Files
oak-gpui/crates/eval/Cargo.toml
T
ce1a674eba eval: Fine-grained assertions (#29246)
- Support programmatic examples
([example](https://github.com/zed-industries/zed/blob/17feb260a0919e102ae4e220669c467885bf4b57/crates/eval/src/examples/file_search.rs))
- Combine data-driven example declarations into a single `.toml` file
([example](https://github.com/zed-industries/zed/blob/17feb260a0919e102ae4e220669c467885bf4b57/crates/eval/src/examples/find_and_replace_diff_card.toml))
- Run judge on individual assertions (previously called "criteria")
- Report judge and programmatic assertions in one combined table

Note: We still need to work on concept naming 

<img width=400
src="https://github.com/user-attachments/assets/fc719c93-467f-412b-8d47-68821bd8a5f5">

Release Notes:

- N/A

---------

Co-authored-by: Richard Feldman <oss@rtfeldman.com>
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Co-authored-by: Thomas Mickley-Doyle <tmickleydoyle@gmail.com>
2025-04-22 23:58:58 -03:00

56 lines
1.3 KiB
TOML

[package]
name = "eval"
version = "0.1.0"
publish.workspace = true
edition.workspace = true
[dependencies]
agent.workspace = true
anyhow.workspace = true
assistant_tool.workspace = true
assistant_tools.workspace = true
async-trait.workspace = true
async-watch.workspace = true
chrono.workspace = true
clap.workspace = true
client.workspace = true
collections.workspace = true
context_server.workspace = true
dirs = "5.0"
env_logger.workspace = true
extension.workspace = true
fs.workspace = true
futures.workspace = true
gpui.workspace = true
gpui_tokio.workspace = true
handlebars.workspace = true
language.workspace = true
language_extension.workspace = true
language_model.workspace = true
language_models.workspace = true
languages = { workspace = true, features = ["load-grammars"] }
node_runtime.workspace = true
paths.workspace = true
project.workspace = true
prompt_store.workspace = true
regex.workspace = true
release_channel.workspace = true
reqwest_client.workspace = true
serde.workspace = true
serde_json.workspace = true
settings.workspace = true
shellexpand.workspace = true
smol.workspace = true
telemetry.workspace = true
toml.workspace = true
unindent.workspace = true
util.workspace = true
uuid = { version = "1.6", features = ["v4"] }
workspace-hack.workspace = true
[[bin]]
name = "eval"
path = "src/eval.rs"
[lints]
workspace = true