Update app.py

app.py

@@ -4,41 +4,40 @@ import glob
 import base64
 import time
 import shutil
+import zipfile
+import re
+import logging
+import asyncio
+from io import BytesIO
+from datetime import datetime
+import pytz
+from dataclasses import dataclass
+from typing import Optional
+
 import streamlit as st
 import pandas as pd
 import torch
-import torch.nn as nn
-import torch.nn.functional as F
-from transformers import AutoModelForCausalLM, AutoTokenizer, AutoModel
-from diffusers import StableDiffusionPipeline
-from torch.utils.data import Dataset, DataLoader
-import csv
 import fitz
 import requests
 from PIL import Image
-import cv2
-import numpy as np
-import logging
-import asyncio
-import aiofiles
-from io import BytesIO
-from dataclasses import dataclass
-from typing import Optional, Tuple
-import zipfile
-import math
-import random
-import re
+from diffusers import StableDiffusionPipeline
+from transformers import AutoModelForCausalLM, AutoTokenizer, AutoModel
+
+# --- OpenAI Setup (for GPT related features) ---
+import openai
+openai.api_key = os.getenv('OPENAI_API_KEY')
+openai.organization = os.getenv('OPENAI_ORG_ID')
 
+# --- Logging ---
 logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
 logger = logging.getLogger(__name__)
 log_records = []
-
 class LogCaptureHandler(logging.Handler):
     def emit(self, record):
         log_records.append(record)
-
 logger.addHandler(LogCaptureHandler())
 
+# --- Streamlit Page Config ---
 st.set_page_config(
     page_title="AI Vision & SFT Titans 🚀",
     page_icon="🤖",
@@ -51,6 +50,7 @@ st.set_page_config(
     }
 )
 
+# --- Session State Defaults ---
 if 'history' not in st.session_state:
     st.session_state['history'] = []
 if 'builder' not in st.session_state:
@@ -74,6 +74,7 @@ if 'cam0_file' not in st.session_state:
 if 'cam1_file' not in st.session_state:
     st.session_state['cam1_file'] = None
 
+# --- Model & Diffusion DataClasses ---
 @dataclass
 class ModelConfig:
     name: str
@@ -95,12 +96,14 @@ class DiffusionConfig:
     def model_path(self):
         return f"diffusion_models/{self.name}"
 
+# --- Model Builders ---
 class ModelBuilder:
     def __init__(self):
         self.config = None
         self.model = None
         self.tokenizer = None
-        self.jokes = ["Why did the AI go to therapy? Too many layers to unpack! 😂", "Training complete! Time for a binary coffee break. ☕"]
+        self.jokes = ["Why did the AI go to therapy? Too many layers to unpack! 😂",
+                      "Training complete! Time for a binary coffee break. ☕"]
     def load_model(self, model_path: str, config: Optional[ModelConfig] = None):
         with st.spinner(f"Loading {model_path}... ⏳"):
             self.model = AutoModelForCausalLM.from_pretrained(model_path)
@@ -128,7 +131,7 @@ class DiffusionBuilder:
             self.pipeline = StableDiffusionPipeline.from_pretrained(model_path, torch_dtype=torch.float32).to("cpu")
             if config:
                 self.config = config
-        st.success(f"Diffusion model loaded! 🎨")
+        st.success("Diffusion model loaded! 🎨")
         return self
     def save_model(self, path: str):
         with st.spinner("Saving diffusion model... 💾"):
@@ -138,6 +141,7 @@ class DiffusionBuilder:
     def generate(self, prompt: str):
         return self.pipeline(prompt, num_inference_steps=20).images[0]
 
+# --- Utility Functions ---
 def generate_filename(sequence, ext="png"):
     timestamp = time.strftime("%d%m%Y%H%M%S")
     return f"{sequence}_{timestamp}.{ext}"
@@ -181,6 +185,7 @@ def download_pdf(url, output_path):
         logger.error(f"Failed to download {url}: {e}")
     return False
 
