Create app.py

app.py

@@ -0,0 +1,154 @@
+import os
+import gradio as gr
+import faiss
+import numpy as np
+import gdown
+
+from groq import Groq
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_community.document_loaders import PyPDFLoader
+from langchain_huggingface import HuggingFaceEmbeddings
+
+
+# ==============================
+# 🔐 Load Groq API Key Securely
+# ==============================
+groq_api_key = os.environ.get("GROQ_API_KEY")
+client = Groq(api_key=groq_api_key)
+
+
+# ==============================
+# 📥 Download Knowledge Base
+# ==============================
+FILE_ID = "1ppfRoaQik3h1Gr9A15xSOLGVpNQtm8eH"
+DOWNLOAD_URL = f"https://drive.google.com/uc?id={FILE_ID}"
+PDF_PATH = "knowledge_base.pdf"
+
+if not os.path.exists(PDF_PATH):
+    gdown.download(DOWNLOAD_URL, PDF_PATH, quiet=False)
+
+
+# ==============================
+# 📚 Create Vector Database
+# ==============================
+embedding_model = HuggingFaceEmbeddings(
+    model_name="sentence-transformers/all-MiniLM-L6-v2"
+)
+
+loader = PyPDFLoader(PDF_PATH)
+documents = loader.load()
+
+text_splitter = RecursiveCharacterTextSplitter(
+    chunk_size=600,
+    chunk_overlap=150
+)
+
+chunks = text_splitter.split_documents(documents)
+texts = [chunk.page_content for chunk in chunks]
+
+embeddings = embedding_model.embed_documents(texts)
+embeddings = np.array(embeddings).astype("float32")
+
+dimension = embeddings.shape[1]
+vector_store = faiss.IndexFlatL2(dimension)
+vector_store.add(embeddings)
+
+print("✅ Knowledge Base Loaded Successfully")
+
+
+# ==============================
+# 🤖 RAG Function
+# ==============================
+def ask_question(question):
+    question_embedding = embedding_model.embed_query(question)
+    question_embedding = np.array([question_embedding]).astype("float32")
+
+    distances, indices = vector_store.search(question_embedding, k=4)
+
+    retrieved_texts = [texts[i] for i in indices[0]]
+    context = "\n\n".join(retrieved_texts)
+
+    prompt = f"""
+You are an expert assistant.
+
+Use ONLY the context below to answer clearly.
+Format with headings and bullet points if needed.
+
+CONTEXT:
+{context}
+
+QUESTION:
+{question}
+"""
+
+    chat_completion = client.chat.completions.create(
+        messages=[{"role": "user", "content": prompt}],
+        model="llama-3.3-70b-versatile",
+    )
+
+    answer = chat_completion.choices[0].message.content
+
+    return f"""
+## 📌 Answer
+
+{answer}
+"""
+
+
+# ==============================
+# 🎨 Professional Yellow UI
+# ==============================
+custom_css = """
+body {
+    background-color: #ffffff;
+    font-family: Arial, sans-serif;
+}
+
+.gradio-container {
+    background-color: #fffbea;
+    border-radius: 15px;
+    padding: 25px;
+}
+
+button {
+    background-color: #ffc107 !important;
+    color: black !important;
+    font-weight: bold !important;
+    border-radius: 10px !important;
+}
+
+textarea {
+    border-radius: 10px !important;
+}
+
+.answer-box {
+    background-color: white;
+    border: 2px solid #ffc107;
+    padding: 20px;
+    border-radius: 12px;
+    min-height: 250px;
+}
+"""
+
+
+with gr.Blocks(css=custom_css) as app:
+
+    gr.Markdown(
+        """
+        # 🟡 KnowledgeBase AI Assistant
+        ### Ask questions from my curated knowledge base
+        """
+    )
+
+    question_input = gr.Textbox(
+        label="Enter Your Question",
+        placeholder="Ask something from the knowledge base..."
+    )
+
+    ask_button = gr.Button("Get Answer")
+
+    answer_output = gr.Markdown(elem_classes="answer-box")
+
+    ask_button.click(ask_question, inputs=question_input, outputs=answer_output)
+
+app.launch()