Update app.py

app.py

@@ -1,4 +1,3 @@
-import os
 from fastapi import FastAPI, UploadFile, File, HTTPException, Form
 from fastapi.staticfiles import StaticFiles
 from fastapi.responses import RedirectResponse, JSONResponse
@@ -9,8 +8,6 @@ import io
 from docx import Document
 import fitz  # PyMuPDF
 import pandas as pd
-import matplotlib.pyplot as plt
-import seaborn as sns
 import uuid
 from transformers import MarianMTModel, MarianTokenizer
 from fastapi.middleware.cors import CORSMiddleware
@@ -47,136 +44,58 @@ def read_root():
     return RedirectResponse(url="/static/index.html")
 
 @app.post("/summarize")
-async def summarize_text(
-    file: UploadFile = File(None),
-    text: str = Form(None)
-):
-    logger.info(f"Received request: file={file}, text={text}")  # Debugging
-
+async def summarize_text(file: UploadFile = File(None), text: str = Form(None)):
     if file:
-        logger.info(f"Received document for summarization: {file.filename}")
-        try:
-            text = await extract_text_from_file(file)
-        except Exception as e:
-            logger.error(f"Error extracting text from file: {e}")
-            raise HTTPException(status_code=400, detail=str(e))
-    elif text:
-        logger.info("Received manual text for summarization")
-    else:
-        logger.error("No file or text provided")  # Debugging
-        raise HTTPException(status_code=400, detail="No file or text provided")
+        text = await extract_text_from_file(file)
+    elif not text:
+        raise HTTPException(status_code=400, detail="No text or file provided")
 
-    try:
-        summary = text_pipeline(f"summarize: {text}", max_length=100)
-        logger.info(f"Generated summary: {summary[0]['generated_text']}")
-        return {"summary": summary[0]['generated_text']}
-    except Exception as e:
-        logger.error(f"Error during summarization: {e}")
-        raise HTTPException(status_code=500, detail=str(e))
+    summary = text_pipeline(f"summarize: {text}", max_length=100)
+    return {"summary": summary[0]['generated_text']}
 
 @app.post("/caption")
 async def caption_image(file: UploadFile = File(...)):
-    logger.info(f"Received image for captioning: {file.filename}")
-    try:
-        image_data = await file.read()
-        image = Image.open(io.BytesIO(image_data))
-
-        # Validate image format
-        if image.format not in ["JPEG", "PNG"]:
-            raise ValueError("Unsupported image format. Please upload a JPEG or PNG file.")
-
-        caption = multimodal_pipeline(image)
-        logger.info(f"Generated caption: {caption[0]['generated_text']}")
-        return {"caption": caption[0]['generated_text']}
-    except Exception as e:
-        logger.error(f"Error during image captioning: {e}")
-        raise HTTPException(status_code=400, detail=str(e))
+    image_data = await file.read()
+    image = Image.open(io.BytesIO(image_data))
+    caption = multimodal_pipeline(image)
+    return {"caption": caption[0]['generated_text']}
 
 @app.post("/translate")
-async def translate_document(
-    file: UploadFile = File(...),
-    target_language: str = Form(...)
-):
-    logger.info(f"Received document for translation: {file.filename}")
-    logger.info(f"Target language: {target_language}")
-
-    try:
+async def translate_document(file: UploadFile = File(None), text: str = Form(None), target_language: str = Form(...)):
+    if file:
         text = await extract_text_from_file(file)
+    elif not text:
+        raise HTTPException(status_code=400, detail="No text or file provided")
 
-        if target_language in translation_models:
-            model_name = translation_models[target_language]
-        else:
-            model_name = "Helsinki-NLP/opus-mt-en-de"  # Default to German
-
-        tokenizer = MarianTokenizer.from_pretrained(model_name)
-        model = MarianMTModel.from_pretrained(model_name)
-
-        translated = model.generate(**tokenizer(text, return_tensors="pt", truncation=True))
-        translated_text = tokenizer.decode(translated[0], skip_special_tokens=True)
-
-        return {"translated_text": translated_text}
-    except Exception as e:
-        logger.error(f"Error during document translation: {e}")
-        raise HTTPException(status_code=500, detail=str(e))
+    model_name = translation_models.get(target_language, "Helsinki-NLP/opus-mt-en-de")
+    tokenizer = MarianTokenizer.from_pretrained(model_name)
+    model = MarianMTModel.from_pretrained(model_name)
+    translated = model.generate(**tokenizer(text, return_tensors="pt", truncation=True))
+    translated_text = tokenizer.decode(translated[0], skip_special_tokens=True)
+    return {"translated_text": translated_text}
 
 @app.post("/answer")
-async def answer_question(
-    file: UploadFile = File(None),
-    text: str = Form(None),
-    question: str = Form(...)
-):
+async def answer_question(file: UploadFile = File(None), text: str = Form(None), question: str = Form(...)):
     if file:
-        logger.info(f"Received document for question answering: {file.filename}")
-        try:
-            text = await extract_text_from_file(file)
-        except Exception as e:
-            logger.error(f"Error extracting text from file: {e}")
-            raise HTTPException(status_code=400, detail=str(e))
-    elif text:
-        logger.info("Received manual text for question answering")
-    else:
-        raise HTTPException(status_code=400, detail="No file or text provided")
+        text = await extract_text_from_file(file)
+    elif not text:
+        raise HTTPException(status_code=400, detail="No text or file provided")
 
-    try:
-        answer = text_pipeline(f"question: {question} context: {text}")
-        logger.info(f"Generated answer: {answer[0]['generated_text']}")
-        return {"answer": answer[0]['generated_text']}
-    except Exception as e:
-        logger.error(f"Error during question answering: {e}")
-        raise HTTPException(status_code=500, detail=str(e))
+    answer = text_pipeline(f"question: {question} context: {text}")
+    return {"answer": answer[0]['generated_text']}
 
