Upload folder using huggingface_hub

README.md

@@ -4,7 +4,7 @@ app_file: src/app.py
 sdk: gradio
 sdk_version: 5.13.1
 ---
-# 🎓 AI Script Generator
+# 🎓 AI Agent Script Builder
 
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/)
@@ -12,13 +12,31 @@ sdk_version: 5.13.1
 [![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](http://makeapullrequest.com)
 [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/rogeliorichman/AI_Script_Generator)
 
-> Transform transcripts and PDFs into timed, structured teaching scripts using AI
+> Transform transcripts and PDFs into timed, structured teaching scripts using an autonomous AI agent
 
-AI Script Generator is an advanced AI system that converts PDF transcripts, raw text, and conversational content into well-structured teaching scripts. It seamlessly processes inputs, extracting and analyzing the content to create organized, pedagogically sound scripts with time markers. Designed for educators, students, content creators, and anyone looking to transform information into clear explanations.
+AI Agent Script Builder is an advanced autonomous agent that converts PDF transcripts, raw text, and conversational content into well-structured teaching scripts. It seamlessly processes inputs, extracting and analyzing the content to create organized, pedagogically scripts with time markers. Designed for educators, students, content creators, and anyone looking to transform information into clear explanations.
+
+## 🤖 AI Agent Architecture
+
+AI Agent Script Builder functions as a **specialized AI agent** that autonomously processes and transforms content with minimal human intervention:
+
+### Agent Capabilities
+- **Autonomous Processing**: Independently analyzes content, determines structure, and generates complete scripts
+- **Decision Making**: Intelligently allocates time, prioritizes topics, and structures content based on input analysis
+- **Contextual Adaptation**: Adjusts to different languages, styles, and requirements through guiding prompts
+- **Obstacle Management**: Implements progressive retry strategies when facing API quota limitations
+- **Goal-Oriented Operation**: Consistently works toward transforming unstructured information into coherent educational scripts
+
+### Agent Limitations
+- **Domain Specificity**: Specialized for educational script generation rather than general-purpose tasks
+- **External API Dependency**: Relies on third-party language models (Gemini/OpenAI) for core reasoning
+- **No Continuous Learning**: Does not improve through experience or previous interactions
+
+This architecture enables the system to function autonomously within its specialized domain while maintaining high-quality output and resilience to common obstacles.
 
 ## 🔗 Live Demo
 
-Try it out: [AI Script Generator on Hugging Face Spaces](https://huggingface.co/spaces/rogeliorichman/AI_Script_Generator)
+Try it out: [AI Agent Script Builder on Hugging Face Spaces](https://huggingface.co/spaces/rogeliorichman/AI_Script_Generator)
 
 ## ✨ Features
 
@@ -30,6 +48,8 @@ Try it out: [AI Script Generator on Hugging Face Spaces](https://huggingface.co/
 - ⏱️ Time-marked sections for pacing
 - 🌐 Multilingual interface (English/Spanish) with flag selector
 - 🌍 Generation in ANY language through the guiding prompt (not limited to UI languages)
+- 🧠 Autonomous decision-making for content organization and pacing
+- 🛡️ Self-healing capabilities with progressive retry strategies for API limitations
 
 ## Output Format
 
@@ -189,12 +209,15 @@ Our system uses a sophisticated multi-stage prompting approach:
 
 ### Architecture
 
-The system follows a modular design:
+The system follows a modular agent-based design:
+
+- 📄 PDF/text processing module (Perception)
+- 🔍 Text analysis component (Cognition)
+- 🤖 AI integration layer (Decision-making)
+- 📝 Output formatting system (Action)
+- 🔄 Error handling system (Self-correction)
 
-- 📄 PDF/text processing module
-- 🔍 Text analysis component
-- 🤖 AI integration layer
-- 📝 Output formatting system
+This agent architecture enables autonomous processing from raw input to final output with built-in adaptation to errors and limitations.
 
 ## 🤝 Contributing
 
@@ -214,7 +237,6 @@ Distributed under the MIT License. See `LICENSE` for more information.
 
 ## 🌟 Acknowledgments
 
-- Thanks to all contributors who have helped shape AI Script Generator
 - Special thanks to the Gemini and OpenAI teams for their amazing APIs
 - Inspired by educators and communicators worldwide who make learning engaging
 

requirements.txt

@@ -1,4 +1,4 @@
-gradio>=4.0.0
+gradio==4.26.0
 transformers>=4.30.0
 torch>=2.0.0
 pypdf2>=3.0.0
@@ -6,4 +6,5 @@ python-dotenv>=0.19.0
 numpy>=1.21.0
 tqdm>=4.65.0
 openai>=1.0.0
-tiktoken>=0.5.0 
+tiktoken>=0.5.0
+fastapi<0.110.0 

src/app.py

@@ -1,12 +1,17 @@
 import os
 import gradio as gr
 import re
+import logging # Added for debugging
 from dotenv import load_dotenv
 from src.core.transformer import TranscriptTransformer
 from src.utils.pdf_processor import PDFProcessor
 from src.utils.text_processor import TextProcessor
 
+# Set up basic logging
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
+
 load_dotenv()
+logging.info("Environment variables loaded.")
 
