[I] Add an opt-in Parallel Search MCP web-research example [hamilton]

["georgeatparallel (via GitHub)" <gi...@apache.org>]

georgeatparallel opened a new issue, #1767:
URL: https://github.com/apache/hamilton/issues/1767

   **Is your feature request related to a problem? Please describe.**
   Hamilton's knowledge-retrieval example shows how to work with arXiv articles. A companion example could help users gather current web sources and excerpts for a research or RAG pipeline without setting up search credentials.
   
   **Describe the solution you'd like**
   Would a standalone example under `examples/LLM_Workflows/parallel_research/` fit here? I'd use [Parallel Search MCP](https://docs.parallel.ai/integrations/mcp/search-mcp) with separate Hamilton nodes to search a topic, select a bounded set of URLs, fetch page excerpts, and format context with source links. Anonymous search uses Fast mode and requires no account or API key.
   
   The example would have its own dependencies and run instructions, preserve existing examples and defaults, and require no LLM to retrieve the source material. I'd test the Hamilton execution path, response handling, timeouts and service errors, plus the documented anonymous setup.
   
   **Describe alternatives you've considered**
   The existing arXiv example fits scholarly retrieval. A separate web-research example would cover broader, current sources without changing that workflow or Hamilton's MCP server.
   
   **Additional context**
   I work at Parallel. This proposal was generated by AI using OpenAI Codex.


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: notifications-unsubscribe@hamilton.apache.org.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org