+# --- Original PDF Snapshot & OCR Functions ---
 async def process_pdf_snapshot(pdf_path, mode="single"):
     start_time = time.time()
     status = st.empty()
@@ -223,11 +228,10 @@ async def process_ocr(image, output_file):
     status.text("Processing GOT-OCR2_0... (0s)")
     tokenizer = AutoTokenizer.from_pretrained("ucaslcl/GOT-OCR2_0", trust_remote_code=True)
     model = AutoModel.from_pretrained("ucaslcl/GOT-OCR2_0", trust_remote_code=True, torch_dtype=torch.float32).to("cpu").eval()
-    # Save image to temporary file since GOT-OCR2_0 expects a file path
     temp_file = f"temp_{int(time.time())}.png"
     image.save(temp_file)
     result = model.chat(tokenizer, temp_file, ocr_type='ocr')
-    os.remove(temp_file)  # Clean up temporary file
+    os.remove(temp_file)
     elapsed = int(time.time() - start_time)
     status.text(f"GOT-OCR2_0 completed in {elapsed}s!")
     async with aiofiles.open(output_file, "w") as f:
@@ -250,49 +254,31 @@ async def process_image_gen(prompt, output_file):
     update_gallery()
     return gen_image
 
-st.title("AI Vision & SFT Titans 🚀")
-
-# Sidebar
-model_type = st.sidebar.selectbox("Model Type", ["Causal LM", "Diffusion"], key="sidebar_model_type", index=0 if st.session_state['selected_model_type'] == "Causal LM" else 1)
-model_dirs = get_model_files(model_type)
-if model_dirs and st.session_state['selected_model'] == "None" and "None" not in model_dirs:
-    st.session_state['selected_model'] = model_dirs[0]
-selected_model = st.sidebar.selectbox("Select Saved Model", model_dirs, key="sidebar_model_select", index=model_dirs.index(st.session_state['selected_model']) if st.session_state['selected_model'] in model_dirs else 0)
-if selected_model != "None" and st.sidebar.button("Load Model 📂"):
-    builder = ModelBuilder() if model_type == "Causal LM" else DiffusionBuilder()
-    config = (ModelConfig if model_type == "Causal LM" else DiffusionConfig)(name=os.path.basename(selected_model), base_model="unknown", size="small")
-    builder.load_model(selected_model, config)
-    st.session_state['builder'] = builder
-    st.session_state['model_loaded'] = True
-    st.rerun()
-
-st.sidebar.header("Captured Files 📜")
-cols = st.sidebar.columns(2)
-with cols[0]:
-    if st.button("Zip All 🤐"):
-        zip_path = f"all_assets_{int(time.time())}.zip"
-        with zipfile.ZipFile(zip_path, 'w', zipfile.ZIP_DEFLATED) as zipf:
-            for file in get_gallery_files():
-                zipf.write(file, os.path.basename(file))
-        st.sidebar.markdown(get_download_link(zip_path, "application/zip", "Download All Assets"), unsafe_allow_html=True)
-with cols[1]:
-    if st.button("Zap All! 🗑️"):
-        for file in get_gallery_files():
-            os.remove(file)
-        st.session_state['asset_checkboxes'].clear()
-        st.session_state['downloaded_pdfs'].clear()
-        st.session_state['cam0_file'] = None
-        st.session_state['cam1_file'] = None
-        st.sidebar.success("All assets vaporized! 💨")
-        st.rerun()
-
-gallery_size = st.sidebar.slider("Gallery Size", 1, 10, 2)