 @app.post("/vqa")
 async def visual_question_answering(file: UploadFile = File(...), question: str = Form(...)):
-    logger.info(f"Received image for visual question answering: {file.filename}")
-    logger.info(f"Received question: {question}")
-    try:
-        image_data = await file.read()
-        image = Image.open(io.BytesIO(image_data))
-
-        # Validate image format
-        if image.format not in ["JPEG", "PNG"]:
-            raise ValueError("Unsupported image format. Please upload a JPEG or PNG file.")
-
-        answer = multimodal_pipeline(image, question=question)
-        logger.info(f"Generated answer: {answer[0]['generated_text']}")
-        return {"answer": answer[0]['generated_text']}
-    except Exception as e:
-        logger.error(f"Error during visual question answering: {e}")
-        raise HTTPException(status_code=400, detail=str(e))
+    image_data = await file.read()
+    image = Image.open(io.BytesIO(image_data))
+    answer = multimodal_pipeline(image, question=question)
+    return {"answer": answer[0]['generated_text']}
 
 @app.post("/visualize")
-async def visualize_data(
-    file: UploadFile = File(...),
-    request: str = Form(...)
-):
-    logger.info(f"Received Excel file for visualization: {file.filename}")
-    logger.info(f"Received visualization request: {request}")
-
-    try:
-        df = pd.read_excel(io.BytesIO(await file.read()))
-
-        if "bar" in request.lower():
-            code = f"""
+async def visualize_data(file: UploadFile = File(...), request: str = Form(...)):
+    df = pd.read_excel(io.BytesIO(await file.read()))
+    if "bar" in request.lower():
+        code = f"""
 import matplotlib.pyplot as plt
 plt.bar(df['{df.columns[0]}'], df['{df.columns[1]}'])
 plt.xlabel('{df.columns[0]}')
@@ -184,8 +103,8 @@ plt.ylabel('{df.columns[1]}')
 plt.title('Bar Chart')
 plt.show()
 """
-        elif "line" in request.lower():
-            code = f"""
+    elif "line" in request.lower():
+        code = f"""
 import matplotlib.pyplot as plt
 plt.plot(df['{df.columns[0]}'], df['{df.columns[1]}'])
 plt.xlabel('{df.columns[0]}')
@@ -193,70 +112,29 @@ plt.ylabel('{df.columns[1]}')
 plt.title('Line Chart')
 plt.show()
 """
-        else:
-            code = f"""
+    else:
+        code = f"""
 import seaborn as sns
 sns.pairplot(df)
 plt.show()
 """
-
-        code_filename = f"visualization_{uuid.uuid4()}.py"
-        with open(code_filename, "w") as f:
-            f.write(code)
-
-        return {"code": code, "filename": code_filename}
-    except Exception as e:
-        logger.error(f"Error during visualization code generation: {e}")
-        raise HTTPException(status_code=500, detail=str(e))
+    return {"code": code}
 
 async def extract_text_from_file(file: UploadFile):
-    try:
-        file_content = await file.read()
-        if not file_content:
-            logger.error("Uploaded file is empty.")
-            raise ValueError("Uploaded file is empty.")
-
-        # Check file size (e.g., limit to 10MB)
-        if len(file_content) > 10 * 1024 * 1024:  # 10MB
-            logger.error("File size exceeds the limit (10MB).")
-            raise ValueError("File size exceeds the limit (10MB).")
-
-        # Check file type
-        if not file.filename.lower().endswith((".pdf", ".docx", ".txt")):
-            logger.error(f"Unsupported files format: {file.filename}")
-            raise ValueError("Unsupported file format. Please upload a PDF, DOCX, or TXT file.")
-
-        if file.filename.endswith(".pdf"):
-            try:
-                # Log the first few bytes of the file for debugging
-                logger.info(f"First 100 bytes of the file: {file_content[:100]}")
-
-                # Attempt to open the PDF
-                doc = fitz.open(stream=file_content, filetype="pdf")
-                text = ""
-                for page in doc:
-                    text += page.get_text()
-                return text
-            except Exception as e:
-                logger.error(f"Error reading PDF file: {e}")
-                raise ValueError("Failed to read PDF file. It might be corrupted or not a valid PDF.")
-        elif file.filename.endswith(".docx"):
-            try:
-                doc = Document(io.BytesIO(file_content))
-                text = "\n".join([para.text for para in doc.paragraphs])
-                return text
-            except Exception as e:
-                logger.error(f"Error reading DOCX file: {e}")
-                raise ValueError("Failed to read DOCX file. It might be corrupted or not a valid DOCX.")
-        elif file.filename.endswith(".txt"):
-            try:
-                return file_content.decode("utf-8")
-            except Exception as e:
-                logger.error(f"Error reading TXT file: {e}")
-                raise ValueError("Failed to read TXT file. It might be corrupted or not a valid TXT.")
-    except Exception as e:
-        logger.error(f"Error extracting text from file: {e}")
-        raise HTTPException(status_code=400, detail=str(e))
+    file_content = await file.read()
+    if file.filename.endswith(".pdf"):
+        doc = fitz.open(stream=file_content, filetype="pdf")
+        text = ""
+        for page in doc:
+            text += page.get_text()
+        return text
+    elif file.filename.endswith(".docx"):
+        doc = Document(io.BytesIO(file_content))
+        return "\n".join([para.text for para in doc.paragraphs])
+    elif file.filename.endswith(".txt"):
+        return file_content.decode("utf-8")
+    else:
+        raise HTTPException(status_code=400, detail="Unsupported file format")
 
 if __name__ == "__main__":
     import uvicorn