Commit Graph

15 Commits (01e582f15b0a617c46b131a00c499cdbf201482e)

Author SHA1 Message Date
Adam Treat 01e582f15b First attempt at providing a persistent chat list experience.
Limitations:

1) Context is not restored for gpt-j models
2) When you switch between different model types in an existing chat
   the context and all the conversation is lost
3) The settings are not chat or conversation specific
4) The sizes of the chat persisted files are very large due to how much
   data the llama.cpp backend tries to persist. Need to investigate how
   we can shrink this.
1 year ago
Adam Treat db094c5b92 More extensive usage stats to help diagnose errors and problems in the ui. 1 year ago
Adam Treat f8c3ae6cc7 Some more startup info to help determine what hardware we need to support. 1 year ago
Adam Treat 925ad70833 Turn the chat list into a model. 1 year ago
Adam Treat 414a12c33d Major refactor in prep for multiple conversations. 1 year ago
Adam Treat cd41eb3280 Don't attempt to send shutdown which won't work anyway. 1 year ago
Adam Treat 869175bc06 Send optout for real and only once. 1 year ago
Adam Treat 812431f78d New startup dialog features. 1 year ago
Adam Treat 5c3c1317f8 Track check for updates. 1 year ago
Adam Treat eafb98b3a9 Initial support for opt-in telemetry. 1 year ago
Adam Treat ac9d9b9476 Add debugging code for ssl errors. 1 year ago
Adam Treat 243268b59a Disable ssl handshake for now. 1 year ago
Adam Treat ee7a14ec45 Update the datalake support. 1 year ago
Adam Treat 876f0537b4 Perform a health check on the datalake before we enable network. 1 year ago
Adam Treat b8fcd406dc New thumbs up/down support for gpt4all-datalake. 1 year ago