Paul Fitzpatrick 0be858c19d allow AI Assistance to run against any chat-completion-style endpoint (#630) ...

This adds an ASSISTANT_CHAT_COMPLETION_ENDPOINT which can be used
to enable AI Assistance instead of an OpenAI API key. The assistant
then works against compatible endpoints, in the mechanical sense.
Quality of course will depend on the model. I found some tweaks
to the prompt that work well both for Llama-2 and for OpenAI's models,
but I'm not including them here because they would conflict with some
prompt changes that are already in the works.

Co-authored-by: Alex Hall <alex.mojaki@gmail.com>

2023-08-18 16:14:42 -04:00

..

declarations

(core) disentangle some server tests, release to core, add GRIST_PROXY_AUTH_HEADER test

2022-03-24 15:11:32 -04:00

lib

allow AI Assistance to run against any chat-completion-style endpoint (#630)

2023-08-18 16:14:42 -04:00

utils

(core) sanitizing redis errors

2023-06-06 10:51:17 +02:00

companion.ts

(core) Add Support Grist page and nudge

2023-07-04 17:36:59 -04:00

declarations.d.ts

(core) Faster builds all around.

2022-07-04 10:42:40 -04:00

devServerMain.ts

REQUEST now supports POST (#588)

2023-07-30 15:13:43 -04:00

generateCheckpoint.ts

(core) get all tests working under python3/gvisor

2021-10-18 17:44:15 -04:00

generateInitialDocSql.ts

(core) Add optional telemetry to grist-core

2023-06-07 12:00:51 -04:00

localization.ts

only offer languages that have been marked as substantially complete (#466)

2023-03-28 10:59:17 -04:00

mergedServerMain.ts

(core) resolved some divergence in mergedServerMain

2023-07-10 07:50:52 -04:00

tsconfig.json

(core) Simple localization support and currency selector.

2021-08-26 13:36:49 -07:00