Update app.py

app.py

@@ -4,7 +4,7 @@ import glob
 import re
 import pandas as pd
 import gradio as gr
-import spaces  # <--- REQUIRED FOR HUGGING FACE ZEROGPU TIERS
+import spaces 
 from pypdf import PdfReader
 import docx2txt
 import speech_recognition as sr
@@ -22,7 +22,7 @@ os.makedirs(PROCESSED_DIR, exist_ok=True)
 # -------------------------------------------------------------
 # CORE PIPELINE LOGIC (TRANSCRIBER, PARSER, CHUNKER)
 # -------------------------------------------------------------
-@spaces.GPU  # <--- TELLS HUGGING FACE TO ALLOCATE GPU POWER FOR TRANSCRIBING
+@spaces.GPU 
 def transcribe_video_audio(file_path):
     try:
         gr.Info(f"🎬 Extracting track layers from {os.path.basename(file_path)}...")
@@ -50,9 +50,56 @@ def clean_text_formatting(text):
         text = text.replace("  ", " ")
     return text.strip()
 
+# 🔥 NEW: ADVANCED FINANCIAL CSV PARSER & TIMESTAMP INJECTOR 🔥
+def process_financial_csv(df, file_name=""):
+    """Detects financial data, sorts chronologically, auto-injects missing timestamps, and translates to NLP sentences."""
+    
+    # 1. Detect and establish the time column
+    time_col = None
+    for col in df.columns:
+        if str(col).lower() in ['date', 'time', 'timestamp', 'datetime', 'timeframe']:
+            time_col = col
+            break
+            
+    if time_col:
+        # Sort existing timestamps chronologically
+        df[time_col] = pd.to_datetime(df[time_col], errors='coerce')
+        df = df.dropna(subset=[time_col]).sort_values(by=time_col)
+    else:
+        # Auto-Inject missing timestamps to establish sequence logic
+        gr.Info(f"⏱️ No timestamp found in {file_name}. Auto-generating chronological sequence...")
+        # (Note: The 1-minute timeframe interval is used here purely as a default structural baseline)
+        df['Generated_Timestamp'] = pd.date_range(start=pd.Timestamp.now().floor('D'), periods=len(df), freq='1min')
+        time_col = 'Generated_Timestamp'
+        
+    # 2. Detect if the file is financial/quantitative data
+    is_financial = any(str(c).lower() in ['open', 'close', 'high', 'low', 'volume', 'vwap', 'rvol'] for c in df.columns)
+    
+    text_output = []
+    
+    if is_financial:
+        gr.Info(f"💹 Financial dataset detected ({file_name}). Translating rows into optimized LLM sentences...")
+        for _, row in df.iterrows():
+            row_time = row[time_col]
+            # Strip the time column out of the details list so it isn't repeated
+            details = [f"{col}: {row[col]}" for col in df.columns if col != time_col]
+            # Construct the predictive NLP sentence
+            sentence = f"Market Data at {row_time} -> " + ", ".join(details) + "."
+            text_output.append(sentence)
+    else:
+        # Standard fallback for non-financial CSV files (e.g., Q&A sheets)
+        for _, row in df.iterrows():
+            details = [f"{col}: {row[col]}" for col in df.columns]
+            text_output.append(" | ".join(details))
+            
+    # Return the data as a massive, chronological string ready for the sentence chunker
+    return "\n".join(text_output)
+
 def parse_incoming_file_to_text(file_path):
     ext = os.path.splitext(file_path)[1].lower()
+    base_name = os.path.basename(file_path)
     text = ""
+    
     if ext == ".txt":
         with open(file_path, "r", encoding="utf-8") as f:
             text = f.read()
@@ -64,8 +111,9 @@ def parse_incoming_file_to_text(file_path):
     elif ext == ".docx":
         text = docx2txt.process(file_path)
     elif ext in [".csv", ".xlsx"]:
+        # Pass dataframes directly into the new translation engine
         df = pd.read_csv(file_path) if ext == ".csv" else pd.read_excel(file_path)
-        text = df.to_string(index=False)
+        text = process_financial_csv(df, base_name)
     elif ext in [".mp4", ".wav", ".mp3"]:
         text = transcribe_video_audio(file_path)
         
