Removing chat with document feature

README.md

@@ -137,13 +137,6 @@ build:
 6. Navigate through pages using the navigation buttons for multi-page documents
 7. Download the converted content in your selected format
 
-### Document Chat
-1. After converting a document, switch to the "Chat with Document" tab
-2. Type your questions about the document content
-3. The AI will analyze the document and provide context-aware responses
-4. Use the conversation history to track your Q&A session
-5. Click "Clear" to start a new conversation
-
 ## Troubleshooting
 
 ### OCR Issues
@@ -201,20 +194,7 @@ markit/
 │   │   ├── __init__.py     # Package initialization
 │   │   └── ui.py           # Gradio UI implementation
 │   └── services/           # External services
-│       ├── __init__.py     # Package initialization
-│       └── docling_chat.py # Chat service
+│       └── __init__.py     # Package initialization
 └── tests/                  # Tests
     └── __init__.py         # Package initialization
-```
-
-### Adding a New Parser
-1. Create a new parser class implementing the `DocumentParser` interface
-2. Register the parser with the `ParserRegistry`
-3. Implement the required methods: `get_name()`, `get_supported_ocr_methods()`, and `parse()`
-4. Add your parser to the imports in `src/parsers/__init__.py`
-
-## Contributing
-Contributions are welcome! Please feel free to submit a Pull Request.
-
-## License
-This project is open source and available under the MIT License.
+```

requirements.txt

@@ -4,7 +4,6 @@ grpcio-status==1.70.0
 markdown==3.7
 marker-pdf==1.3.5
 multiprocess==0.70.16
-openai==1.61.1
 pipdeptree==2.25.0
 pytesseract==0.3.13
 semchunk==2.2.2

src/services/docling_chat.py

@@ -1,29 +0,0 @@
-import openai
-import os
-
-# Load API key from environment variable
-openai.api_key = os.getenv("OPENAI_API_KEY")
-
-# Check if API key is available and print a message if not
-if not openai.api_key:
-    print("Warning: OPENAI_API_KEY environment variable not found. Chat functionality may not work.")
-
-def chat_with_document(message, history, document_text_state):
-    history = history or []
-    history.append({"role": "user", "content": message})
-
-    context = f"Document: {document_text_state}\n\nUser: {message}"
-
-    # Add error handling for API calls
-    try:
-        response = openai.chat.completions.create(
-            model="gpt-4o-2024-08-06",
-            messages=[{"role": "system", "content": context}] + history
-        )
-        reply = response.choices[0].message.content
-    except Exception as e:
-        reply = f"Error: Could not generate response. Please check your OpenAI API key. Details: {str(e)}"
-        print(f"OpenAI API error: {str(e)}")
-    
-    history.append({"role": "assistant", "content": reply})
-    return history, history

src/ui/ui.py

@@ -5,7 +5,6 @@ import time
 import logging
 from pathlib import Path
 from src.core.converter import convert_file, set_cancellation_flag, is_conversion_in_progress
-from src.services.docling_chat import chat_with_document
 from src.parsers.parser_registry import ParserRegistry
 
 # Configure logging
@@ -169,52 +168,44 @@ def create_ui():
         # State to store the output format (fixed to Markdown)
         output_format_state = gr.State("Markdown")
 
-        with gr.Tabs():
-            with gr.Tab("Upload and Convert"):
-                # File input first
-                file_input = gr.File(label="Upload PDF", type="filepath")
-                
-                # Provider and OCR options below the file input
-                with gr.Row(elem_classes=["provider-options-row"]):
-                    with gr.Column(scale=1):
-                        parser_names = ParserRegistry.get_parser_names()
-                        default_parser = parser_names[0] if parser_names else "PyPdfium"
-                        
-                        provider_dropdown = gr.Dropdown(
-                            label="Provider",
-                            choices=parser_names,
-                            value=default_parser,
-                            interactive=True
-                        )
-                    with gr.Column(scale=1):
-                        default_ocr_options = ParserRegistry.get_ocr_options(default_parser)
-                        default_ocr = default_ocr_options[0] if default_ocr_options else "No OCR"
-                        
-                        ocr_dropdown = gr.Dropdown(
-                            label="OCR Options",
-                            choices=default_ocr_options,
-                            value=default_ocr,
-                            interactive=True
-                        )
+        # File input first
+        file_input = gr.File(label="Upload PDF", type="filepath")
+        
+        # Provider and OCR options below the file input
+        with gr.Row(elem_classes=["provider-options-row"]):
+            with gr.Column(scale=1):
+                parser_names = ParserRegistry.get_parser_names()
+                default_parser = parser_names[0] if parser_names else "PyPdfium"
                 
-                # Simple output container with just one scrollbar
-                file_display = gr.HTML(
-                    value="<div class='output-container'></div>",
-                    label="Converted Content"
+                provider_dropdown = gr.Dropdown(
+                    label="Provider",
+                    choices=parser_names,
+                    value=default_parser,
+                    interactive=True
                 )
+            with gr.Column(scale=1):
+                default_ocr_options = ParserRegistry.get_ocr_options(default_parser)
+                default_ocr = default_ocr_options[0] if default_ocr_options else "No OCR"
                 
-                file_download = gr.File(label="Download File")
-                
-                # Processing controls row
-                with gr.Row(elem_classes=["processing-controls"]):
-                    convert_button = gr.Button("Convert", variant="primary")
-                    cancel_button = gr.Button("Cancel", variant="stop", visible=False)
-
-            with gr.Tab("Chat with Document"):
-                document_text_state = gr.State("")
-                chatbot = gr.Chatbot(label="Chat", type="messages")
-                text_input = gr.Textbox(placeholder="Type here...")
-                clear_btn = gr.Button("Clear")
+                ocr_dropdown = gr.Dropdown(
+                    label="OCR Options",
+                    choices=default_ocr_options,
+                    value=default_ocr,
+                    interactive=True
+                )
+        
+        # Simple output container with just one scrollbar
+        file_display = gr.HTML(
+            value="<div class='output-container'></div>",
+            label="Converted Content"
+        )
+        
+        file_download = gr.File(label="Download File")
+        
+        # Processing controls row
+        with gr.Row(elem_classes=["processing-controls"]):
+            convert_button = gr.Button("Convert", variant="primary")
+            cancel_button = gr.Button("Cancel", variant="stop", visible=False)
 
         # Event handlers
         provider_dropdown.change(
@@ -269,24 +260,6 @@ def create_ui():
             queue=False  # Execute immediately
         )
 
-        file_display.change(
-            lambda text: text,
-            inputs=[file_display],
-            outputs=[document_text_state]
-        )
-
-        text_input.submit(
-            fn=chat_with_document,
-            inputs=[text_input, chatbot, document_text_state],
-            outputs=[chatbot, chatbot]
-        )
-
-        clear_btn.click(
-            lambda: ([], []),
-            None,
-            [chatbot, chatbot]
-        )
-
     return demo