chore: import upstream snapshot with attribution

examples/eval-standalone-assertions/README.md

@@ -0,0 +1,22 @@
+# eval-standalone-assertions (Standalone Assertions)
+
+You can run this example with:
+
+```bash
+npx promptfoo@latest init --example eval-standalone-assertions
+cd eval-standalone-assertions
+```
+
+To get started, have a look at `asserts.yaml`
+
+If you use a model-graded eval, you must set your OPENAI_API_KEY environment variable or override the provider (see https://promptfoo.dev/docs/configuration/expected-outputs/model-graded/#overriding-the-llm-grader).
+
+Then run:
+
+```bash
+promptfoo eval --assertions asserts.yaml --model-outputs outputs.json
+```
+
+`outputs-with-tags.json` shows a different JSON format that allows you to show basic string metadata in the web UI view.
+
+Afterwards, you can view the results by running `promptfoo view`

examples/eval-standalone-assertions/asserts.yaml

@@ -0,0 +1,9 @@
+# For more information on assertions, see https://promptfoo.dev/docs/configuration/expected-outputs
+- type: icontains
+  value: hello
+- type: javascript
+  value: 1 / (output.length + 1) # prefer shorter outputs
+
+# For more information on model-graded evals, see https://promptfoo.dev/docs/configuration/expected-outputs/model-graded
+- type: model-graded-closedqa
+  value: ensure that the output contains a greeting

examples/eval-standalone-assertions/outputs-with-tags.json

@@ -0,0 +1,5 @@
+[
+  { "output": "Hello world", "tags": ["foo", "bar"] },
+  { "output": "Greetings, planet", "tags": ["foo", "bar"] },
+  { "output": "Salutations, Earth", "tags": ["foo", "bar"] }
+]

examples/eval-standalone-assertions/outputs.json

@@ -0,0 +1 @@
+["Hello world", "Greetings, planet", "Salutations, Earth"]