Added MultiCandidateChunks which can hold candidates for retrieval across many indices (it's a flat structure to be similar to CandidateChunks and easy to reason about).
JSON serialization support extended for RAGResult, CandidateChunks, and MultiCandidateChunks to increase observability of RAG systems
Added a new search refiner TavilySearchRefiner - it will search the web via Tavily API to try to improve on the RAG answer (see ?refine!).
Introduced a few small utilities for manipulation of nested kwargs (necessary for RAG pipelines), check out getpropertynested, setpropertynested, merge_kwargs_nested.
[BREAKING] change to CandidateChunks where it's no longer allowed to be nested (ie, cc.positions being a list of several CandidateChunks). This is a breaking change for the RAGTools module only. We have introduced a new MultiCandidateChunks types that can refer to CandidateChunks across many indices.
Changed default model for RAGTools.CohereReranker to "cohere-rerank-english-v3.0".
Added
MultiCandidateChunks
which can hold candidates for retrieval across many indices (it's a flat structure to be similar toCandidateChunks
and easy to reason about).JSON serialization support extended for
RAGResult
,CandidateChunks
, andMultiCandidateChunks
to increase observability of RAG systemsAdded a new search refiner
TavilySearchRefiner
- it will search the web via Tavily API to try to improve on the RAG answer (see?refine!
).Introduced a few small utilities for manipulation of nested kwargs (necessary for RAG pipelines), check out
getpropertynested
,setpropertynested
,merge_kwargs_nested
.[BREAKING] change to
CandidateChunks
where it's no longer allowed to be nested (ie,cc.positions
being a list of severalCandidateChunks
). This is a breaking change for theRAGTools
module only. We have introduced a newMultiCandidateChunks
types that can refer toCandidateChunks
across many indices.Changed default model for
RAGTools.CohereReranker
to "cohere-rerank-english-v3.0".