Upload 3 files

app.py

@@ -0,0 +1,100 @@
+import streamlit as st
+import llm_part
+import os
+from langchain_groq import ChatGroq
+
+# Sidebar to select the LLM model
+st.sidebar.title("LLM Model Selector")
+llm_model = st.sidebar.selectbox("Select LLM Model", ("Google Gemini", "Llama"))
+
+
+# Define Llama-specific configurations
+if llm_model == "Google Gemini":  # Check if "Google Gemini" is selected
+    llm = llm_part.llm_1  # Assign Google Gemini to llm
+else:
+    llm = llm_part.llm_2  # Use the Llama model
+
+
+
+
+# Main app
+st.title("Jony's Custom Research Notes Extracted from PDFs Using " + llm_model)
+option = st.selectbox("Select PDF Source:", ("Enter URL", "Upload Local File"))
+
+document_text = ""
+
+if option == "Enter URL":
+    pdf_url = st.text_input("Enter the PDF URL:")
+    
+    if pdf_url:
+        try:
+            with st.spinner("Processing PDF from URL..."):
+                local_pdf_path = "downloaded_paper.pdf"
+                llm_part.download_pdf_from_url(pdf_url, local_pdf_path)
+                document_text = llm_part.extract_text_from_pdf(local_pdf_path)
+                os.remove(local_pdf_path)
+
+        except Exception as e:
+            st.error(f"Error processing PDF from URL: {e}")
+
+elif option == "Upload Local File":
+    uploaded_file = st.file_uploader("Choose a PDF file", type="pdf")
+    
+    if uploaded_file is not None:
+        try:
+            with st.spinner("Processing uploaded PDF..."):
+                local_pdf_path = "uploaded_paper.pdf"
+                with open(local_pdf_path, "wb") as f:
+                    f.write(uploaded_file.read())
+                document_text = llm_part.extract_text_from_pdf(local_pdf_path)
+                os.remove(local_pdf_path)
+
+        except Exception as e:
+            st.error(f"Error processing uploaded PDF: {e}")
+
+if document_text:
+    with st.spinner("Generating the summary..."):
+        query = llm_part.prompt.format(document_text=document_text[:20000])
+        result = llm.invoke(query)
+        st.write("### Summary in Table Format:")
+        st.write(result.content) 
+        lines = result.content.split('\n')
+        paragraph_output = []
+
+        for line in lines[2:]:
+            if "|" not in line or not line.strip():
+                continue
+
+            parts = [part.strip() for part in line.split("|") if part.strip()]
+            if len(parts) == 2:
+                _, details = parts
+                if "Not specified" in details or "Not mentioned" in details:
+                    continue
+                details_clean = llm_part.clean_html_tags(details)
+                paragraph_output.append(details_clean) 
+
+        paragraph_output = ". ".join(paragraph_output) + "."
+        paragraph_output = paragraph_output.replace(" ,", ",").replace(" .", ".")
+        paragraph_output = paragraph_output.replace(". CNN", ". In this approach, CNN").replace("Federated learning (FL)", "The use of Federated Learning (FL)")
+
+        paragraph_output = paragraph_output.replace("The use of Federated Learning", "The study explores the use of Federated Learning")
+        paragraph_output = paragraph_output.replace("In this approach, CNN", "In this approach, a combination of CNN models was used to enhance performance")
+        paragraph_output = paragraph_output.replace("achieved", "yielded results indicating")
+        paragraph_output = paragraph_output.replace("slightly lower", "only marginally lower")
+    
+        query2 = llm_part.prompt2.format(paragraph=paragraph_output)
+        result2 = llm.invoke(query2)
+        st.write("### Answer in Paragraph Style:")
+        st.markdown("""
+            <style>
+            .justified-text {
+                text-align: justify;
+            }
+            </style>
+            """, unsafe_allow_html=True)
+
+        st.markdown(f"<div class='justified-text'>{result2.content}</div>", unsafe_allow_html=True)
+
+
+        #pip install -r requirements.txt
+

llm_part.py

@@ -0,0 +1,81 @@
+import os
+import requests
+import streamlit as st
+from PyPDF2 import PdfReader
+from langchain.prompts import PromptTemplate
+from langchain_google_genai import ChatGoogleGenerativeAI
+import re
+from langchain_groq import ChatGroq
+from secret_key import gemeni_key,llama_key
+
+api_key = os.getenv("Gemini_api_key")
+llm_1 = ChatGoogleGenerativeAI(model="gemini-pro", api_key=api_key)
+
+api_key2=os.getenv("Llama_api_key")
+MODEL_ID = "llama3-groq-70b-8192-tool-use-preview"
+llm_2=ChatGroq(model=MODEL_ID, temperature=0, groq_api_key=api_key2)
+
+
+
+def download_pdf_from_url(url, local_file_path):
+    response = requests.get(url)
+    with open(local_file_path, 'wb') as f:
+        f.write(response.content)
+
+
+def extract_text_from_pdf(pdf_file_path):
+    reader = PdfReader(pdf_file_path)
+    text = ""
+    for page in reader.pages:
+        extracted_text = page.extract_text()
+        if extracted_text:  
+            text += extracted_text + "\n"  
+    return text.strip()
+
+def clean_html_tags(text):
+    clean_text = re.sub(r"<ul>|</ul>|<li>|</li>", "", text)
+    clean_text = re.sub(r"<.*?>", "", clean_text)
+    return clean_text.strip()
+
+# Define the template for summarization
+template = """
+Based on the following document:
+
+{document_text}
+
+Please provide the summary in a **table format**. Each point should be in its own row, with the following columns:
+
+| **Aspect**               | **Details**                                                         |
+|--------------------------|---------------------------------------------------------------------|
+| What did they do?         | Briefly describe the main task, objective, or experiment.           |
+| Contributions             | Highlight the main contributions of the paper.                     |
+| Hardware                  | Name, model, price (if available), link (if available), function.   |
+| Software                  | Type (commercial/free/custom-developed), version, availability, features. |
+| Dataset                   | Type (public/private), type of data (image, text, video, log), duration, size. |
+| Algorithms                | List the algorithms or models used.                                |
+| Place of Experiment       | Where was the experiment conducted (institution/lab)?               |
+| Claimed Results           | Summarize the key results and findings.                            |
+| Limitations               | Identify limitations or shortcomings.                              |
+| Solutions                 | Suggest possible solutions for overcoming limitations.             |
+| Improvements              | Suggest potential improvements or additions.                       |
+
+Ensure each section is concise but informative.
+"""
+
+# Prompt Template
+prompt = PromptTemplate(template=template, input_variables=["document_text"])
+
+template2 = """
+Paraphrase the following paragraph in academic research format:
+#NO PREAMBLE #
+#DONT INCLUDE ANY BULLET POINTS WRITE IN SINGLE PARAGRAPH#
+
+
+{paragraph}
+"""
+
+# Prompt Template
+prompt2 = PromptTemplate(template=template2, input_variables=["paragraph"])
+
+
+

requirements.txt

@@ -0,0 +1,8 @@
+
+requests
+streamlit
+PyPDF2
+langchain
+langchain-google-genai
+langchain-groq
+langchain_community