Update main.py

main.py

@@ -1,4 +1,4 @@
-from fastapi import FastAPI, UploadFile, File, Form, Request
+"""from fastapi import FastAPI, UploadFile, File, Form, Request
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.responses import HTMLResponse, JSONResponse, FileResponse
 from fastapi.staticfiles import StaticFiles
@@ -72,4 +72,301 @@ async def predict(
         else:
             return JSONResponse({"error": "Invalid option"}, status_code=400)
     except Exception as e:
-        return JSONResponse({"error": f"Prediction failed: {str(e)}"}, status_code=500)
+        return JSONResponse({"error": f"Prediction failed: {str(e)}"}, status_code=500) """
+from fastapi import FastAPI, UploadFile, File, Form, Request, HTTPException
+from fastapi.responses import HTMLResponse, JSONResponse, FileResponse
+from fastapi.staticfiles import StaticFiles
+from fastapi.templating import Jinja2Templates
+from fastapi.middleware.cors import CORSMiddleware
+from transformers import pipeline, AutoTokenizer, AutoModelForSeq2SeqLM, AutoProcessor, AutoModelForCausalLM
+from PIL import Image
+import torch
+import fitz  # PyMuPDF
+import docx
+import pptx
+import openpyxl
+import re
+import nltk
+from nltk.tokenize import sent_tokenize
+from gtts import gTTS
+from fpdf import FPDF
+import tempfile
+import os
+import shutil
+import datetime
+import hashlib
+import easyocr
+from typing import Optional
+
+# Initialize app
+app = FastAPI()
+
+# CORS Configuration
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# Static assets
+app.mount("/static", StaticFiles(directory="static"), name="static")
+app.mount("/resources", StaticFiles(directory="resources"), name="resources")
+
+# Templates
+templates = Jinja2Templates(directory="templates")
+
+# Initialize models
+nltk.download('punkt', quiet=True)
+
+# Document processing models
+try:
+    tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large-cnn")
+    model = AutoModelForSeq2SeqLM.from_pretrained("facebook/bart-large-cnn")
+    model.eval()
+    summarizer = pipeline("summarization", model=model, tokenizer=tokenizer, device=-1)
+    reader = easyocr.Reader(['en'], gpu=torch.cuda.is_available())
+except Exception as e:
+    print(f"Error loading summarization models: {e}")
+    summarizer = None
+
+# Image captioning models
+try:
+    processor = AutoProcessor.from_pretrained("microsoft/git-large-coco")
+    git_model = AutoModelForCausalLM.from_pretrained("microsoft/git-large-coco")
+    git_model.eval()
+    USE_GIT = True
+except Exception as e:
+    print(f"Error loading GIT model, falling back to ViT: {e}")
+    captioner = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")
+    USE_GIT = False
+
+# Helper functions
+def clean_text(text: str) -> str:
+    text = re.sub(r'\s+', ' ', text)
+    text = re.sub(r'\u2022\s*|\d\.\s+', '', text)
+    text = re.sub(r'\[.*?\]|\(.*?\)', '', text)
+    text = re.sub(r'\bPage\s*\d+\b', '', text, flags=re.IGNORECASE)
+    return text.strip()
+
+def extract_text(file_path: str, file_extension: str):
+    try:
+        if file_extension == "pdf":
+            with fitz.open(file_path) as doc:
+                text = "\n".join(page.get_text("text") for page in doc)
+                if len(text.strip()) < 50:
+                    images = [page.get_pixmap() for page in doc]
+                    temp_img = tempfile.NamedTemporaryFile(suffix=".png", delete=False)
+                    images[0].save(temp_img.name)
+                    ocr_result = reader.readtext(temp_img.name, detail=0)
+                    os.unlink(temp_img.name)
+                    text = "\n".join(ocr_result) if ocr_result else text
+                return clean_text(text), ""
+
+        elif file_extension == "docx":
+            doc = docx.Document(file_path)
+            return clean_text("\n".join(p.text for p in doc.paragraphs)), ""
+
+        elif file_extension == "pptx":
+            prs = pptx.Presentation(file_path)
+            text = [shape.text for slide in prs.slides for shape in slide.shapes if hasattr(shape, "text")]
+            return clean_text("\n".join(text)), ""
+
+        elif file_extension == "xlsx":
+            wb = openpyxl.load_workbook(file_path, read_only=True)
+            text = [" ".join(str(cell) for cell in row if cell) for sheet in wb.sheetnames for row in wb[sheet].iter_rows(values_only=True)]
+            return clean_text("\n".join(text)), ""
+
+        return "", "Unsupported file format"
+    except Exception as e:
+        return "", f"Error reading {file_extension.upper()} file: {str(e)}"
+
+def chunk_text(text: str, max_tokens: int = 950):
+    try:
+        sentences = sent_tokenize(text)
+    except:
+        words = text.split()
+        sentences = [' '.join(words[i:i+20]) for i in range(0, len(words), 20)]
+
+    chunks = []
+    current_chunk = ""
+    for sentence in sentences:
+        token_length = len(tokenizer.encode(current_chunk + " " + sentence))
+        if token_length <= max_tokens:
+            current_chunk += " " + sentence
+        else:
+            chunks.append(current_chunk.strip())
+            current_chunk = sentence
+
+    if current_chunk:
+        chunks.append(current_chunk.strip())
+
+    return chunks
+
+def generate_summary(text: str, length: str = "medium") -> str:
+    cache_key = hashlib.md5((text + length).encode()).hexdigest()
+    
+    length_params = {
+        "short": {"max_length": 80, "min_length": 30},
+        "medium": {"max_length": 200, "min_length": 80},
+        "long": {"max_length": 300, "min_length": 210}
+    }
+    
+    chunks = chunk_text(text)
+    try:
+        summaries = summarizer(
+            chunks,
