Do I need to know machine learning to use Truvec?
Do I need to know machine learning to use Truvec?
Does Truvec evaluate the answers my chatbot writes?
Does Truvec evaluate the answers my chatbot writes?
Which embedding models are supported?
Which embedding models are supported?
Can I test hybrid search and rerankers?
Can I test hybrid search and rerankers?
Why does a reranker make the cost per query jump?
Why does a reranker make the cost per query jump?
How many documents do I need?
How many documents do I need?
How many test questions do I need?
How many test questions do I need?
How much does an evaluation cost?
How much does an evaluation cost?
Are my documents sent to third parties?
Are my documents sent to third parties?
Why did scores change when I re-ran the same evaluation?
Why did scores change when I re-ran the same evaluation?
Can I evaluate the chunks my production pipeline already produces?
Can I evaluate the chunks my production pipeline already produces?
Can I compare chunking strategies?
Can I compare chunking strategies?
Can I edit a committed golden dataset?
Can I edit a committed golden dataset?
Can I export a golden dataset?
Can I export a golden dataset?
Can I use Truvec programmatically?
Can I use Truvec programmatically?