as demo:
                                 custom_language,
                                 api_key,
                                 model_id,
-                                base_url
+                                base_url,
+                                debug_mode
                             ],
-                            outputs=translation_output
+                            outputs=[translation_output, debug_info_state]
+                        )
+                        
+                        # Show debug button only when debug mode is on and after translation
+                        result.then(
+                            fn=lambda debug_info, debug_mode: gr.update(visible=debug_mode and debug_info is not None),
+                            inputs=[debug_info_state, debug_mode],
+                            outputs=[debug_btn]
+                        )
+                        
+                        # Connect debug button to show modal with debug info
+                        debug_btn.click(
+                            fn=format_debug_info,
+                            inputs=[debug_info_state],
+                            outputs=[debug_markdown]
+                        ).then(
+                            fn=lambda: True,
+                            outputs=[debug_modal]
                         )
     
     # Connect the extract button to the function
@@ -345,6 +416,25 @@ with gr.Blocks(theme=gr.themes.Monochrome()) as demo:
         outputs=[sidebar_expanded, sidebar, main_content, sidebar_show_btn]
     )
     
+    # Add debug info display to the bottom of the sidebar
+    with sidebar:
+        debug_header = gr.Markdown("### Debug Information", visible=False)
+        debug_display = gr.Markdown(visible=False)
+    
+    # Update the debug button click handler to show debug info in the sidebar
+    for i in range(0, len(section_components), 4):
+        debug_btn = section_components[i+3]  # The debug button is the 4th component
+        
+        # Re-connect debug button with proper click handling
+        debug_btn.click(
+            fn=format_debug_info,
+            inputs=[debug_info_state],
+            outputs=[debug_display]
+        ).then(
+            fn=lambda: (gr.update(visible=True), gr.update(visible=True)),
+            outputs=[debug_header, debug_display]
+        )
+    
 # Launch the app
 if __name__ == "__main__":
     demo.launch()

utils/llm_parser.py

@@ -6,7 +6,7 @@ def init_llm_client(api_key, base_url=None):
     """
     Initialize the OpenAI client with the provided API key and model ID.
     """
-    print("base_url", base_url)
+
     if base_url and len(base_url) > 0 and base_url.startswith("http"):
         os.environ["OPENAI_API_BASE"] = base_url
     else: