Andreas Geert Motzfeldt
Andreas Geert Motzfeldt
### Potential concern: In the [self-grading example](https://github.com/promptfoo/promptfoo/blob/main/examples/custom-grading-prompt/promptfooconfig.yaml), you utilise LLMs to judge text quality using a form-based method. I've spotted two problems with this scoring approach: 1. Often, one number,...
We summarize our planned features in this issue. This issue will keep being updated. ## Dataloaders: Support more datasets for common IR & Gen AI ##### Primary: - [x] MSMarco...
**WHY** Currently, VOD Training only complies with document-level embeddings. This represents each document with a single-vector representation, constraining the granularity of the contextual information captured. ColBERT introduced a more complex...
**WHY** The costs of accessing, fine-tuning and querying foundation models to perform new tasks are large. Given these costs, access to performant LLMs has been gated behind expensive and often...
``` yaml.scanner.ScannerError: while scanning a simple key in "", line 39, column 1 could not find expected ':' in "", line 41, column 11 ``` The error indicates that the...