Closes#4424.
A few design decisions that may need some rethinking or later PRs:
* Other providers have a check for authentication. I use this
opportunity to fetch the models which doubles as a way of finding out if
the Ollama server is running.
* Ollama has _no_ API for getting the max tokens per model
* Ollama has _no_ API for getting the current token count
https://github.com/ollama/ollama/issues/1716
* Ollama does allow setting the `num_ctx` so I've defaulted this to
4096. It can be overridden in settings.
* Ollama models will be "slow" to start inference because they're
loading the model into memory. It's faster after that. There's no UI
affordance to show that the model is being loaded.
Release Notes:
- Added an Ollama Provider for the assistant. If you have
[Ollama](https://ollama.com/) running locally on your machine, you can
enable it in your settings under:
```jsonc
"assistant": {
"version": "1",
"provider": {
"name": "ollama",
// Recommended setting to allow for model startup
"low_speed_timeout_in_seconds": 30,
}
}
```
Chat like usual
<img width="1840" alt="image"
src="https://github.com/zed-industries/zed/assets/836375/4e0af266-4c4f-4d9e-9d74-1a91f76a12fe">
Interact with any model from the [Ollama
Library](https://ollama.com/library)
<img width="587" alt="image"
src="https://github.com/zed-industries/zed/assets/836375/87433ac6-bf87-4a99-89e1-96a93bf8de8a">
Open up the terminal to download new models via `ollama pull`:
This PR adds a tag handler for collecting crate items from rustdoc's
HTML output.
This will serve as the foundation for getting more insight into a
crate's contents.
Release Notes:
- N/A
TODO:
- [x] Finish GPUI changes on other operating systems
This is a largely internal change to how we report data to our
diagnostics and telemetry. This PR also includes an update to our blade
backend which allows us to report errors in a more useful way when
failing to initialize blade.
Release Notes:
- N/A
---------
Co-authored-by: Conrad Irwin <conrad.irwin@gmail.com>
This PR improves the `/fetch` command with better support for URLs that
return JSON content.
JSON response bodies will now be pretty-printed and placed within a
Markdown code block:
<img width="690" alt="Screenshot 2024-06-10 at 3 39 52 PM"
src="https://github.com/zed-industries/zed/assets/1486634/4a7c1cb7-9f5b-4a63-9e8e-5168bf9a6625">
Release Notes:
- Improved the handling of JSON response bodies in the `/fetch` command
in the Assistant.
This PR adds a `/now` command to the Assistant for indicating the
current date and time to the model.
Release Notes:
- Added `/now` command to the Assistant for getting the current date and
time.
This PR fixes an issue where the prompt library did not properly have
the UI font or rem size set.
Since it is being opened in a new window, we need to re-initialize these
values the same way we do in the main window.
Release Notes:
- N/A
Release Notes:
- Improved UX for the inline assistant. It will now automatically wrap
when the text gets too long, and you can insert newlines using
`shift-enter`.
This PR overhauls the HTML to Markdown conversion functionality in order
to make it more pluggable. This will ultimately allow for supporting a
variety of different HTML input structures (both natively and via
extensions).
As part of this, the `rustdoc_to_markdown` crate has been renamed to
`html_to_markdown`.
The `MarkdownWriter` now accepts a list of trait objects that can be
used to drive the conversion of the HTML into Markdown. Right now we
have some generic handler implementations for going from plain HTML
elements to their Markdown equivalents, as well as some rustdoc-specific
ones.
Release Notes:
- N/A
This could still use some improvement UI-wise but the user experience
should be a lot better.
- [x] Show in "Window" application menu
- [x] Load prompt as it's selected in the picker
- [x] Refocus picker on `esc`
- [x] When creating a new prompt, if a new prompt already exists and is
unedited, activate it instead
- [x] Add `/default` command
- [x] Evaluate /commands on prompt insertion
- [x] Autocomplete /commands (but don't evaluate) during prompt editing
- [x] Show token count using the settings model, right-aligned in the
editor
- [x] Picker
- [x] Sorted alpha
- [x] 2 sublists
- Default
- Empty state: Star a prompt to add it to your default prompt
- Otherwise show prompts with star on hover
- All
- Move prompts with star on hover
Release Notes:
- N/A
This PR adds a new `/fetch` slash command to the Assistant for fetching
the content of an arbitrary URL as Markdown.
Currently it's just using the same HTML to Markdown conversion that
`/rustdoc` uses, but I'll be working to refine the output to be more
widely useful.
Release Notes:
- N/A
This PR updates the `/rustdoc` slash command to use local docs built
with `cargo doc`.
