Skip to content

Add finance-agent routing eval dataset and builder guidance #1625

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
maxpetrusenko wants to merge 1 commit into
base: main
Choose a base branch
from
+13 −0
Open

Add finance-agent routing eval dataset and builder guidance #1625

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions docs/build-eval.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,8 @@ Each JSON object will represent one data point in your eval. The keys you need i

For the basic evals `Match`, `Includes`, and `FuzzyMatch`, the other required key is `"ideal"`, which is a string (or a list of strings) specifying the correct reference answer(s). For model-graded evals, the required keys vary based on the eval but is determined by the `{key}`s in the evaluation `prompt` that are not covered by the (optional) `args`.

For agent routing and tool selection tasks, a practical pattern is to make the `"ideal"` value the expected route label (for example, `portfolio_analysis` or `market_data_lookup`). This gives you a deterministic regression check for planner behavior before you evaluate full natural-language answer quality. You can also set `"ideal"` to a list of acceptable labels for intentionally ambiguous prompts.

We have implemented small subsets of the [CoQA](https://stanfordnlp.github.io/coqa/) dataset for various eval templates to illustrate how the data should be formatted. See [`coqa/match.jsonl`](../evals/registry/data/coqa/match.jsonl) for an example of data that is suitable for the `Match` basic eval template and [`coqa/samples.jsonl`](../evals/registry/data/coqa/samples.jsonl) for data that is suitable for `fact` and `closedqa` model-graded evals. Note that even though these two model-graded evals expect different keys, we can include the superset of keys in our data in order to support both evals.

If the dataset file is on your local machine, put the `jsonl` file in `evals/registry/data/<eval_name>/samples.jsonl`. If it is in Cloud Object Storage, we support path-style URLs for the major clouds (for your personal use only, we will not accept PRs with cloud URLs).
Expand Down
3 changes: 3 additions & 0 deletions evals/registry/data/finance_agent_routing/samples.jsonl
View file
Open in desktop
Git LFS file not shown
8 changes: 8 additions & 0 deletions evals/registry/evals/finance-agent-routing.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,8 @@
finance-agent-routing:
id: finance-agent-routing.dev.v0
description: Evaluate routing decisions for a finance assistant across portfolio analysis, risk assessment, market lookup, memory lookup, and direct response intents.
metrics: [accuracy]
finance-agent-routing.dev.v0:
class: evals.elsuite.basic.match:Match
args:
samples_jsonl: finance_agent_routing/samples.jsonl