app.py

import streamlit as st
from langchain_community.document_loaders import PyPDFLoader
import groq
import os
import tempfile

# Try importing pypdf and pdfminer as backups
try:
    import pypdf
    pypdf_installed = True
except ImportError:
    pypdf_installed = False

try:
    from pdfminer.high_level import extract_text
    pdfminer_installed = True
except ImportError:
    pdfminer_installed = False

# Basic Streamlit setup
st.set_page_config(page_title="Research Assistant", layout="centered")
st.title("📚 Research Assistant")

# Initialize Groq client
def get_groq_client():
    api_key = os.environ.get("GROQ_API_KEY")
    if not api_key:
        st.error("GROQ_API_KEY is missing. Please set it in the environment variables.")
        return None
    try:
        return groq.Client(api_key=api_key)  # ✅ FIXED: No 'proxies' argument
    except Exception as e:
        st.error(f"Failed to initialize Groq client: {e}")
        return None

# Function to analyze text
def analyze_content(text):
    client = get_groq_client()
    if not client or not text:
        return "Analysis unavailable"
    
    try:
        response = client.chat.completions.create(
            messages=[
                {"role": "system", "content": "You are a helpful research assistant"},
                {"role": "user", "content": f"Summarize this research content:\n\n{text[:3000]}"}
            ],
            model="llama3-70b-8192",
            temperature=0.7,
            max_tokens=500
        )
        return response.choices[0].message.content
    except Exception as e:
        return f"Analysis failed: {e}"

# Function to process PDF using either PyPDFLoader or pdfminer
def process_pdf(file):
    with tempfile.NamedTemporaryFile(suffix=".pdf", delete=False) as tmp:
        tmp.write(file.getvalue())
        tmp_path = tmp.name
    
    try:
        if pypdf_installed:
            loader = PyPDFLoader(tmp_path)
            pages = loader.load()
            return " ".join(page.page_content for page in pages[:3])  # First 3 pages
        elif pdfminer_installed:
            return extract_text(tmp_path)[:3000]  # Extract up to 3000 characters
        else:
            return "Neither pypdf nor pdfminer is installed. Please restart and rebuild the app."
    except Exception as e:
        return f"Error processing PDF: {e}"
    finally:
        os.unlink(tmp_path)

# Main App
tab1, tab2 = st.tabs(["Text Analysis", "PDF Analysis"])

with tab1:
    user_text = st.text_area("Enter research text:", height=150)
    if st.button("Analyze Text"):
        if user_text:
            with st.spinner("Analyzing..."):
                result = analyze_content(user_text)
                st.write(result)
        else:
            st.warning("Please enter some text")

with tab2:
    uploaded_file = st.file_uploader("Upload PDF", type=["pdf"])
    if uploaded_file and st.button("Analyze PDF"):
        with st.spinner("Processing PDF..."):
            pdf_text = process_pdf(uploaded_file)
            result = analyze_content(pdf_text)
            st.write(result)

st.markdown("---")
st.caption("Powered by Groq's Llama 3 70B")