Gabriel Altay

I think the issue is that the current setup creates two tables, * (collection_store) `langchain_pg_collection` * (embedding_store) `langchain_pg_embedding` specifying a collection_name that does not exist will add a row to...

oh, nice find @patdmob , I'll give that a try!

that does work, good call. it turns out i'm still getting high latency but now I think its in the way that the metadata is indexed (collection_ids and/or metadata in...

created a new issue for the metadata filtering issue https://github.com/langchain-ai/langchain-postgres/issues/34

to confirm the speed change i hacked in this command, ```python filter_clauses = self.EmbeddingStore.cmetadata["some_id"].astext == filter["some_value"] ``` here (https://github.com/langchain-ai/langchain-postgres/blob/main/langchain_postgres/vectorstores.py#L911) which is significantly faster w/o an index than the json_path_ops appears...