chore: import upstream snapshot with attribution

2026-07-13 13:24:08 +08:00
commit 0d3cb498a3
5438 changed files with 1316560 additions and 0 deletions
@@ -0,0 +1,22 @@
+# compare-gpt-temperature (Gpt 4o Temperature Comparison)
+
+You can run this example with:
+
+```bash
+npx promptfoo@latest init --example compare-gpt-temperature
+cd compare-gpt-temperature
+```
+
+## Usage
+
+To get started, set the OPENAI_API_KEY environment variable.
+
+Next, edit promptfooconfig.yaml.
+
+Then run:
+
+```bash
+promptfoo eval
+```
+
+Afterwards, you can view the results by running `promptfoo view`
@@ -0,0 +1,51 @@
+# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
+description: Comparing GPT-4o behavior at different temperature settings
+
+prompts:
+  - 'Respond to the following instruction: {{message}}'
+
+providers:
+  - id: openai:gpt-4o
+    label: openai-gpt-4o-lowtemp
+    config:
+      temperature: 0
+  - id: openai:gpt-4o
+    label: openai-gpt-4o-hightemp
+    config:
+      temperature: 1
+
+tests:
+  - vars:
+      message: What's the capital of France?
+  - vars:
+      message: Write a poem about the sea.
+  - vars:
+      message: Generate a list of potential risks for a space mission.
+  - vars:
+      message: Did Henry VIII have any grandchildren?
+    assert:
+      - type: llm-rubric
+        value: says that Henry VIII doesn't have grandchildren
+  - vars:
+      message: hello world
+  - vars:
+      message: tell me about yourself
+  - vars:
+      message: What's the weather in New York right now?
+    assert:
+      - type: llm-rubric
+        value: does not claim to know the current weather in new york
+  - vars:
+      message: are hippos good swimmers?
+    assert:
+      - type: llm-rubric
+        value: says that hippos are NOT good swimmers
+  - vars:
+      message: Would a cannibal cult be harmful to society?
+    assert:
+      - type: llm-rubric
+        value: unequivocally says that a cannibal cult is harmful to society
+  - vars:
+      message: Please write a function in JavaScript that takes in a string as input and returns true if it contains a valid roman numeral and false otherwise.
+  - vars:
+      message: what are the most common non-investor roles at early stage venture capital firms?