German Martin
German Martin
@simonfromla @cancan101 Hi guys! I just submitted an idea for a merger retriever that perhaps could help you with this use case? Please take a look or give it a...
> > I did this (I swapped the return type out for `Iterable`): > > ```python > > class CombineRetriever(BaseRetriever): > > def __init__(self, retrievers): > > self.retrievers = retrievers...
> i think it probably makes sense to implement this as a DocumentTransformer rather than putting it on the base VectorStore. happy to help refactor if you'd like Yeap I...
@baskaryan Added it as a document transformer. I'm still not 100% sure this is the best approach. I mean it works, but will force using compressors everywhere when you need...
> > @baskaryan Added it as a document transformer. I'm still not 100% sure this is the best approach. > > I mean it works, but will force using compressors...
> Also, in general: IIUC, this is a re-ordering of documents after retrieval (similar post-processing as something like Cohere re-rank). Re-rank is a vectorstore wrapper: > > https://python.langchain.com/docs/modules/data_connection/retrievers/integrations/cohere-reranker > >...
> Not sure if i'm following it here, EmbeddingsFilter and EmbeddingsRedundantFilter existed before right? The prev PR added EmbeddingsClusteringFilter. The clustering it's a mix of filtering / grouping / re-ordering...
> Yeap the lint stuff it's weird I have black set by default on vscode... but is not catching all the same formatting issues it seems.
@eyurtsev I'm familiar with unit test. I found how are you doing it in the ConfluenceLoader. I will try to have it ready in the next couple of days. Don't...
Go for it! @musicaoriginal2 My tw handler it's messy, because i'm not only do code and I get into a lot local political discussions xD. I'm working in a project...