Create app.py

app.py

@@ -0,0 +1,67 @@
+import os
+import streamlit as st
+import requests
+from bs4 import BeautifulSoup
+from sentence_transformers import SentenceTransformer
+import faiss
+from groq import Groq
+
+# Scrape data from the webpage
+def scrape_tariff_data(url):
+    response = requests.get(url)
+    soup = BeautifulSoup(response.text, 'html.parser')
+    tariff_data = []
+    for paragraph in soup.find_all('p'):
+        tariff_data.append(paragraph.text.strip())
+    return "\n".join(tariff_data)
+
+# Chunking text
+def chunk_text(text, max_length=512):
+    words = text.split()
+    chunks = []
+    for i in range(0, len(words), max_length):
+        chunks.append(" ".join(words[i:i+max_length]))
+    return chunks
+
+# Embed text and save in FAISS
+def create_faiss_index(chunks, model_name='all-MiniLM-L6-v2'):
+    model = SentenceTransformer(model_name)
+    embeddings = model.encode(chunks)
+    dimension = embeddings.shape[1]
+    index = faiss.IndexFlatL2(dimension)
+    index.add(embeddings)
+    return index, embeddings, model
+
+# Groq API for LLM
+def query_llm(prompt, api_key):
+    client = Groq(api_key=api_key)
+    chat_completion = client.chat.completions.create(
+        messages=[
+            {
+                "role": "user",
+                "content": prompt,
+            }
+        ],
+        model="llama3-8b-8192",
+    )
+    return chat_completion.choices[0].message.content
+
+# Streamlit UI
+st.title("RAG-Based Tariff Data Application")
+
+url = st.text_input("Enter Tariff Data URL", "https://iesco.com.pk/index.php/customer-services/tariff-guide")
+api_key = st.text_input("Enter Groq API Key", type="password")
+
+if st.button("Process Tariff Data"):
+    with st.spinner("Extracting and processing data..."):
+        text = scrape_tariff_data(url)
+        chunks = chunk_text(text)
+        index, embeddings, model = create_faiss_index(chunks)
+        st.success("Data processed and indexed!")
+
+if st.text_input("Query"):
+    prompt = st.text_input("Enter your query")
+    if prompt and api_key:
+        with st.spinner("Fetching response..."):
+            response = query_llm(prompt, api_key)
+            st.write(response)