[UPDATE] The Use of BM25 for Semantic Search Example in Unit 2.1 retrieval_agents.mdx

The `PartyPlanningRetrieverTool` subclass in the example retrieval code currently uses BM25 (`BM25Retriever`), which I believe is a lexical search algorithm. However, the description labels this as a "semantic search," which may cause confusion. Unlike vector-based retrieval methods, BM25 does not capture the meaning or context of words but instead relies on keyword frequency and ranking.
This builds on the clarification from my previous PR (# 279 merged and closed), which revised the definition of vector databases and semantic search to avoid similar confusion.

Proposed Fix:
Option 1: Clearly state that this code example uses a keyword retrieval method, which is BM25, rather than a semantic search.
Option 2: Replace BM25 with a vector-based retriever to demonstrate a true semantic search approach.

Let me know what you think and if you'd like any help.