Commit Graph

7 Commits

Author SHA1 Message Date
George Gevoian
0a34292536 (core) Add telemetry for AI Assistant
Summary: Also fixes a few bugs with some telemetry events not being recorded.

Test Plan: Manual.

Reviewers: paulfitz

Reviewed By: paulfitz

Differential Revision: https://phab.getgrist.com/D3960
2023-07-20 12:50:26 -04:00
Jarosław Sadziński
d13b9b9019 (core) Billing for formula assistant
Summary:
Adding limits for AI calls and connecting those limits with a Stripe Account.

- New table in homedb called `limits`
- All calls to the AI are not routed through DocApi and measured.
- All products now contain a special key `assistantLimit`, with a default value 0
- Limit is reset every time the subscription has changed its period
- The billing page is updated with two new options that describe the AI plan
- There is a new popup that allows the user to upgrade to a higher plan
- Tiers are read directly from the Stripe product with a volume pricing model

Test Plan: Updated and added

Reviewers: georgegevoian, paulfitz

Reviewed By: georgegevoian

Subscribers: dsagal

Differential Revision: https://phab.getgrist.com/D3907
2023-07-10 13:24:08 +02:00
Alex Hall
bb7cf6ba20 (core) Modify prompt so that model may say it cannot help with certain requests.
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
2023-06-27 15:57:56 +02:00
Alex Hall
d88f79bc5e (core) Add cases involving lookups to formula dataset
Summary: I looked through the template documents mentioned in `formula-dataset-index.csv` and selected formulas involving lookups to add to the CSV, particularly nontrivial formulas.

Test Plan: Running the test script on the new dataset gives a score of 47/61 compared to the previous 45/47, i.e. it scores 2/14 on the new entries. Lookups are clearly challenging and we'll need to add more information to the prompt, maybe even consider a more complicated strategy than a single prompt. This diff is purely for expanding the dataset, improving performance will come later.

Reviewers: paulfitz

Reviewed By: paulfitz

Differential Revision: https://phab.getgrist.com/D3931
2023-06-26 13:18:52 +02:00
Alex Hall
52469c5a7e (core) Improve parsing formula from completion
Summary:
The previous code for extracting a Python formula from the LLM completion involved some shaky string manipulation which this improves on.
Overall the 'test results' from `runCompletion` went from 37/47 to 45/47 for `gpt-3.5-turbo-0613`.

The biggest problem that motivated these changes was that it assumed that code was always inside a markdown code block
(i.e. triple backticks) and so if there was no block there was no code. But the completion often consists of *only* code
with no accompanying explanation or markdown. By parsing the completion in Python instead of JS,
we can easily check if the entire completion is valid Python syntax and accept it if it is.

I also noticed one failure resulting from the completion containing the full function (instead of just the body)
and necessary imports before that function instead of inside. The new parsing moves import inside.

Test Plan: Added a Python unit test

Reviewers: paulfitz

Reviewed By: paulfitz

Subscribers: paulfitz

Differential Revision: https://phab.getgrist.com/D3922
2023-06-16 13:38:20 +02:00
Paul Fitzpatrick
51a195bd94
add support for conversational state to assistance endpoint (#506)
* add support for conversational state to assistance endpoint

This refactors the assistance code somewhat, to allow carrying
along some conversational state. It extends the OpenAI-flavored
assistant to make use of that state to have a conversation.
The front-end is tweaked a little bit to allow for replies that
don't have any code in them (though I didn't get into formatting
such replies nicely).

Currently tested primarily through the runCompletion script,
which has been extended a bit to allow testing simulated
conversations (where an error is pasted in follow-up, or
an expected-vs-actual comparison).

Co-authored-by: George Gevoian <85144792+georgegevoian@users.noreply.github.com>
2023-05-08 14:15:22 -04:00
Cyprien P
1ff93f89c2 (core) Porting the AI evaluation script
Summary:
Porting script that run an evaluation against our formula dataset.

To test you need an openai key (see here: https://platform.openai.com/)
or hugging face (it should work as well), then checkout the branch and run

`OPENAI_API_KEY=<my_openai_api_key> node core/test/formula-dataset/runCompletion.js`

Test Plan:
Needs manually testing: so far there is no plan to make it part of CI.

The current score is somewhere around 34 successful prompts over a total of 47.

Reviewers: paulfitz

Reviewed By: paulfitz

Subscribers: jarek

Differential Revision: https://phab.getgrist.com/D3816
2023-03-15 14:54:28 +01:00