Commit graph

16 commits

Author SHA1 Message Date
Bennet Bo Fenner
aae39071ef
editor: Show hints for using AI features on empty lines (#20824)
Co-Authored-by: Thorsten <thorsten@zed.dev>
Co-Authored-by: Antonio <antonio@zed.dev>

Screenshot:

![screenshot-2024-11-18-17 11
08@2x](https://github.com/user-attachments/assets/610fd7db-7476-4b9b-9465-a3d55df12340)

TODO:
- [x] docs

Release Notes:

- Added inline hints that guide users on how to invoke the inline
assistant and open the assistant panel. (These hints can be disabled by
setting `{"assistant": {"show_hints": false}}`.)

---------

Co-authored-by: Thorsten <thorsten@zed.dev>
Co-authored-by: Antonio <antonio@zed.dev>
Co-authored-by: Thorsten Ball <mrnugget@gmail.com>
2024-11-19 09:41:44 +01:00
Thorsten Ball
aee01f2c50
assistant: Remove low_speed_timeout (#20681)
This removes the `low_speed_timeout` setting from all providers as a
response to issue #19509.

Reason being that the original `low_speed_timeout` was only as part of
#9913 because users wanted to _get rid of timeouts_. They wanted to bump
the default timeout from 5sec to a lot more.

Then, in the meantime, the meaning of `low_speed_timeout` changed in
#19055 and was changed to a normal `timeout`, which is a different thing
and breaks slower LLMs that don't reply with a complete response in the
configured timeout.

So we figured: let's remove the whole thing and replace it with a
default _connect_ timeout to make sure that we can connect to a server
in 10s, but then give the server as long as it wants to complete its
response.

Closes #19509

Release Notes:

- Removed the `low_speed_timeout` setting from LLM provider settings,
since it was only used to _increase_ the timeout to give LLMs more time,
but since we don't have any other use for it, we simply remove the
setting to give LLMs as long as they need.

---------

Co-authored-by: Antonio <antonio@zed.dev>
Co-authored-by: Peter Tripp <peter@zed.dev>
2024-11-15 07:37:31 +01:00
Peter Tripp
291af664e1
Switch to Anthropic -latest tags (#19615)
- Closes: https://github.com/zed-industries/zed/issues/19609

Switches us to using `-latest` tags with Anthropic models instead of
pinning to a specific date version.
See: [Anthropic Model
Docs](https://docs.anthropic.com/en/docs/about-claude/models)

This is a no-op for:
- Claude 3 Opus (`claude-3-opus-20240229`)
- Claude 3 Sonnet (`claude-3-sonnet-20240229`)
- Claude 3 Haiku (`claude-3-haiku-20240307`)

For Claude 3.5 Sonnet this will update us from
`claude-3-5-sonnet-20240620` to `claude-3-5-sonnet-20241022`. We will
also pickup any subsequent model updates automatically when Anthropic
updates the `latest` tag.

This matches the behavior for OpenAI where use `gpt-4o` as the
model_name and not `gpt-4o-2024-08-06`.
2024-10-23 15:13:52 -04:00
Peter Tripp
87cc208f9f
docs: Fix ollama available_models example (#18842) 2024-10-07 21:04:36 -04:00
Peter Tripp
03c7f08581
docs: Ollama api_url improvements (#18440) 2024-09-27 10:29:49 -04:00
Antonio Scandurra
15b4130fa5
Introduce the ability to cycle between alternative inline assists (#18098)
Release Notes:

- Added a new `assistant.inline_alternatives` setting to configure
additional models that will be used to perform inline assists in
parallel.

---------

Co-authored-by: Nathan <nathan@zed.dev>
Co-authored-by: Roy <roy@anthropic.com>
Co-authored-by: Adam <wolffiex@anthropic.com>
2024-09-19 17:50:00 -06:00
Peter Tripp
67f149a4bc
Ollama: Specify keep_alive via settings (#17906) 2024-09-16 18:47:25 -04:00
Peter Tripp
d245f5e75c
OpenAI o1-preview and o1-mini support (#17796)
Release Notes:

- Added support for OpenAI o1-mini and o1-preview models.

---------

Co-authored-by: Jason Mancuso <7891333+jvmncs@users.noreply.github.com>
Co-authored-by: Bennet <bennet@zed.dev>
2024-09-13 16:23:55 -04:00
Peter Tripp
fb9d01b0d5
assistant: Add display_name for OpenAI and Gemini (#17508) 2024-09-10 13:41:06 -04:00
Marshall Bowers
fe53113ee4
docs: Update the example custom API URL for the Assistant (#17432)
This PR updates the docs showcasing how to use a custom API URL for the
Assistant to only use a base URL (without a path).

Closes #17431.

Release Notes:

- N/A
2024-09-05 12:55:29 -04:00
Peter Tripp
c909bc09db
docs: Fix Ollama formatting; remove stale link to stable Nix package (#17158) 2024-08-30 09:47:36 -04:00
Peter Tripp
b62e63349b
Ollama max_tokens settings (#17025)
- Support `available_models` for Ollama
- Clamp default max tokens (context length) to 16384.
- Add documentation for ollama context configuration.
2024-08-30 08:52:00 -04:00
Danilo Leal
ec98e71190
docs: Add tweaks to the assistant Configuration page (#16632)
This PR adds some slight writing tweaks to the Configuration page under
the assistant section. As a general rule of thumb, I usually avoid
adding links in the word "here" when that's within a sentence; a more
descriptive approach can be clearer.

---

Release Notes:

- N/A
2024-08-21 19:26:15 -03:00
Bennet Bo Fenner
0c980cde74
docs: Cleanup assistant configuration documentation (#16526)
Release Notes:

- N/A
2024-08-20 17:40:19 +02:00
Bennet Bo Fenner
c251a50e41
assistant: Update docs (#16515)
- Fix links on assistant page to subpages
- Mention the configuration view in the `configuration.md` and document
more settings

Release Notes:

- N/A

---------

Co-authored-by: Piotr <piotr@zed.dev>
2024-08-20 14:42:10 +02:00
Nate Butler
1f0dc8b754
Expand assistant docs (#16501)
This PR significantly expands the assistant documentation, breaking it
out into sections, adding examples and further documenting features.

This PR introduces a convention in docs for swapping keybindings for mac
vs linux:

`<kbd>cmd-enter|ctrl-enter</kbd>`

In the above example, the first will be shown for mac, the second for
linux or windows.

TODO:

- [ ] Fix table style (for `/assistant/configuration`)
- [x] Add script to swap keybindings based on platform
- It should take in this format: [`cmd-n` (mac)|`ctrl-n`(linux)] and
return just the correct binding for the viewer's platform.
- [ ] Add image/video assets (non-blocking)

Release Notes:

- Updated assistant documentation
2024-08-19 23:50:09 -04:00