Update app.py

app.py

@@ -1,37 +1,25 @@
-from fastapi import FastAPI, File, UploadFile
+
+from fastapi import FastAPI, UploadFile
 import pdfplumber
-import pytesseract
-from PIL import Image
-import easyocr
 import docx
 import openpyxl
 from pptx import Presentation
 from transformers import pipeline
 import gradio as gr
-import pandas as pd
-import matplotlib.pyplot as plt
-import seaborn as sns
 from fastapi.responses import RedirectResponse
-import io
 
 # ✅ Initialize FastAPI
 app = FastAPI()
 
-# ✅ Load AI Models
-from transformers import pipeline
-
-qa_pipeline = pipeline("text2text-generation",model="google/flan-t5-large",tokenizer="google/flan-t5-large",use_fast=True,device=0)
-table_analyzer = pipeline("table-question-answering",model="google/tapas-large-finetuned-wtq",tokenizer="google/tapas-large-finetuned-wtq",use_fast=True,device=0)
-code_generator = pipeline("text-generation",model="openai-community/gpt2-medium",tokenizer="openai-community/gpt2-medium",use_fast=True,device=0)
-vqa_pipeline = pipeline("image-to-text",model="Salesforce/blip-vqa-base",device=0 )
+# ✅ Load AI Model
+qa_pipeline = pipeline("text2text-generation", model="google/flan-t5-large", tokenizer="google/flan-t5-large", use_fast=True, device=0)
 
-
-# ✅ Function to truncate text to 450 tokens
+# ✅ Function to truncate text to avoid token limit errors
 def truncate_text(text, max_tokens=450):
     words = text.split()
-    return " ".join(words[:max_tokens])  # ✅ Keeps only the first 450 words
+    return " ".join(words[:max_tokens])
 
-# ✅ Functions for Document & Image QA
+# ✅ Functions to extract text from different file formats
 def extract_text_from_pdf(pdf_file):
     text = ""
     with pdfplumber.open(pdf_file) as pdf:
@@ -60,11 +48,7 @@ def extract_text_from_excel(excel_file):
             text.append(" ".join(map(str, row)))
     return "\n".join(text)
 
-def extract_text_from_image(image_file):
-    reader = easyocr.Reader(["en"])
-    result = reader.readtext(image_file)
-    return " ".join([res[1] for res in result])
-
+# ✅ Function to answer questions based on document content
 def answer_question_from_document(file, question):
     file_ext = file.name.split(".")[-1].lower()
     
@@ -83,25 +67,11 @@ def answer_question_from_document(file, question):
         return "No text extracted from the document."
 
     truncated_text = truncate_text(text)  # ✅ Prevents token limit error
-
-    input_text = f"Question: {question} Context: {truncated_text}"  # ✅ Proper FLAN-T5 format
-    response = qa_pipeline(input_text)
-
-    return response[0]["generated_text"]  # ✅ Returns the correct output
-
-def answer_question_from_image(image, question):
-    image_text = extract_text_from_image(image)
-    if not image_text:
-        return "No text detected in the image."
-
-    truncated_text = truncate_text(image_text)  # ✅ Prevents token limit error
-
     input_text = f"Question: {question} Context: {truncated_text}"
     response = qa_pipeline(input_text)
-
     return response[0]["generated_text"]
 
-# ✅ Gradio UI for Document & Image QA
+# ✅ Gradio UI for Document QA
 doc_interface = gr.Interface(
     fn=answer_question_from_document,
     inputs=[gr.File(label="Upload Document"), gr.Textbox(label="Ask a Question")],
@@ -109,28 +79,8 @@ doc_interface = gr.Interface(
     title="AI Document Question Answering"
 )
 
-img_interface = gr.Interface(
-    fn=answer_question_from_image,
-    inputs=[gr.Image(label="Upload Image"), gr.Textbox(label="Ask a Question")],
-    outputs="text",
-    title="AI Image Question Answering"
-)
-
-
-# ✅ Gradio UI for Data Visualization
-viz_interface = gr.Interface(
-    fn=generate_visualization,
-    inputs=[
-        gr.File(label="Upload Excel File"),
-        gr.Radio(["Bar Chart", "Line Chart", "Scatter Plot", "Histogram"], label="Choose Visualization Type"),
-        gr.Textbox(label="Enter Visualization Request")
-    ],
-    outputs=[gr.Code(label="Generated Python Code"), gr.Image(label="Visualization Output")],
-    title="AI-Powered Data Visualization"
-)
-
 # ✅ Mount Gradio Interfaces
-demo = gr.TabbedInterface([doc_interface, img_interface], ["Document QA", "Image QA"])
+demo = gr.TabbedInterface([doc_interface], ["Document QA"])
 app = gr.mount_gradio_app(app, demo, path="/")
 
 @app.get("/")