Update app.py

app.py

@@ -1,90 +1,48 @@
+import numpy  # Ensure NumPy is loaded first to avoid FAISS issues
+import faiss  # Load FAISS after NumPy
 import os
 import streamlit as st
 import pandas as pd
 import pdfplumber
 from sentence_transformers import SentenceTransformer
-import faiss
 from groq import Groq
 
-# Set the Groq API key
-os.environ["GROQ_API_KEY"] = "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"
-
-# Initialize the embedding model and Groq API client
+# Initialize the embedding model and Groq API
 embed_model = SentenceTransformer('all-MiniLM-L6-v2')
-client = Groq(api_key=os.environ["GROQ_API_KEY"])
+client = Groq(api_key=os.environ.get("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"))
 
 # Function to extract text from PDF
 def extract_text_from_pdf(pdf_file):
-    text = ""
     with pdfplumber.open(pdf_file) as pdf:
-        for page in pdf.pages:
-            text += page.extract_text()
-    return text
-
-# Function to extract text from CSV or Excel
-def extract_text_from_table(file):
-    if file.name.endswith('.csv'):
-        df = pd.read_csv(file)
-    elif file.name.endswith('.xlsx'):
-        df = pd.read_excel(file)
-    else:
-        raise ValueError("Unsupported file format")
-    return " ".join(df.astype(str).values.flatten())
+        return ' '.join(page.extract_text() for page in pdf.pages)
 
-# Chunk the text
-def chunk_text(text, chunk_size=512):
-    words = text.split()
-    chunks = [' '.join(words[i:i + chunk_size]) for i in range(0, len(words), chunk_size)]
-    return chunks
-
-# Store embeddings in FAISS
-def create_faiss_index(chunks):
+# Function to create embeddings and store them in FAISS
+def create_embeddings(text):
+    chunks = [text[i:i+500] for i in range(0, len(text), 500)]
     embeddings = embed_model.encode(chunks)
-    dimension = embeddings.shape[1]
-    index = faiss.IndexFlatL2(dimension)
+    index = faiss.IndexFlatL2(embeddings.shape[1])
     index.add(embeddings)
-    return index, embeddings
-
-# Query FAISS for relevant chunks
-def query_faiss(index, query, chunks, embeddings):
-    query_embedding = embed_model.encode([query])
-    _, indices = index.search(query_embedding, k=3)
-    return [chunks[i] for i in indices[0]]
-
-# Query Groq API
-def query_groq(context, question):
-    response = client.chat.completions.create(
-        messages=[{"role": "user", "content": f"Context: {context}\nQuestion: {question}"}],
-        model="llama3-8b-8192"
-    )
-    return response.choices[0].message.content
-
-# Streamlit App
-st.title("RAG-based Application")
-
-uploaded_file = st.file_uploader("Upload your document (PDF, CSV, or Excel)", type=["pdf", "csv", "xlsx"])
-
-if uploaded_file:
-    try:
-        # Extract text from the uploaded document
-        if uploaded_file.name.endswith('.pdf'):
-            document_text = extract_text_from_pdf(uploaded_file)
-        else:
-            document_text = extract_text_from_table(uploaded_file)
-        
-        # Chunk the document and create FAISS index
-        st.write("Processing document...")
-        chunks = chunk_text(document_text)
-        faiss_index, embeddings = create_faiss_index(chunks)
-        st.success("Document processed successfully!")
-        
-        # Query input
-        user_query = st.text_input("Enter your query:")
-        if user_query:
-            relevant_chunks = query_faiss(faiss_index, user_query, chunks, embeddings)
-            context = " ".join(relevant_chunks)
-            answer = query_groq(context, user_query)
-            st.subheader("Answer:")
-            st.write(answer)
-    except Exception as e:
-        st.error(f"Error: {str(e)}")
+    return index
+
+# Streamlit app
+def main():
+    st.title("Document Processing with RAG")
+    uploaded_file = st.file_uploader("Upload a document (PDF, CSV, or Excel)", type=["pdf", "csv", "xlsx"])
+
+    if uploaded_file:
+        file_type = uploaded_file.type
+        if file_type == "application/pdf":
+            text = extract_text_from_pdf(uploaded_file)
+        elif file_type in ["text/csv", "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"]:
+            df = pd.read_csv(uploaded_file) if file_type == "text/csv" else pd.read_excel(uploaded_file)
+            text = df.to_string()
+
+        st.write("Document Content:")
+        st.text_area("Extracted Text", text, height=300)
+
+        st.write("Creating embeddings...")
+        index = create_embeddings(text)
+        st.success("Embeddings created and stored in FAISS index.")
+
+if __name__ == "__main__":
+    main()