@@ -88,10 +136,10 @@ def structure_unsloth_rows(chunks, archetype):
         elif "🧮 Math Wizard" in archetype or "📈 Day Trading" in archetype:
             instr = "Deconstruct structural math patterns or trading indicator calculations."
             if "📈 Day Trading" in archetype:
-                instr = "Parse market metrics and technical data to extract signals."
+                instr = "Analyze the chronological sequence of market data parameters to establish structural setup context."
             rows.append({
                 "instruction": instr,
-                "input": f"Data segment context: {idx}",
+                "input": f"Market Narrative Segment {idx}:",
                 "output": chunk
             })
         elif "💻 Code Assistant" in archetype:
@@ -104,10 +152,10 @@ def structure_unsloth_rows(chunks, archetype):
             rows.append({"text": chunk})
     return rows
 
-@spaces.GPU  # <--- DECORATES THE TOP LEVEL CONVERSION Pipeline FOR ZEROGPU STABILITY
+@spaces.GPU  
 def execute_dataset_builder_pipeline(files, archetype, enable_chunking, chunk_size, chunk_overlap):
     if not files:
-        return "⚠️ Target file loading queue is empty. Please upload files."
+        return "⚠️ Target file loading queue is empty. Please upload files.", None
         
     for f in glob.glob(os.path.join(PROCESSED_DIR, "*.jsonl")):
         os.remove(f)
@@ -122,7 +170,7 @@ def execute_dataset_builder_pipeline(files, archetype, enable_chunking, chunk_si
             total_files_compiled += 1
             
     if not all_extracted_text_blocks:
-        return "❌ Failed to extract content from assets."
+        return "❌ Failed to extract content from assets.", None
         
     combined_master_string = "\n\n--- FILE SPLIT ---\n\n".join(all_extracted_text_blocks)
     
@@ -138,7 +186,9 @@ def execute_dataset_builder_pipeline(files, archetype, enable_chunking, chunk_si
         for obj in formatted_dataset_objects:
             master_f.write(json.dumps(obj) + "\n")
             
-    return f"🔥 Conversion Complete!\n\n• Processed: {total_files_compiled}/{len(files)} files\n• Rows: {len(formatted_dataset_objects)}\n• Saved At: {MASTER_FILE}"
+    success_log = f"🔥 Conversion Complete!\n\n• Processed: {total_files_compiled}/{len(files)} files\n• Rows Generated: {len(formatted_dataset_objects)}\n• Saved At: {MASTER_FILE}"
+    
+    return success_log, MASTER_FILE
 
 # -------------------------------------------------------------
 # THEME TOGGLE SWITCH LOGIC ☀️/🌙
@@ -175,7 +225,6 @@ custom_theme = gr.themes.Default(
     neutral_hue="zinc"
 )
 
-# Removed theme and title parameters from constructor to prevent Gradio 6 layout deprecation warnings
 with gr.Blocks() as demo:
     ui_theme_state = gr.State("dark")
     
@@ -187,7 +236,7 @@ with gr.Blocks() as demo:
     
     with gr.Row():
         with gr.Column(scale=1):
-            file_uploader = gr.File(file_count="multiple", label="📥 Drop Assets Here (.pdf, .txt, .docx, .mp4)")
+            file_uploader = gr.File(file_count="multiple", label="📥 Drop Assets Here (.pdf, .txt, .docx, .mp4, .csv)")
             archetype_dropdown = gr.Dropdown(choices=archetype_choices, value=archetype_choices[0], label="🤖 Choose Target AI Archetype Layout Mapping")
             
             with gr.Accordion("✂️ Text Chunking Control Panel", open=True):
@@ -198,12 +247,13 @@ with gr.Blocks() as demo:
             run_btn = gr.Button("🚀 Run Conversion & Combine Files", variant="primary")
             
         with gr.Column(scale=1):
-            log_monitor = gr.Textbox(label="🖥️ Core Engine Pipeline Logs", lines=15)
+            log_monitor = gr.Textbox(label="🖥️ Core Engine Pipeline Logs", lines=12)
+            download_btn = gr.DownloadButton("💾 Download Compiled Dataset (.jsonl)", variant="primary")
             
     run_btn.click(
         fn=execute_dataset_builder_pipeline,
         inputs=[file_uploader, archetype_dropdown, chunk_toggle, size_input, overlap_input],
-        outputs=log_monitor
+        outputs=[log_monitor, download_btn]
     )
     
     theme_toggle_btn.click(
@@ -219,5 +269,4 @@ with gr.Blocks() as demo:
     demo.load(fn=lambda: "dark", outputs=ui_theme_state).then(fn=None, inputs=[ui_theme_state], js=js_theme_switcher)
 
 if __name__ == "__main__":
-    # Theme configuration parameters passed to launch method matching Gradio 6 guidelines
     demo.launch(theme=custom_theme)