+# --- New Function: Process an image (PIL) with a custom prompt using GPT ---
+def process_image_with_prompt(image, prompt, model="o3-mini-high"):
+    buffered = BytesIO()
+    image.save(buffered, format="PNG")
+    img_str = base64.b64encode(buffered.getvalue()).decode("utf-8")
+    messages = [{
+        "role": "user",
+        "content": [
+            {"type": "text", "text": prompt},
+            {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{img_str}"}}
+        ]
+    }]
+    try:
+        response = openai.ChatCompletion.create(model=model, messages=messages)
+        return response.choices[0].message.content
+    except Exception as e:
+        return f"Error processing image with GPT: {str(e)}"
+
+# --- Gallery Update ---
 def update_gallery():
     all_files = get_gallery_files()
     if all_files:
         st.sidebar.subheader("Asset Gallery 📸📖")
         cols = st.sidebar.columns(2)
-        for idx, file in enumerate(all_files[:gallery_size * 2]):
+        for idx, file in enumerate(all_files[:st.sidebar.slider("Gallery Size", 1, 10, 2)]):
             with cols[idx % 2]:
                 st.session_state['unique_counter'] += 1
                 unique_id = st.session_state['unique_counter']
@@ -305,46 +291,41 @@ def update_gallery():
                     st.image(img, caption=os.path.basename(file), use_container_width=True)
                     doc.close()
                 checkbox_key = f"asset_{file}_{unique_id}"
-                st.session_state['asset_checkboxes'][file] = st.checkbox(
-                    "Use for SFT/Input", 
-                    value=st.session_state['asset_checkboxes'].get(file, False), 
-                    key=checkbox_key
-                )
+                st.session_state['asset_checkboxes'][file] = st.checkbox("Use for SFT/Input", value=st.session_state['asset_checkboxes'].get(file, False), key=checkbox_key)
                 mime_type = "image/png" if file.endswith('.png') else "application/pdf"
                 st.markdown(get_download_link(file, mime_type, "Snag It! 📥"), unsafe_allow_html=True)
                 if st.button("Zap It! 🗑️", key=f"delete_{file}_{unique_id}"):
                     os.remove(file)
-                    if file in st.session_state['asset_checkboxes']:
-                        del st.session_state['asset_checkboxes'][file]
-                    if file.endswith('.pdf'):
-                        url_key = next((k for k, v in st.session_state['downloaded_pdfs'].items() if v == file), None)
-                        if url_key:
-                            del st.session_state['downloaded_pdfs'][url_key]
-                    if file == st.session_state['cam0_file']:
-                        st.session_state['cam0_file'] = None
-                    if file == st.session_state['cam1_file']:
-                        st.session_state['cam1_file'] = None
+                    st.session_state['asset_checkboxes'].pop(file, None)
                     st.sidebar.success(f"Asset {os.path.basename(file)} vaporized! 💨")
-                    st.rerun()
+                    st.experimental_rerun()
 update_gallery()
 
