[STESOL-554] Have eval script use main search function and add sources to eval answers

[brikin01]

Summary

• Route retrieval evaluation through the shared arm_kb_search.search() path so eval matches production search behavior
• Set explicit search candidate depth from requested result count, avoiding accidental coupling to deduplication candidate count
• Add alternate expected URLs for eval questions where multiple relevant sources satisfy the query.
• Bump package version to 0.2.0.

[NeethuESim]

@brikin01 why is this line added here ? Won't this reduce the number of relevant chunks ?

[brikin01]

This line makes the default runtime search use the same candidate-depth calculation as the original evaluate_retrieval.py (see L59 of the original file).

For a requested k=5, that means examining 100 dense and BM25 candidates. Without this line, hybrid_search() calculates its default from deduplication_candidate_count(k), which is 50, resulting in a candidate depth of 1,000.

Reducing the depth from 1,000 to 100 can theoretically exclude a relevant chunk ranked below 100 in the initial retrieval stage, but it does not reduce the requested number of final results (although as mentioned above, we were never actually using a depth of 1000 in this particular eval script). Also, I tested the retrieval evaluation with both values. 100 produced equivalent or slightly better results while requiring less search and reranking work, so 100 seems like the better tradeoff here.

[NeethuESim]

LGTM