infrastructure-ollama-connectivity-connecterror-from-httpx-httpcore-when-querying-lla-487259a3

THEN Implement a retry mechanism with exponential backoff for queries. Verify that the Ollama server is running and reachable from the environment. If using Google Colab, check if outbound connections to the default Ollama port (11434) are allowed; consider running locally or adjusting network settings. Optionally, switch to a different HTTP client like `requests` if the issue persists.

from tenacity import retry, stop_after_attempt, wait_exponential

@retry(stop=stop_after_attempt(3), wait=wait_exponential(multiplier=1, min=2, max=10))
def query_with_retry(query_engine, query_str):
    return query_engine.query(query_str)

response = query_with_retry(query_engine, 'What did the author write about?')