Create app.py

app.py

@@ -0,0 +1,56 @@
+import os
+import faiss
+import gradio as gr
+from groq import Groq
+from datasets import load_dataset
+from sentence_transformers import SentenceTransformer
+from pypdf import PdfReader
+
+# Use Hugging Face secret for API key
+client = Groq(api_key=os.environ["GROQ_API_KEY"])
+
+# Embedding model
+embedder = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
+
+# Load dataset (example: AG News small subset)
+dataset = load_dataset("ag_news", split="train[:100]")
+texts = [item["text"] for item in dataset]
+
+# Chunking
+def chunk_text(text, chunk_size=200):
+    words = text.split()
+    return [" ".join(words[i:i+chunk_size]) for i in range(0, len(words), chunk_size)]
+
+chunks = []
+for doc in texts:
+    chunks.extend(chunk_text(doc))
+
+# Embeddings + FAISS
+embeddings = embedder.encode(chunks)
+dimension = embeddings.shape[1]
+index = faiss.IndexFlatL2(dimension)
+index.add(embeddings)
+
+# Retriever
+def retrieve(query, k=3):
+    q_emb = embedder.encode([query])
+    D, I = index.search(q_emb, k)
+    return [chunks[i] for i in I[0]]
+
+# RAG pipeline
+def rag_pipeline(query):
+    retrieved = retrieve(query)
+    context = "\n".join(retrieved)
+    prompt = f"Answer the question using context:\n{context}\n\nQuestion: {query}\nAnswer:"
+    response = client.chat.completions.create(
+        model="mixtral-8x7b-32768",
+        messages=[{"role": "user", "content": prompt}]
+    )
+    return response.choices[0].message.content
+
+# Gradio UI
+def chatbot(query):
+    return rag_pipeline(query)
+
+demo = gr.Interface(fn=chatbot, inputs="text", outputs="text", title="RAGify Bilal")
+demo.launch()