 # Translations dictionary for UI elements
 TRANSLATIONS = {
@@ -66,12 +71,14 @@ LANGUAGE_PROMPTS = {
 
 class TranscriptTransformerApp:
     def __init__(self):
+        logging.info("Initializing TranscriptTransformerApp...")
         self.pdf_processor = PDFProcessor()
         self.text_processor = TextProcessor()
         self.current_language = "en"  # Default language
         self.last_generated_content = ""  # Store the last generated content
         self.content_with_timestamps = ""  # Store content with timestamps
         self.content_without_timestamps = ""  # Store content without timestamps
+        logging.info("TranscriptTransformerApp initialized.")
 
     def process_transcript(self, 
                            language: str,
@@ -100,9 +107,11 @@ class TranscriptTransformerApp:
         Returns:
             str: Generated teaching transcript
         """
+        logging.info(f"Processing transcript. Language: {language}, InputType: {input_type}, HasFile: {file_obj is not None}, HasText: {bool(raw_text_input)}, Duration: {target_duration}, Examples: {include_examples}, Gemini: {use_gemini}, ThinkingModel: {use_thinking_model}")
         try:
             # Force enable Gemini if thinking model is selected
             if use_thinking_model:
+                logging.info("Thinking model selected, forcing use_gemini=True")
                 use_gemini = True
                 
             self.transformer = TranscriptTransformer(
@@ -144,32 +153,43 @@ class TranscriptTransformerApp:
             
             # Store the generated content
             self.content_with_timestamps = lecture_transcript
+            logging.info("Generated content stored (with timestamps).")
             
             # Create a version without timestamps
             self.content_without_timestamps = self.remove_timestamps(lecture_transcript)
+            logging.info("Generated content stored (without timestamps).")
             
             # Default: show content with timestamps
             self.last_generated_content = lecture_transcript
             
+            logging.info("Transcript processing successful.")
             return lecture_transcript
             
         except Exception as e:
+            logging.error(f"Error processing transcript: {e}", exc_info=True) # Log exception info
             return f"{TRANSLATIONS[language]['error_prefix']}{str(e)}"
     
     def remove_timestamps(self, text):
         """Remove all timestamps (e.g., [00:00]) from the text"""
+        logging.info("Removing timestamps...")
         # Regex to match the timestamp pattern [MM:SS] or [HH:MM:SS]
-        return re.sub(r'\[\d{1,2}:\d{2}(:\d{2})?\]', '', text)
+        result = re.sub(r'\[\d{1,2}:\d{2}(:\d{2})?\]', '', text)
+        logging.info("Timestamps removed.")
+        return result
     
     def toggle_timestamps(self, show_timestamps):
         """Toggle visibility of timestamps in output"""
+        logging.info(f"Toggling timestamps visibility. Show: {show_timestamps}")
         if show_timestamps:
+            logging.info("Returning content WITH timestamps.")
             return self.content_with_timestamps
         else:
+            logging.info("Returning content WITHOUT timestamps.")
             return self.content_without_timestamps
     
     def update_ui_language(self, language):
         """Update UI elements based on selected language"""
+        logging.info(f"Updating UI language to: {language}")
         self.current_language = language
         
         translations = TRANSLATIONS[language]
@@ -191,11 +211,14 @@ class TranscriptTransformerApp:
             translations["submit_button"],
             translations["output_label"]
         ]
+        logging.info("UI language updated.")
 
     def launch(self):
         """Launch the Gradio interface"""
+        logging.info("Configuring Gradio interface...")
         # Get the path to the example PDF
         example_pdf = os.path.join(os.path.dirname(os.path.dirname(__file__)), "data", "sample2.pdf")
+        logging.info(f"Example PDF path: {example_pdf}")
         
         with gr.Blocks(title=TRANSLATIONS["en"]["title"]) as interface:
             # Header with title and language selector side by side
@@ -301,10 +324,14 @@ class TranscriptTransformerApp:
             
             # Get language code from display value
             def get_language_code(language_display):
-                return lang_map.get(language_display, "en")
+                logging.info(f"Getting language code for display value: {language_display}")
+                code = lang_map.get(language_display, "en")
+                logging.info(f"Language code: {code}")
+                return code
             
             # Update UI elements when language changes
             def update_ui_with_display(language_display):
+                logging.info(f"Update UI triggered for language: {language_display}")
                 language = get_language_code(language_display)
                 self.current_language = language
                 
@@ -325,6 +352,7 @@ class TranscriptTransformerApp:
                     gr.update(label=translations["output_label"]),
                     gr.update(label=translations["show_timestamps"])
                 ]
+                logging.info("UI elements update values prepared.")
             
             input_type.change(
                 fn=lambda lang_display, choice: update_input_visibility(lang_display, choice),
@@ -371,13 +399,21 @@ class TranscriptTransformerApp:
             )
             
             # Example for PDF input
+            logging.info("Setting up Gradio Examples...")
             gr.Examples(
                 examples=[[example_pdf, "", "", 30, True, True]],
                 inputs=[file_input, text_input, initial_prompt, target_duration, include_examples, use_thinking_model]
             )
+            logging.info("Gradio Examples configured.")
         
+        logging.info("Launching Gradio interface...")
+        # Note: Setting share=True is not recommended/supported in Spaces, but kept for consistency with original code
+        # It might generate a warning, which is expected.
         interface.launch(share=True)
+        logging.info("Gradio interface launched.")
 
 if __name__ == "__main__":
+    logging.info("Starting application...")
     app = TranscriptTransformerApp()
-    app.launch() 
+    app.launch()
+    logging.info("Application finished.")