* Introduces new configuration variables for OIDC:
- GRIST_OIDC_IDP_ENABLED_PROTECTIONS
- GRIST_OIDC_IDP_ACR_VALUES
- GRIST_OIDC_IDP_EXTRA_CLIENT_METADATA
* Implements all supported protections in oidc/Protections.ts
* Includes a better error page for failed OIDC logins
* Includes some other improvements, e.g. to logging, to OIDC
* Adds a large unit test for OIDCConfig
* Adds support for SERVER_NODE_OPTIONS for running tests
* Adds to documentation/develop.md info about GREP_TESTS, VERBOSE, and SERVER_NODE_OPTIONS.
Start documenting the databases including:
* document ACL and other tables
* Permissions
* Groups, secrets, and other tables
---------
Co-authored-by: jordigh <jordigh@octave.org>
Summary:
Added OPENAI_API_KEY and GRIST_FORMULA_ASSISTANT to the README. GRIST_FORMULA_ASSISTANT may be removed in the long term, but for now the goal is just to get something into the grist-core README quickly for self-hosters.
Removed `documentation/llm.md` because it's outdated and not really providing value.
Test Plan: none
Reviewers: paulfitz
Reviewed By: paulfitz
Differential Revision: https://phab.getgrist.com/D3963
Summary:
This tweaks the prompting so that the user's message is given on its own instead of as a docstring within Python. This is so that the prompt makes sense when:
- the user asks a question such as "Can you write me a formula which does ...?" rather than describing their formula as a docstring would, or
- the user sends a message that doesn't ask for a formula at all (https://grist.slack.com/archives/C0234CPPXPA/p1687699944315069?thread_ts=1687698078.832209&cid=C0234CPPXPA)
Also added wording for the model to refuse when the user asks for something that the model cannot do.
Because the code (and maybe in some cases the model) for non-ChatGPT models relies on the prompt consisting entirely of Python code produced by the data engine (which no longer contains the user's message) those code paths have been disabled for now. Updating them now seems like undesirable drag, I think it'd be better to revisit this when iteration/experimentation has slowed down and stabilised.
Test Plan:
Added entries to the formula dataset where the response shouldn't contain a formula, indicated by the value `1` for the new column `no_formula`.
This is somewhat successful, as the model does refuse to help in some of the new test cases, but not all. Performance on existing entries also seems a bit worse, but it's hard to distinguish this from random noise. Hopefully this can be remedied in the future with more work, e.g. automatic followup messages containing example inputs and outputs.
Reviewers: paulfitz
Reviewed By: paulfitz
Subscribers: dsagal
Differential Revision: https://phab.getgrist.com/D3936
Summary: This is a backend part for the formula AI.
Test Plan: New tests
Reviewers: paulfitz
Reviewed By: paulfitz
Subscribers: cyprien
Differential Revision: https://phab.getgrist.com/D3786
