Update app.py

app.py

@@ -24,100 +24,58 @@ import matplotlib.pyplot as plt
 import plotly.express as px
 import requests
 
-# Ensure required libraries are installed
-try:
-    import torch
-except ImportError:
-    subprocess.check_call(["pip", "install", "torch"])
-try:
-    import pdfplumber
-except ImportError:
-    subprocess.check_call(["pip", "install", "pdfplumber"])
-try:
-    import plotly
-except ImportError:
-    subprocess.check_call(["pip", "install", "plotly"])
 
 # NLP Model for summarization
 summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
 
+# Helper function to clean text
+def clean_text(text):
+    """Clean extracted text by removing non-ASCII characters and extra whitespace."""
+    text = text.encode("ascii", "ignore").decode()
+    text = re.sub(r"\s+", " ", text)
+    return text.strip()
+
 # Title and Description
 st.title("Automated Datasheet Summarizer")
 st.write("Upload a datasheet PDF or enter a component name to get simplified summaries, key specs, and visual insights.")
 
-# Error Handling for Unsupported Files
-def validate_pdf(file):
-    try:
-        with pdfplumber.open(file) as pdf:
-            return pdf.pages[0].extract_text() is not None
-    except Exception as e:
-        return False
-
-# Function to fetch datasheet from an online database
-def fetch_datasheet(component_name):
-    try:
-        url = f"https://api.example.com/datasheets/{component_name}"  # Placeholder API
-        response = requests.get(url)
-        response.raise_for_status()
-        return response.content  # Assuming API returns a PDF file
-    except requests.exceptions.RequestException as e:
-        st.error(f"Error fetching datasheet: {e}")
-        return None
-
 # Input Options
 input_type = st.radio("Select Input Type:", ["Upload PDF", "Enter Component Name"])
 
 if input_type == "Upload PDF":
     uploaded_file = st.file_uploader("Upload a Datasheet PDF", type=["pdf"])
     if uploaded_file is not None:
-        if validate_pdf(uploaded_file):
+        try:
             with pdfplumber.open(uploaded_file) as pdf:
                 text = "".join([page.extract_text() for page in pdf.pages])
-            st.subheader("Extracted Text")
-            st.text_area("Datasheet Text", value=text[:5000], height=300)  # Show only first 5000 characters
             
+            cleaned_text = clean_text(text[:1024])  # Clean and truncate text
+            st.text_area("Extracted Text (Preview)", value=cleaned_text, height=300)
+
             if st.button("Summarize PDF"):
-                # Summarize the text
-                summary = summarizer(text[:1024], max_length=300, min_length=50, do_sample=False)[0]["summary_text"]
-                st.subheader("Simplified Summary")
-                st.write(summary)
-        else:
-            st.error("The uploaded file is either unsupported or does not contain readable text.")
+                if len(cleaned_text) == 0:
+                    st.error("No valid text extracted for summarization.")
+                else:
+                    try:
+                        # Summarize the text
+                        summary = summarizer(cleaned_text, max_length=300, min_length=50, do_sample=False)[0]["summary_text"]
+                        st.subheader("Simplified Summary")
+                        st.write(summary)
+                    except Exception as e:
+                        st.error(f"Error during summarization: {e}")
+
+        except Exception as e:
+            st.error(f"Error processing the PDF: {e}")
 
 elif input_type == "Enter Component Name":
     component_name = st.text_input("Enter Component Name")
     if component_name and st.button("Search and Summarize"):
-        datasheet_pdf = fetch_datasheet(component_name)
-        if datasheet_pdf:
-            with open("temp_datasheet.pdf", "wb") as f:
-                f.write(datasheet_pdf)
-            with pdfplumber.open("temp_datasheet.pdf") as pdf:
-                text = "".join([page.extract_text() for page in pdf.pages])
-            summary = summarizer(text[:1024], max_length=300, min_length=50, do_sample=False)[0]["summary_text"]
-            st.subheader("Simplified Summary")
-            st.write(summary)
-
-
-if st.button("Summarize PDF"):
-    # Clean and truncate text
-    input_text = clean_text(text[:1024])
-    st.text_area("Summarization Input", value=input_text, height=200)
-
-    if len(input_text.strip()) == 0:
-        st.error("No valid text extracted for summarization.")
-    else:
-        try:
-            # Summarize the text
-            summary = summarizer(input_text, max_length=300, min_length=50, do_sample=False)[0]["summary_text"]
-            st.subheader("Simplified Summary")
-            st.write(summary)
-        except Exception as e:
-            st.error(f"Error during summarization: {e}")
+        st.error("Component search functionality is under development.")
 
-# Dynamic Table Parsing
-if input_type == "Upload PDF" and uploaded_file is not None and validate_pdf(uploaded_file):
+# Dynamic Table Parsing (Example Data)
+if input_type == "Upload PDF" and uploaded_file is not None:
     if st.button("Generate Key Specifications Table"):
-        # Mock parsing logic for demonstration
+        # Mock parsing logic
         parsed_data = {
             "Parameter": ["Voltage", "Current", "Power", "Efficiency"],
             "Value": ["3.3V", "2A", "6.6W", "85%"],
@@ -126,7 +84,7 @@ if input_type == "Upload PDF" and uploaded_file is not None and validate_pdf(upl
         st.subheader("Key Specifications")
         st.table(df)
 
-        # Enhanced Visualization with Plotly
+        # Enhanced Visualization
         st.subheader("Interactive Key Parameters Graph")
         fig = px.bar(df, x="Parameter", y="Value", title="Key Specifications", text="Value")
         st.plotly_chart(fig)