Skip to content

Instantly share code, notes, and snippets.

@andrewkkchan
Last active April 28, 2025 08:48
Show Gist options
  • Save andrewkkchan/2cc601878ae5e0b9aa35a1a0b4dc729f to your computer and use it in GitHub Desktop.
Save andrewkkchan/2cc601878ae5e0b9aa35a1a0b4dc729f to your computer and use it in GitHub Desktop.
llama_index_qa
import os
from llama_index.llms.bedrock import Bedrock
llm = Bedrock(
model_id="anthropic.claude-3-sonnet-20250219-v1:0",
temperature=0,
)
question = (
"I’m a 40-year-old investor with a moderate risk tolerance. "
"I have $50,000 to invest, and I would like to grow it over the next 10 years "
"for my retirement. Can you run financial simulations (like Monte Carlo) "
"to estimate potential returns and recommend suitable fund products?"
)
prompt = (
"You are a chartered financial planner.\n"
"Think step-by-step, run an internal Monte-Carlo simulation "
"(10 000 trials, 7 % mean, 15 % σ, 10 yr horizon), then output:\n"
"• Simulated median + 10th & 90th percentiles\n"
"• Key assumptions/caveats (1-2 sentences)\n"
"• 2-3 low-cost funds fit for moderate risk\n"
"• Quick next-step checklist\n"
"Hide your chain-of-thought. ≤ 250 words.\n\n"
f"{question}"
)
response = llm.complete(prompt)
print(response.text)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment