Create rag.py

rag.py

@@ -0,0 +1,22 @@
+from duckduckgo_search import DDGS
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+def search_web(query):
+    with DDGS() as ddgs:
+        results = ddgs.text(query, max_results=5)
+    return "\n".join([r["body"] for r in results])
+
+tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b-it")
+model = AutoModelForCausalLM.from_pretrained("google/gemma-7b-it")
+
+def ask(question):
+    context = search_web(question)
+    prompt = f"Use this information:\n{context}\n\nQuestion: {question}\nAnswer:"
+
+    inputs = tokenizer(prompt, return_tensors="pt")
+    output = model.generate(**inputs, max_new_tokens=200)
+    return tokenizer.decode(output[0], skip_special_tokens=True)
+
+if __name__ == "__main__":
+    print(ask("When was the Eiffel Tower built?"))
+    python rag.py