+            max_length=length_params[length]["max_length"],
+            min_length=length_params[length]["min_length"],
+            do_sample=False,
+            truncation=True
+        )
+        summary_texts = [s['summary_text'] for s in summaries]
+    except Exception as e:
+        summary_texts = [f"[Error: {str(e)}"]
+
+    final_summary = " ".join(summary_texts)
+    final_summary = ". ".join(s.strip().capitalize() for s in final_summary.split(". ") if s.strip())
+    return final_summary if len(final_summary) > 25 else "Summary too short"
+
+def text_to_speech(text: str):
+    try:
+        tts = gTTS(text)
+        temp_audio = tempfile.NamedTemporaryFile(delete=False, suffix=".mp3")
+        tts.save(temp_audio.name)
+        return temp_audio.name
+    except Exception as e:
+        print(f"Error in text-to-speech: {e}")
+        return ""
+
+def create_pdf(summary: str, original_filename: str):
+    try:
+        pdf = FPDF()
+        pdf.add_page()
+        pdf.set_font("Arial", 'B', 16)
+        pdf.cell(200, 10, txt="Document Summary", ln=1, align='C')
+        pdf.set_font("Arial", size=12)
+        pdf.cell(200, 10, txt=f"Original file: {original_filename}", ln=1)
+        pdf.cell(200, 10, txt=f"Generated on: {datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')}", ln=1)
+        pdf.ln(10)
+        pdf.multi_cell(0, 10, txt=summary)
+        temp_pdf = tempfile.NamedTemporaryFile(delete=False, suffix=".pdf")
+        pdf.output(temp_pdf.name)
+        return temp_pdf.name
+    except Exception as e:
+        print(f"Error creating PDF: {e}")
+        return ""
+
+def generate_caption(image_path: str) -> str:
+    try:
+        if USE_GIT:
+            image = Image.open(image_path).convert("RGB")
+            inputs = processor(images=image, return_tensors="pt")
+            outputs = git_model.generate(**inputs, max_length=50)
+            caption = processor.batch_decode(outputs, skip_special_tokens=True)[0]
+        else:
+            result = captioner(image_path)
+            caption = result[0]['generated_text']
+        return caption
+    except Exception as e:
+        raise Exception(f"Caption generation failed: {str(e)}")
+
+# API Endpoints
+@app.post("/summarize/")
+async def summarize_document(file: UploadFile = File(...), length: str = Form("medium")):
+    valid_types = [
+        'application/pdf',
+        'application/vnd.openxmlformats-officedocument.wordprocessingml.document',
+        'application/vnd.openxmlformats-officedocument.presentationml.presentation',
+        'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet'
+    ]
+    
+    if file.content_type not in valid_types:
+        raise HTTPException(
+            status_code=400,
+            detail="Please upload a valid document (PDF, DOCX, PPTX, or XLSX)"
+        )
+
+    try:
+        # Save temp file
+        with tempfile.NamedTemporaryFile(delete=False, suffix=os.path.splitext(file.filename)[1]) as temp:
+            shutil.copyfileobj(file.file, temp)
+            temp_path = temp.name
+
+        # Process file
+        text, error = extract_text(temp_path, os.path.splitext(file.filename)[1][1:].lower())
+        if error:
+            raise HTTPException(status_code=400, detail=error)
+
+        if not text or len(text.split()) < 30:
+            raise HTTPException(status_code=400, detail="Document too short to summarize")
+
+        summary = generate_summary(text, length)
+        audio_path = text_to_speech(summary)
+        pdf_path = create_pdf(summary, file.filename)
+
+        return {
+            "summary": summary,
+            "audio_url": f"/files/{os.path.basename(audio_path)}" if audio_path else None,
+            "pdf_url": f"/files/{os.path.basename(pdf_path)}" if pdf_path else None
+        }
+
+    except HTTPException:
+        raise
+    except Exception as e:
+        raise HTTPException(
+            status_code=500,
+            detail=f"Summarization failed: {str(e)}"
+        )
+    finally:
+        if 'temp_path' in locals() and os.path.exists(temp_path):
+            os.unlink(temp_path)
+
+@app.post("/imagecaption/")
+async def caption_image(file: UploadFile = File(...)):
+    valid_types = ['image/jpeg', 'image/png', 'image/gif', 'image/webp']
+    if file.content_type not in valid_types:
+        raise HTTPException(
+            status_code=400,
+            detail="Please upload a valid image (JPEG, PNG, GIF, or WEBP)"
+        )
+
+    try:
+        # Save temp file
+        with tempfile.NamedTemporaryFile(delete=False, suffix=os.path.splitext(file.filename)[1]) as temp:
+            shutil.copyfileobj(file.file, temp)
+            temp_path = temp.name
+
+        # Generate caption
+        caption = generate_caption(temp_path)
+        
+        # Generate audio
+        audio_path = text_to_speech(caption)
+
+        return {
+            "answer": caption,
+            "audio": f"/files/{os.path.basename(audio_path)}" if audio_path else None
+        }
+
+    except HTTPException:
+        raise
+    except Exception as e:
+        raise HTTPException(
+            status_code=500,
+            detail=str(e)
+        )
+    finally:
+        if 'temp_path' in locals() and os.path.exists(temp_path):
+            os.unlink(temp_path)
+
+@app.get("/files/{filename}")
+async def serve_file(filename: str):
+    file_path = os.path.join(tempfile.gettempdir(), filename)
+    if os.path.exists(file_path):
+        return FileResponse(file_path)
+    raise HTTPException(status_code=404, detail="File not found")
+
+@app.get("/", response_class=HTMLResponse)
+async def serve_home(request: Request):
+    return templates.TemplateResponse("HomeS.html", {"request": request})