Is anyone else seeing consistently low relevance scores from Copilot’s real-time assist? We’re on Genesys Cloud, API v2. The expectation is the platform should surface articles exceeding a score of 0.7, but it’s consistently below 0.5 - basically doing jack all.
The knowledge base connector syncs fine - no 503s this time, thankfully. Article metadata is populated correctly, and the intent mapping in the Copilot UI looks sound. I’ve checked the POST /api/v2/copilot/knowledge/articles/relevance payload; it’s returning these scores.
{
"articleId": "kb-1234",
"relevanceScore": 0.32,
"matchedIntents": ["billing", "payment"],
"queryText": "payment issue"
}
The documentation states the relevance score considers semantic similarity and the article’s popularity (view count, upvotes) - https://developer.genesys.cloud/reference/copilot/knowledge-articles-relevance. Low view counts could be the culprit. It’s worth noting, new articles consistently score lower.