Commit graph

47 commits

Author SHA1 Message Date
KCaverly
3712794e56 move OpenAILanguageModel to providers folder 2023-10-22 13:47:28 +02:00
KCaverly
a62baf34f2 rename templates to prompts in ai crate 2023-10-22 13:46:49 +02:00
KCaverly
a874a09b7e added openai language model tokenizer and LanguageModel trait 2023-10-17 16:21:03 -04:00
KCaverly
40755961ea added initial template outline 2023-10-16 11:54:32 -04:00
KCaverly
68c37ca2a4 move embedding provider to ai crate 2023-09-22 09:33:59 -04:00
KCaverly
48e151495f introduce ai crate with completion providers 2023-09-21 22:44:56 -04:00
KCaverly
5f6334696a rename ai crate to assistant crate 2023-09-21 21:54:59 -04:00
Joseph T. Lyons
5df9a57a8b
Add assistant events (#2978)
Add assistant events

Release Notes:

- N/A
2023-09-15 15:25:35 -04:00
Antonio Scandurra
6d9333dc3b Add a failing test for codegen autoindent 2023-09-11 14:35:15 +02:00
Antonio Scandurra
02078140c0 Extract code generation logic into its own module 2023-09-11 11:25:37 +02:00
Antonio Scandurra
27c90f12f6 Merge remote-tracking branch 'origin/main' into ai-refactoring 2023-08-25 13:37:32 +02:00
Antonio Scandurra
c1bd035875 Rework inline assistant 2023-08-25 11:39:27 +02:00
Antonio Scandurra
c1d9b37dbc Move to an inline refactoring prompt 2023-08-24 15:46:18 +02:00
Antonio Scandurra
a9871a7a70 Add randomized tests for incremental diff 2023-08-23 09:09:01 +02:00
Antonio Scandurra
1ae5a909cd Start on a custom diff implementation 2023-08-22 12:07:41 +02:00
Joseph T. Lyons
a836f9c23d
Add a default_open_ai_model setting for the assistant (#2876)
[This PR has been sitting around for a
bit](https://github.com/zed-industries/zed/pull/2845). I received a bit
of mixed opinions from the team on how this setting should work, if it
should use the full model names or some simpler form of it, etc. I went
ahead and made the decision to do the following:

- Use the full model names in settings - ex: `gpt-4-0613`
- Default to `gpt-4-0613` when no setting is present
- Save the full model names in the conversation history files (this is
how it was prior) - ex: `gpt-4-0613`
- Display the shortened model names in the assistant - ex: `gpt-4`
- Not worry about adding an option to add custom models (can add in a
follow-up PR)
- Not query what models are available to the user via their api key (can
add in a follow-up PR)

Release Notes:

- Added a `default_open_ai_model` setting for the assistant (defaults to
`gpt-4-0613`).

---------

Co-authored-by: Mikayla <mikayla@zed.dev>
2023-08-22 02:55:27 -04:00
Antonio Scandurra
42f02eb4e7 Incrementally diff input coming from GPT 2023-08-21 15:13:26 +02:00
Antonio Scandurra
3ad7f528cb Start on a refactoring assistant 2023-08-18 17:58:22 +02:00
Antonio Scandurra
5408275c7a Filter out non-json files when loading conversations 2023-07-06 14:38:05 +02:00
Antonio Scandurra
c38bf2de33 Sort conversations in descending chronological order 2023-06-23 10:05:21 +02:00
Antonio Scandurra
a011ced698 Allow loading a previously-saved conversation 2023-06-21 16:06:09 +02:00
Antonio Scandurra
06701e78aa WIP 2023-06-21 11:44:32 +02:00
Nathan Sobo
bd7f8e8b38 Scan conversations dir on assistant panel open and on changes
Co-Authored-By: Julia Risley <julia@zed.dev>
2023-06-20 16:19:43 -06:00
Nathan Sobo
230b4d237e Add SavedConversation::list() method
Co-Authored-By: Kyle Caverly <kyle@zed.dev>
2023-06-20 13:29:34 -06:00
Antonio Scandurra
c83a918a7e Merge remote-tracking branch 'origin/main' into save-conversations 2023-06-20 18:16:40 +02:00
Antonio Scandurra
cb55356106 WIP 2023-06-19 17:53:05 +02:00
Nathan Sobo
882009bc75 Save conversations to ~/.config/zed/conversations
Still need to implement loading / listing.
I'd really be rather write operations to a database. Maybe we
should be auto-saving? Integrating with panes? I just did
the simple thing for now.
2023-06-16 16:15:07 -06:00
Antonio Scandurra
ef7ec265c8 Cycle message roles on click
Co-Authored-By: Nathan Sobo <nathan@zed.dev>
2023-06-06 18:45:08 +02:00
Antonio Scandurra
ac7178068f Include message headers in copied assistant text
Co-Authored-By: Nathan Sobo <nathan@zed.dev>
2023-06-06 18:18:04 +02:00
Antonio Scandurra
bef6932da7 Avoid accidentally taking the api_key when requesting an assist 2023-06-05 11:25:21 +02:00
Antonio Scandurra
d0aff65b1c Allow moving the assistant panel to other docks 2023-06-02 10:55:19 +02:00
Antonio Scandurra
55c8c6d3fb Allow adding new contexts 2023-06-02 10:29:22 +02:00
Nathan Sobo
ffbfbe422b WIP: Not sure I actually want to rip this out 2023-05-26 16:11:58 -06:00
Nathan Sobo
3904971bd8 Hide assistant gutter 2023-05-26 15:38:03 -06:00
Nathan Sobo
80080a43e4 Start on an assistant panel based on multi-buffers
Each message is represented as a multibuffer excerpt to allow for
fluid editing of the conversation transcript.

Co-Authored-By: Antonio Scandurra <antonio@zed.dev>
2023-05-26 10:09:55 -06:00
Antonio Scandurra
7e1ea8f274 Remove stray dbg! 2023-05-25 12:04:41 +02:00
Nathan Sobo
26051de160 Clean up 2023-05-24 11:08:00 -06:00
Nathan Sobo
d495c1b804 Only run AI agent on dev and preview 2023-05-24 10:58:33 -06:00
Nathan Sobo
d934da1905 WIP 2023-05-23 15:25:34 -06:00
Nathan Sobo
5362e7d346 WIP 2023-05-23 01:52:37 -06:00
Nathan Sobo
394e87d17c WIP 2023-05-23 01:23:01 -06:00
Nathan Sobo
0de5a444d3 WIP 2023-05-23 00:22:21 -06:00
Nathan Sobo
234dbc3ca9 WIP 2023-05-23 00:16:44 -06:00
Nathan Sobo
c4d88bc529 WIP 2023-05-22 23:43:02 -06:00
Nathan Sobo
30de64845f WIP 2023-05-22 23:11:27 -06:00
Nathan Sobo
7e6cccfa3d WIP: Stream in completions
Drop dependency on tokio introduced by async-openai and do it ourselves.

The approach I'm taking of replacing instead of appending is causing issues. Need to just append.
2023-05-22 20:28:22 -06:00
Nathan Sobo
912fd23006 Parse markdown into an OpenAI chat completion request 2023-05-20 09:43:12 -06:00