This introduces semantic indexing in Zed based on chunking text from
files in the developer's workspace and creating vector embeddings using
an embedding model. As part of this, we've created an embeddings
provider trait that allows us to work with OpenAI, a local Ollama model,
or a Zed hosted embedding.
The semantic index is built by breaking down text for known
(programming) languages into manageable chunks that are smaller than the
max token size. Each chunk is then fed to a language model to create a
high dimensional vector which is then normalized to a unit vector to
allow fast comparison with other vectors with a simple dot product.
Alongside the vector, we store the path of the file and the range within
the document where the vector was sourced from.
Zed will soon grok contextual similarity across different text snippets,
allowing for natural language search beyond keyword matching. This is
being put together both for human-based search as well as providing
results to Large Language Models to allow them to refine how they help
developers.
Remaining todo:
* [x] Change `provider` to `model` within the zed hosted embeddings
database (as its currently a combo of the provider and the model in one
name)
Release Notes:
- N/A
---------
Co-authored-by: Nathan Sobo <nathan@zed.dev>
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Conrad Irwin <conrad@zed.dev>
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
Co-authored-by: Antonio <antonio@zed.dev>
Co-authored-by: Antonio <antonio@zed.dev>
Resurrected this from some assistant work I did in Spring of 2023.
- [x] Resurrect streaming responses
- [x] Use streaming responses to enable AI via Zed's servers by default
(but preserve API key option for now)
- [x] Simplify protobuf
- [x] Proxy to OpenAI on zed.dev
- [x] Proxy to Gemini on zed.dev
- [x] Improve UX for switching between openAI and google models
- We current disallow cycling when setting a custom model, but we need a
better solution to keep OpenAI models available while testing the google
ones
- [x] Show remaining tokens correctly for Google models
- [x] Remove semantic index
- [x] Delete `ai` crate
- [x] Cloud front so we can ban abuse
- [x] Rate-limiting
- [x] Fix panic when using inline assistant
- [x] Double check the upgraded `AssistantSettings` are
backwards-compatible
- [x] Add hosted LLM interaction behind a `language-models` feature
flag.
Release Notes:
- We are temporarily removing the semantic index in order to redesign it
from scratch.
---------
Co-authored-by: Antonio <antonio@zed.dev>
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Thorsten <thorsten@zed.dev>
Co-authored-by: Max <max@zed.dev>
This PR moves the Clippy configuration up to the workspace level.
We're using the [`lints`
table](https://doc.rust-lang.org/cargo/reference/workspaces.html#the-lints-table)
to configure the Clippy ruleset in the workspace's `Cargo.toml`.
Each crate in the workspace now has the following in their own
`Cargo.toml` to inherit the lints from the workspace:
```toml
[lints]
workspace = true
```
This allows for configuring rust-analyzer to show Clippy lints in the
editor by using the following configuration in your Zed `settings.json`:
```json
{
"lsp": {
"rust-analyzer": {
"initialization_options": {
"check": {
"command": "clippy"
}
}
}
}
```
Release Notes:
- N/A
This PR fixes some formatting issues in some of the `Cargo.toml` files.
I tried to fix most of these in #7126, but there were a few that I
missed.
Release Notes:
- N/A
This PR sorts the dependency lists in our `Cargo.toml` files so that
they are in alphabetical order.
This should make them easier to visually scan when looking for a
dependency.
Apologies in advance for any merge conflicts 🙈
Release Notes:
- N/A
This should prevent a class of bugs where one queries the wrong type of
global, which results in oddities at runtime.
Release Notes:
- N/A
---------
Co-authored-by: Marshall <marshall@zed.dev>
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
- [x] Fill in GPL license text.
- [x] live_kit_client depends on live_kit_server as non-dev dependency,
even though it seems to only be used for tests. Is that an issue?
Release Notes:
- N/A
This reduces size of release binary by ~20% from 134MB to 107MB without noticeable slowdown on startup. Assets are decompressed granularly, on first access
