Create app.py

app.py

@@ -0,0 +1,79 @@
+import os
+import gradio as gr
+import faiss
+import numpy as np
+from PyPDF2 import PdfReader
+from sentence_transformers import SentenceTransformer
+from groq import Groq
+
+# 🔐 Groq API Key (embed securely for private use only)
+GROQ_API_KEY = "your_groq_api_key_here"
+
+# 📦 Load embedding model
+model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
+
+# 📂 Global storage for vector index and chunks
+chunks = []
+index = None
+
+# 📄 PDF Text Extraction & Processing
+def process_pdf(file):
+    global chunks, index
+    reader = PdfReader(file.name)
+    text = "\n".join(page.extract_text() or "" for page in reader.pages)
+
+    if not text.strip():
+        return "❌ No text found in the PDF. Please upload a different file."
+
+    # 📏 Chunking
+    chunk_size = 300
+    chunk_overlap = 50
+    words = text.split()
+    chunks = [
+        " ".join(words[i:i + chunk_size])
+        for i in range(0, len(words), chunk_size - chunk_overlap)
+    ]
+
+    # 📊 Embeddings + FAISS
+    embeddings = model.encode(chunks)
+    dimension = embeddings.shape[1]
+    index = faiss.IndexFlatL2(dimension)
+    index.add(np.array(embeddings))
+
+    return f"✅ Processed {len(chunks)} chunks from uploaded PDF. You can now ask questions."
+
+# ❓ Ask a Question
+def ask_question(query):
+    if not chunks or index is None:
+        return "⚠️ Please upload and process a PDF first."
+
+    query_embedding = model.encode([query])
+    distances, indices = index.search(np.array(query_embedding), k=3)
+    context = "\n".join([chunks[i] for i in indices[0]])
+
+    client = Groq(api_key=GROQ_API_KEY)
+    prompt = f"Answer the question based on the following context:\n\n{context}\n\nQuestion: {query}"
+
+    try:
+        response = client.chat.completions.create(
+            messages=[{"role": "user", "content": prompt}],
+            model="llama3-70b-8192"
+        )
+        return response.choices[0].message.content
+    except Exception as e:
+        return f"❌ Error from Groq API: {str(e)}"
+
+# 🎛️ Gradio Interface
+file_input = gr.File(label="📄 Upload PDF")
+question_input = gr.Textbox(label="❓ Ask a Question about the PDF")
+answer_output = gr.Textbox(label="📘 Answer")
+
+pdf_processor = gr.Interface(fn=process_pdf, inputs=file_input, outputs="text")
+pdf_qa = gr.Interface(fn=ask_question, inputs=question_input, outputs=answer_output)
+
+app = gr.TabbedInterface(
+    [pdf_processor, pdf_qa],
+    tab_names=["Upload PDF", "Ask a Question"]
+)
+
+app.launch()