Create app.py

app.py

@@ -0,0 +1,146 @@
+import os
+import requests
+import gradio as gr
+import faiss
+import numpy as np
+
+from groq import Groq
+from pypdf import PdfReader
+from sentence_transformers import SentenceTransformer
+from dotenv import load_dotenv
+
+# =====================================
+# LOAD ENV VARIABLES
+# =====================================
+load_dotenv()
+GROQ_API_KEY = os.getenv("GROQ_API_KEY")
+client = Groq(api_key=GROQ_API_KEY)
+
+# =====================================
+# CONFIG
+# =====================================
+GROQ_MODEL = "llama-3.3-70b-versatile"
+EMBED_MODEL = "sentence-transformers/all-MiniLM-L6-v2"
+
+# Put your public Google Drive links here
+PDF_LINKS = [
+    "https://drive.google.com/file/d/1J89BeL4W-LpwaE4hY_81qPxw23DdXfqJ/view?usp=sharing"
+]
+
+# =====================================
+# DOWNLOAD PDF FROM GOOGLE DRIVE
+# =====================================
+def download_pdf_from_drive(link, save_path):
+    file_id = link.split("/d/")[1].split("/")[0]
+    download_url = f"https://drive.google.com/uc?id={file_id}"
+    response = requests.get(download_url)
+    with open(save_path, "wb") as f:
+        f.write(response.content)
+
+# =====================================
+# LOAD PDF TEXT
+# =====================================
+def load_pdf_text(pdf_path):
+    reader = PdfReader(pdf_path)
+    text = ""
+    for page in reader.pages:
+        text += page.extract_text() or ""
+    return text
+
+# =====================================
+# CHUNK TEXT
+# =====================================
+def chunk_text(text, chunk_size=500, overlap=100):
+    chunks = []
+    start = 0
+    while start < len(text):
+        end = start + chunk_size
+        chunks.append(text[start:end])
+        start += chunk_size - overlap
+    return chunks
+
+# =====================================
+# BUILD VECTOR DATABASE
+# =====================================
+all_chunks = []
+os.makedirs("data", exist_ok=True)
+
+for i, link in enumerate(PDF_LINKS):
+    pdf_path = f"data/doc_{i}.pdf"
+    download_pdf_from_drive(link, pdf_path)
+    text = load_pdf_text(pdf_path)
+    chunks = chunk_text(text)
+    all_chunks.extend(chunks)
+
+embed_model = SentenceTransformer(EMBED_MODEL)
+embeddings = embed_model.encode(all_chunks)
+embeddings = np.array(embeddings).astype("float32")
+
+dimension = embeddings.shape[1]
+index = faiss.IndexFlatL2(dimension)
+index.add(embeddings)
+
+# =====================================
+# RAG FUNCTION
+# =====================================
+def answer_question(question):
+    query_embedding = embed_model.encode([question])
+    query_embedding = np.array(query_embedding).astype("float32")
+
+    distances, indices = index.search(query_embedding, 3)
+
+    context = ""
+    for idx in indices[0]:
+        context += all_chunks[idx] + "\n\n"
+
+    prompt = f"""
+Use the context below to answer the question.
+If answer is not in the context, say you don't know.
+
+Context:
+{context}
+
+Question:
+{question}
+"""
+
+    response = client.chat.completions.create(
+        messages=[{"role": "user", "content": prompt}],
+        model=GROQ_MODEL,
+    )
+
+    return response.choices[0].message.content
+
+# =====================================
+# GRADIO UI
+# =====================================
+custom_css = """
+body { background: #0f172a; }
+h1 { text-align: center; color: white; }
+button {
+    background: linear-gradient(90deg,#6366f1,#8b5cf6);
+    color: white !important;
+    border-radius: 10px !important;
+}
+textarea { border-radius: 12px !important; }
+"""
+
+with gr.Blocks(css=custom_css) as demo:
+    gr.Markdown("# 📚 Public Google Drive RAG")
+
+    question = gr.Textbox(
+        label="Ask your question",
+        placeholder="Type your question...",
+        lines=3
+    )
+
+    ask_btn = gr.Button("Ask Question")
+
+    answer = gr.Textbox(
+        label="Answer",
+        lines=10
+    )
+
+    ask_btn.click(answer_question, inputs=question, outputs=answer)
+
+demo.launch()