Update app.py

app.py

@@ -1,32 +1,36 @@
-from fine_tuning import fine_tune_model  # Import the function from fine_tuning.py
+import gradio as gr
+from text_analysis import generate_lesson_from_transcript as generate_lesson_from_transcript_logic
+from utils import process_large_text
+from pdfminer.high_level import extract_text  # Import PDF-to-text conversion
 
-def clean_text_with_spacy(text):
-    # Clean the text using spaCy
-    doc = nlp(text)
-    tokens = [token.lemma_.lower() for token in doc if not token.is_stop and not token.is_punct]
-    return " ".join(tokens)
+def pdf_to_text(pdf_path):
+    """ Converts PDF to text """
+    return extract_text(pdf_path)
 
-# Function to read prompts.txt file
-def read_prompts(file_path):
-    input_texts = []
-    target_texts = []
-    with open(file_path, "r", encoding="utf-8") as file:
-        lines = file.readlines()
-        for line in lines:
-            if line.startswith("input:"):
-                input_texts.append(line.replace("input:", "").strip())
-            elif line.startswith("target:"):
-                target_texts.append(line.replace("target:", "").strip())
-    return input_texts, target_texts
+def generate_lesson(doc_text=None, pdf_file=None):
+    """
+    Generate lesson from transcript text or PDF input.
+    """
+    try:
+        if pdf_file:
+            doc_text = pdf_to_text(pdf_file.name)
+        
+        # Process large text
+        processed_text = process_large_text(doc_text)
 
-# Function to process input texts for fine-tuning
-def process_input_for_fine_tuning(input_texts, target_texts):
-    cleaned_input_texts = [clean_text_with_spacy(text) for text in input_texts]
-    cleaned_target_texts = [clean_text_with_spacy(text) for text in target_texts]
-    fine_tune_model(cleaned_input_texts, cleaned_target_texts)
+        # Generate lesson
+        generated_text, output_path = generate_lesson_from_transcript_logic(processed_text)
 
-# Reading data from prompts.txt
-input_texts, target_texts = read_prompts("prompts.txt")
+        if output_path:
+            return generated_text, gr.File(output_path)
+        else:
+            return generated_text, None
 
-# Initiating the fine-tuning process
-process_input_for_fine_tuning(input_texts, target_texts)
+    except Exception as e:
+        return f"Error occurred: {str(e)}", None
+
+gr.Interface(
+    fn=generate_lesson,
+    inputs=[gr.Textbox(label="Input Text"), gr.File(label="Upload PDF")],
+    outputs=["text", "file"],
+).launch()