Create app.py

app.py

@@ -0,0 +1,119 @@
+from typing import Optional
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_groq import ChatGroq
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.vectorstores import Chroma
+from langchain.chains import ConversationalRetrievalChain
+from langchain.memory import ConversationBufferMemory
+import os
+from dotenv import load_dotenv
+import requests
+from bs4 import BeautifulSoup
+import gradio as gr
+
+# Load environment variables
+load_dotenv()
+GROQ_API_KEY = os.getenv("GROQ_API_KEY")
+
+# Initialize global session states
+session_state = {
+    "messages": [],
+    "qa_chain": None,
+    "current_blog_url": None,
+    "blog_content": None
+}
+
+# Function to fetch and extract blog text
+def fetch_blog_text(url: str) -> str:
+    response = requests.get(url)
+    soup = BeautifulSoup(response.text, "html.parser")
+    paragraphs = [p.get_text() for p in soup.find_all("p")]
+    return "\n".join(paragraphs)
+
+# Function to create vector store from blog text
+def create_vector_store(text: str):
+    splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
+    chunks = splitter.split_text(text)
+    embeddings = HuggingFaceEmbeddings()
+    vectordb = Chroma.from_texts(chunks, embeddings)
+    return vectordb
+
+# Set up the RAG chain
+def setup_chain(vectordb):
+    memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
+    llm = ChatGroq(api_key=GROQ_API_KEY, model="gemma2-9b-it")
+    qa_chain = ConversationalRetrievalChain.from_llm(
+        llm, vectordb.as_retriever(), memory=memory
+    )
+    return qa_chain
+
+# Load and process blog function
+def load_blog(blog_url):
+    try:
+        text = fetch_blog_text(blog_url)
+        vectordb = create_vector_store(text)
+        session_state["qa_chain"] = setup_chain(vectordb)
+        session_state["current_blog_url"] = blog_url
+        session_state["blog_content"] = text
+        session_state["messages"] = []
+        return f"✅ Blog loaded! You can now ask questions.\n\nPreview:\n{text[:1000]}{'...' if len(text) > 1000 else ''}"
+    except Exception as e:
+        return f"❌ Error loading blog: {str(e)}"
+
+# Chat handler
+def chat_with_blog(question):
+    if not session_state["qa_chain"]:
+        return "❌ Please load a blog first."
+
+    session_state["messages"].append({"role": "user", "content": question})
+    try:
+        result = session_state["qa_chain"]({
+            "question": question,
+            "chat_history": [
+                (m["content"] if m["role"] == "user" else "",
+                 m["content"] if m["role"] == "assistant" else "")
+                for m in session_state["messages"][:-1]
+            ]
+        })
+        response = result["answer"]
+        session_state["messages"].append({"role": "assistant", "content": response})
+        return response
+    except Exception as e:
+        return f"❌ Error: {str(e)}"
+
+# Gradio UI
+def main():
+    with gr.Blocks(theme=gr.themes.Base(), css="""
+        textarea, input, button {
+            font-size: 1.2em;
+        }
+        .chat-box {
+            height: 300px;
+            overflow-y: auto;
+            background-color: #1f1f1f;
+            color: white;
+            padding: 1em;
+            border-radius: 8px;
+        }
+    """) as demo:
+        gr.Markdown("# 📝 Blog Bot\nYour AI-powered blog analysis companion")
+
+        with gr.Row():
+            blog_url_input = gr.Textbox(label="Enter Blog URL", placeholder="Paste blog URL here...")
+            load_btn = gr.Button("✨ Load Blog")
+
+        blog_preview = gr.Markdown("", label="Blog Preview")
+
+        with gr.Row():
+            chat_input = gr.Textbox(label="Ask a question about the blog...", lines=2)
+            send_btn = gr.Button("Send")
+
+        chat_output = gr.Textbox(label="Response", lines=4)
+
+        load_btn.click(fn=load_blog, inputs=blog_url_input, outputs=blog_preview)
+        send_btn.click(fn=chat_with_blog, inputs=chat_input, outputs=chat_output)
+
+    demo.launch()
+
+if __name__ == "__main__":
+    main()