Hi great Video, I have one question, To label the ground truth dataset did you use another LLM or did you label it by hand with human annotators? If so, did you use any software for the annotations or did you directly read the PDF and write a JSON by hand?
Excited to try out those models! Evaluating latency, cost, and accuracy is key for top-notch pipelines. Let’s see how the Lang Chain tools stack up!
Hi great Video, I have one question, To label the ground truth dataset did you use another LLM or did you label it by hand with human annotators? If so, did you use any software for the annotations or did you directly read the PDF and write a JSON by hand?
Really useful
Thats super useful!!!!