If the docs for a particular crate/module are available locally, those
will be used. Otherwise, it will fall back to retrieving the docs from
`docs.rs`.
The placeholder output for the slash command will indicate which source
was used for the docs:
<img width="289" alt="Screenshot 2024-06-03 at 4 13 42 PM"
src="https://github.com/zed-industries/zed/assets/1486634/729112e4-80ca-4f08-bdb3-88fc950351c3">
Release Notes:
- N/A
Using the file system as a database seems like it's easy, but it's
actually a real pain. I'd like to use LMDB to store the prompts locally
so we have more control. We can always add an export option, but I want
the source of truth to be somewhere other than the file system.
So far, I have a PromptStore which is global to the application and can
be initialized on startup. Then there's a `PromptLibrary` which is
intended to be the root of a new kind of Zed window. I haven't actually
seen pixels yet, but I've sketched out the basics needed to create a new
prompt, save, etc.
Still lots to figure out but the foundations of being backed by a DB and
rendering in an independent window are in place.
/cc @iamnbutler @as-cii
Release Notes:
- N/A
---------
Co-authored-by: Antonio Scandurra <me@as-cii.com>
This is still pretty raw, so I'd like to hold off on shipping it to all
users.
Release Notes:
- Hide the prompt library for non-staff until it is in a more complete
state.
This PR adds a `/rustdoc` slash command for retrieving and inserting
rustdoc docs into the Assistant.
Right now the command accepts the crate name as an argument and will
return the top-level docs from `docs.rs`.
Release Notes:
- N/A
We should reintroduce this as part of the prompt library.
Release Notes:
- Removed an over-eager system prompt from the assistant that was
causing misbehavior. Going forward, our intent is to always let you
observe and edit text before we send it.
---------
Co-authored-by: Marshall <marshall@zed.dev>
- Confirming a completion now runs the command immediately
- Hitting `enter` on a line with a command now runs it
- The output of commands gets folded away and replaced with a custom
placeholder
- Eliminated ambient context
<img width="1588" alt="image"
src="https://github.com/zed-industries/zed/assets/482957/b1927a45-52d6-4634-acc9-2ee539c1d89a">
Release Notes:
- N/A
---------
Co-authored-by: Nathan Sobo <nathan@zed.dev>
Adds the following features to the prompt manager:
- New prompt – Create a new prompt from the UI. It will only persist if
it is saved.
- Save prompt – Save a prompt by clicking the save button in the UI. A
keybinding will be added for this in the future.
- Reveal prompt - Show the selected prompt on the file system. Only
available for saved prompts.
New prompts that are saved will use the
`{slugified_title}_{ver}_{id}.md` format which all imported prompts will
move to in the near future.
Also orders prompts in alphabetical order by default.
Release Notes:
- N/A
This PR replaces an `expect` with a precondition check to avoid a panic
if the `LspAdapterDelegate` isn't set when invoking a slash command.
Release Notes:
- N/A
Moved some things around so prompts now always have front-matter to
return, either by creating a prompt with default front-matter, or
bailing earlier on importing the prompt to the library.
In the future we'll improve visibility of malformed prompts in the
`prompts` folder in the prompt manager UI.
Fixes:
- Prompts inserted with the `/prompt` command now only include their
body, not the entire file including metadata.
- Prompts with an invalid title will now show "Untitled prompt" instead
of an empty line.
Release Notes:
- N/A
This PR adds initial support for defining slash commands for the
Assistant from extensions.
Slash commands are defined in an extension's `extension.toml`:
```toml
[slash_commands.gleam-project]
description = "Returns information about the current Gleam project."
requires_argument = false
```
and then executed via the `run_slash_command` method on the `Extension`
trait:
```rs
impl Extension for GleamExtension {
// ...
fn run_slash_command(
&self,
command: SlashCommand,
_argument: Option<String>,
worktree: &zed::Worktree,
) -> Result<Option<String>, String> {
match command.name.as_str() {
"gleam-project" => Ok(Some("Yayyy".to_string())),
command => Err(format!("unknown slash command: \"{command}\"")),
}
}
}
```
Release Notes:
- N/A
This PR extracts the `SlashCommand` trait (along with the
`SlashCommandRegistry`) from the `assistant` crate.
This will allow us to register slash commands from extensions without
having to make `extension` depend on `assistant`.
Release Notes:
- N/A
Kyle Kelley
Marshall Bowers
Mikayla MakiandConrad Irwin
Antonio Scandurra
slowlydev
Nate Butler
Bennet Bo Fenner
