David S. Batista
David S. Batista
The `2.1.x` patch releases aren't listed but the `2.0.1` is. https://haystack.deepset.ai/release-notes
Within the context of the the LLM-based evaluators, the replies given by OpenAI contain different values for `finish_reason`: for instance, `content filter` was triggered: ``` The completion for index 0...
**Is your feature request related to a problem? Please describe.** The LLM-based evaluators are non-deterministic, and this can be an issue in replicating and comparing evaluation results. **Describe the solution...
Adding two advanced use case notebooks: - automatic metadata extraction and enrichment for indexing - extracting metadata filters from a user query
The MRR evaluator always returns 0.0 when we index/retrieve chunks of the original document. - Related to this: https://github.com/deepset-ai/haystack/blob/main/haystack/components/evaluators/document_mrr.py#L77 - Because we index/retrieve not the original document with its full...
### Related Issues - fixes [#7905](https://github.com/deepset-ai/haystack/issues/7905) ### Proposed Changes: pass the `meta` entry from openai api to the result for all the LLM-based evaluators, containing the following fields: - model...
Auto-merging retrieval aims to combine (or merge) information from multiple sources or segments of text to create a more comprehensive and contextually relevant response to a query. This approach is...