Gabriel Altay

metadata equality filter loss of performance

1

in previous versions of the langchain postgres implementation i was able to get sub-second latency on queries that filtered by a string id in the embedding metadata ... something like,...

Potential solutions for being able to index different vector sizes?

8

Curious if anyone was thinking about re-writing the table schemas such that collections map to different tables (and would therefore support indexing different embedding vector sizes) ? ``` embedding_length: The...

"text" and "tokens" are hard coded as column names in the text_data module. might be nice to be able to provide different column names as args

A fresh pip install leads to, ```bash ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the...