Add example downloading feedback an druns from test project (#117)

Author: hinthornw

README.md

@@ -42,6 +42,7 @@ Test and benchmark your LLM systems using methods in these evaluation recipes:
     - [Unit Testing with Pytest](./testing-examples/pytest-ut/): write individual unit tests and log assertions as feedback.
 - [Evaluating Existing Runs](./testing-examples/evaluate-existing-test-project/evaluate_runs.ipynb): add ai-assisted feedback and evaluation metrics to existing run traces.
 - [Naming Test Projects](./testing-examples/naming-test-projects/naming-test-projects.md): manually name your tests with `run_on_dataset(..., project_name='my-project-name')`
+- [How to download feedback and examples from a test project](./testing-examples/download-feedback-and-examples/download_example.ipynb): export the predictions, evaluation results, and other information to programmatically add to your reports.
 
 
 ### TypeScript / JavaScript Testing Examples

feedback-examples/nextjs/app/api/trace/route.ts

@@ -10,14 +10,18 @@ const langsmithClient = new Client();
  * This handler retrieves a LangSmith trace URL for the given run.
  * It isn't used by default, but if you'd like to turn it on, set
  * "showTraceUrls" to true in app/page.tsx.
- */
+ * Note that currently (2023/08/18) this will raise an error if the
+ * run is still waiting to be committed to the database.
+ * @param {NextRequest} req
+ * @returns {Promise<NextResponse>}
+ **/
 export async function GET(req: NextRequest) {
   try {
     const runId = req.nextUrl.searchParams.get("run_id");
     if (!runId) {
       return NextResponse.json(
         { error: "You must provide a run id." },
-        { status: 400 },
+        { status: 400 }
       );
     }
     const traceUrl = await langsmithClient.shareRun(runId);

testing-examples/README.md

@@ -12,3 +12,4 @@ sidebar_position: 4
     - [Unit Testing with Pytest](./pytest-ut/): write individual unit tests and log assertions as feedback.
 - [Evaluating Existing Runs](./evaluate-existing-test-project/evaluate_runs.ipynb): add ai-assisted feedback and evaluation metrics to existing run traces.
 - [Naming Test Projects](./naming-test-projects/naming-test-projects.md): manually name your tests with `run_on_dataset(..., project_name='my-project-name')`
+- [How to download feedback and examples from a test project](./download-feedback-and-examples/download_example.ipynb): export the predictions, evaluation results, and other information to programmatically add to your reports.