+# --- Sidebar Logs & History ---
 st.sidebar.subheader("Action Logs 📜")
-log_container = st.sidebar.empty()
-with log_container:
+with st.sidebar:
     for record in log_records:
         st.write(f"{record.asctime} - {record.levelname} - {record.message}")
-
 st.sidebar.subheader("History 📜")
-history_container = st.sidebar.empty()
-with history_container:
-    for entry in st.session_state['history'][-gallery_size * 2:]:
+with st.sidebar:
+    for entry in st.session_state['history']:
         st.write(entry)
 
-tab1, tab2, tab3, tab4 = st.tabs([
-    "Camera Snap 📷", "Download PDFs 📥", "Test OCR 🔍", "Build Titan 🌱"
+# --- Create Tabs (Existing + New) ---
+tabs = st.tabs([
+    "Camera Snap 📷",
+    "Download PDFs 📥",
+    "Test OCR 🔍",
+    "Build Titan 🌱",
+    "Test Image Gen 🎨",
+    "PDF Process 📄",
+    "Image Process 🖼️",
+    "MD Gallery 📚"
 ])
+(tab_camera, tab_download, tab_ocr, tab_build, tab_imggen, tab_pdf_process, tab_image_process, tab_md_gallery) = tabs
 
-with tab1:
+# === Tab: Camera Snap (existing) ===
+with tab_camera:
     st.header("Camera Snap 📷")
     st.subheader("Single Capture")
     cols = st.columns(2)
@@ -363,8 +344,6 @@ with tab1:
             st.image(Image.open(filename), caption="Camera 0", use_container_width=True)
             logger.info(f"Saved snapshot from Camera 0: {filename}")
             update_gallery()
-        elif st.session_state['cam0_file'] and os.path.exists(st.session_state['cam0_file']):
-            st.image(Image.open(st.session_state['cam0_file']), caption="Camera 0", use_container_width=True)
     with cols[1]:
         cam1_img = st.camera_input("Take a picture - Cam 1", key="cam1")
         if cam1_img:
@@ -380,10 +359,9 @@ with tab1:
             st.image(Image.open(filename), caption="Camera 1", use_container_width=True)
             logger.info(f"Saved snapshot from Camera 1: {filename}")
             update_gallery()
-        elif st.session_state['cam1_file'] and os.path.exists(st.session_state['cam1_file']):
-            st.image(Image.open(st.session_state['cam1_file']), caption="Camera 1", use_container_width=True)
 
-with tab2:
+# === Tab: Download PDFs (existing) ===
+with tab_download:
     st.header("Download PDFs 📥")
     if st.button("Examples 📚"):
         example_urls = [
@@ -420,7 +398,7 @@ with tab2:
                         entry = f"Downloaded PDF: {output_path}"
                         if entry not in st.session_state['history']:
                             st.session_state['history'].append(entry)
-                        st.session_state['asset_checkboxes'][output_path] = True  # Auto-check the box
+                        st.session_state['asset_checkboxes'][output_path] = True
                     else:
                         st.error(f"Failed to nab {url} 😿")
                 else:
@@ -429,7 +407,6 @@ with tab2:
                 progress_bar.progress((idx + 1) / total_urls)
         status_text.text("Robo-Download complete! 🚀")
         update_gallery()
-
     mode = st.selectbox("Snapshot Mode", ["Single Page (High-Res)", "Two Pages (High-Res)", "All Pages (High-Res)"], key="download_mode")
     if st.button("Snapshot Selected 📸"):
         selected_pdfs = [path for path in get_gallery_files() if path.endswith('.pdf') and st.session_state['asset_checkboxes'].get(path, False)]
@@ -439,12 +416,13 @@ with tab2:
                 snapshots = asyncio.run(process_pdf_snapshot(pdf_path, mode_key))
                 for snapshot in snapshots:
                     st.image(Image.open(snapshot), caption=snapshot, use_container_width=True)
-                    st.session_state['asset_checkboxes'][snapshot] = True  # Auto-check new snapshots
+                    st.session_state['asset_checkboxes'][snapshot] = True
             update_gallery()
         else:
-            st.warning("No PDFs selected for snapshotting! Check some boxes in the sidebar gallery.")
+            st.warning("No PDFs selected for snapshotting! Check some boxes in the sidebar.")
 
-with tab3:
+# === Tab: Test OCR (existing) ===
+with tab_ocr:
     st.header("Test OCR 🔍")
     all_files = get_gallery_files()
     if all_files:
@@ -509,7 +487,8 @@ with tab3:
     else:
         st.warning("No assets in gallery yet. Use Camera Snap or Download PDFs!")
 
-with tab4:
+# === Tab: Build Titan (existing) ===
+with tab_build:
     st.header("Build Titan 🌱")
     model_type = st.selectbox("Model Type", ["Causal LM", "Diffusion"], key="build_type")
     base_model = st.selectbox("Select Tiny Model", 
@@ -530,10 +509,10 @@ with tab4:
         if entry not in st.session_state['history']:
             st.session_state['history'].append(entry)
         st.success(f"Model downloaded and saved to {config.model_path}! 🎉")
-        st.rerun()
+        st.experimental_rerun()
 
-tab5 = st.tabs(["Test Image Gen 🎨"])[0]
-with tab5:
+# === Tab: Test Image Gen (existing) ===
+with tab_imggen:
     st.header("Test Image Gen 🎨")
     all_files = get_gallery_files()
     if all_files:
@@ -560,5 +539,140 @@ with tab5:
                 st.session_state['processing']['gen'] = False
     else:
         st.warning("No images or PDFs in gallery yet. Use Camera Snap or Download PDFs!")
+    update_gallery()
 
