mrm1001

At the moment, we only support OpenAI generator, but there has been demand in the community to use other models, such as Anthropic's Claude LLMs. Below is an example from...

**Is your feature request related to a problem? Please describe.** At the moment, users need to run 2 pipelines to get evaluation metrics: the pipeline that iterates over the documents...

Motivation: In order to have a soft launch of this new (and unique) feature of Haystack, it would help to have some end-to-end example other than the feature usage example...

Add default "else" branch to the conditional router

2

When adding a conditional router with many branching options, it would be good to have an easy way to define a default "catch-all" branch in case the other conditions are...

**Context** Naive RAG starts to fail on more complex type of queries, where information might be spread across different chunks or document sources. The type of queries where it does...

Handle errors separately in evaluators and the run results

1

**Context** When running the evaluators over larger datasets, depending on the model, it is very common to run into LLM errors where the output is not valid JSON. For example,...