private-gpt
private-gpt copied to clipboard
Ingesting large number of files
trafficstars
I am trying to ingest about 340k files of about 30Gb size in total. After few hours of ingesting I got SQLite error:
sqlite3.DataError: string or blob too big
Has anyone ever faced similar issue? Is it okay to ingest such amount of data? Is it really possible to avoid SQLite restrictions?
Its using SQLLite as its using simple (filesystem based) indexes and doc stores. Once this https://github.com/imartinez/privateGPT/pull/1706 is pulled, those things can be moved into Postgres.