-update_gallery()
+# === New Tab: PDF Process ===
+with tab_pdf_process:
+    st.header("PDF Process")
+    st.subheader("Upload PDFs for GPT-based text extraction")
+    uploaded_pdfs = st.file_uploader("Upload PDF files", type=["pdf"], accept_multiple_files=True, key="pdf_process_uploader")
+    view_mode = st.selectbox("View Mode", ["Single Page", "Double Page"], key="pdf_view_mode")
+    if st.button("Process Uploaded PDFs", key="process_pdfs"):
+        combined_text = ""
+        for pdf_file in uploaded_pdfs:
+            pdf_bytes = pdf_file.read()
+            temp_pdf_path = f"temp_{pdf_file.name}"
+            with open(temp_pdf_path, "wb") as f:
+                f.write(pdf_bytes)
+            try:
+                doc = fitz.open(temp_pdf_path)
+                st.write(f"Processing {pdf_file.name} with {len(doc)} pages")
+                if view_mode == "Single Page":
+                    for i, page in enumerate(doc):
+                        pix = page.get_pixmap(matrix=fitz.Matrix(2.0, 2.0))
+                        img = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
+                        st.image(img, caption=f"{pdf_file.name} Page {i+1}")
+                        gpt_text = process_image_with_prompt(img, "Extract the electronic text from image")
+                        combined_text += f"\n## {pdf_file.name} - Page {i+1}\n\n{gpt_text}\n"
+                else:  # Double Page: combine two consecutive pages
+                    pages = list(doc)
+                    for i in range(0, len(pages), 2):
+                        if i+1 < len(pages):
+                            pix1 = pages[i].get_pixmap(matrix=fitz.Matrix(2.0, 2.0))
+                            img1 = Image.frombytes("RGB", [pix1.width, pix1.height], pix1.samples)
+                            pix2 = pages[i+1].get_pixmap(matrix=fitz.Matrix(2.0, 2.0))
+                            img2 = Image.frombytes("RGB", [pix2.width, pix2.height], pix2.samples)
+                            total_width = img1.width + img2.width
+                            max_height = max(img1.height, img2.height)
+                            combined_img = Image.new("RGB", (total_width, max_height))
+                            combined_img.paste(img1, (0, 0))
+                            combined_img.paste(img2, (img1.width, 0))
+                            st.image(combined_img, caption=f"{pdf_file.name} Pages {i+1}-{i+2}")
+                            gpt_text = process_image_with_prompt(combined_img, "Extract the electronic text from image")
+                            combined_text += f"\n## {pdf_file.name} - Pages {i+1}-{i+2}\n\n{gpt_text}\n"
+                        else:
+                            pix = pages[i].get_pixmap(matrix=fitz.Matrix(2.0, 2.0))
+                            img = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
+                            st.image(img, caption=f"{pdf_file.name} Page {i+1}")
+                            gpt_text = process_image_with_prompt(img, "Extract the electronic text from image")
+                            combined_text += f"\n## {pdf_file.name} - Page {i+1}\n\n{gpt_text}\n"
+                doc.close()
+            except Exception as e:
+                st.error(f"Error processing {pdf_file.name}: {str(e)}")
+            finally:
+                os.remove(temp_pdf_path)
+        output_filename = generate_filename("processed_pdf", "md")
+        with open(output_filename, "w", encoding="utf-8") as f:
+            f.write(combined_text)
+        st.success(f"PDF processing complete. MD file saved as {output_filename}")
+        st.markdown(get_download_link(output_filename, "text/markdown", "Download Processed PDF MD"), unsafe_allow_html=True)
+
+# === New Tab: Image Process ===
+with tab_image_process:
+    st.header("Image Process")
+    st.subheader("Upload Images for GPT-based OCR")
+    prompt_img = st.text_input("Enter prompt for image processing", "Extract the electronic text from image", key="img_process_prompt")
+    uploaded_images = st.file_uploader("Upload image files", type=["png", "jpg", "jpeg"], accept_multiple_files=True, key="image_process_uploader")
+    if st.button("Process Uploaded Images", key="process_images"):
+        combined_text = ""
+        for img_file in uploaded_images:
+            try:
+                img = Image.open(img_file)
+                st.image(img, caption=img_file.name)
+                gpt_text = process_image_with_prompt(img, prompt_img)
+                combined_text += f"\n## {img_file.name}\n\n{gpt_text}\n"
+            except Exception as e:
+                st.error(f"Error processing image {img_file.name}: {str(e)}")
+        output_filename = generate_filename("processed_image", "md")
+        with open(output_filename, "w", encoding="utf-8") as f:
+            f.write(combined_text)
+        st.success(f"Image processing complete. MD file saved as {output_filename}")
+        st.markdown(get_download_link(output_filename, "text/markdown", "Download Processed Image MD"), unsafe_allow_html=True)
+
+# === New Tab: MD Gallery ===
+with tab_md_gallery:
+    st.header("MD Gallery and GPT Processing")
+    md_files = sorted(glob.glob("*.md"))
+    if md_files:
+        st.subheader("Individual File Processing")
+        cols = st.columns(2)
+        for idx, md_file in enumerate(md_files):
+            with cols[idx % 2]:
+                st.write(md_file)
+                if st.button(f"Process {md_file}", key=f"process_md_{md_file}"):
+                    try:
+                        with open(md_file, "r", encoding="utf-8") as f:
+                            content = f.read()
+                        prompt_md = "Summarize this into markdown outline with emojis and number the topics 1..12"
+                        messages = [{"role": "user", "content": prompt_md + "\n\n" + content}]
+                        response = openai.ChatCompletion.create(model="o3-mini-high", messages=messages)
+                        result_text = response.choices[0].message.content
+                        st.markdown(result_text)
+                        output_filename = generate_filename(f"processed_{os.path.splitext(md_file)[0]}", "md")
+                        with open(output_filename, "w", encoding="utf-8") as f:
+                            f.write(result_text)
+                        st.markdown(get_download_link(output_filename, "text/markdown", f"Download {output_filename}"), unsafe_allow_html=True)
+                    except Exception as e:
+                        st.error(f"Error processing {md_file}: {str(e)}")
+        st.subheader("Batch Processing")
+        st.write("Select MD files to combine and process:")
+        selected_md = {}
+        for md_file in md_files:
+            selected_md[md_file] = st.checkbox(md_file, key=f"checkbox_md_{md_file}")
+        batch_prompt = st.text_input("Enter batch processing prompt", "Summarize this into markdown outline with emojis and number the topics 1..12", key="batch_prompt")
+        if st.button("Process Selected MD Files", key="process_batch_md"):
+            combined_content = ""
+            for md_file, selected in selected_md.items():
+                if selected:
+                    try:
+                        with open(md_file, "r", encoding="utf-8") as f:
+                            combined_content += f"\n## {md_file}\n" + f.read() + "\n"
+                    except Exception as e:
+                        st.error(f"Error reading {md_file}: {str(e)}")
+            if combined_content:
+                messages = [{"role": "user", "content": batch_prompt + "\n\n" + combined_content}]
+                try:
+                    response = openai.ChatCompletion.create(model="o3-mini-high", messages=messages)
+                    result_text = response.choices[0].message.content
+                    st.markdown(result_text)
+                    output_filename = generate_filename("batch_processed_md", "md")
+                    with open(output_filename, "w", encoding="utf-8") as f:
+                        f.write(result_text)
+                    st.success(f"Batch processing complete. MD file saved as {output_filename}")
+                    st.markdown(get_download_link(output_filename, "text/markdown", "Download Batch Processed MD"), unsafe_allow_html=True)
+                except Exception as e:
+                    st.error(f"Error processing batch: {str(e)}")
+            else:
+                st.warning("No MD files selected.")
+    else:
+        st.warning("No MD files found.")