chore: import upstream snapshot with attribution

examples/eval-bert-score/README.md

@@ -0,0 +1,68 @@
+# eval-bert-score (BERTScore Evaluation)
+
+Use BERTScore to measure semantic similarity between LLM outputs and reference text.
+
+```bash
+npx promptfoo@latest init --example eval-bert-score
+cd eval-bert-score
+```
+
+## Setup
+
+```bash
+pip install -r requirements.txt
+```
+
+Note: First run will download the BERT model (~1.4GB).
+
+## Usage
+
+### Basic Example
+
+```yaml
+# promptfooconfig.yaml
+tests:
+  - vars:
+      text: 'Hello world'
+      reference: 'Hi there'
+    assert:
+      - type: python
+        value: file://bertscore_check.py
+        threshold: 0.7 # Pass if similarity > 70%
+```
+
+Run: `promptfoo eval`
+
+### Advanced Example
+
+Compare against multiple valid references:
+
+```yaml
+# promptfooconfig-advanced.yaml
+assert:
+  - type: python
+    value: |
+      from bert_score import score
+      references = [
+          "First valid answer",
+          "Second valid answer",
+          "Third valid answer"
+      ]
+      scores = []
+      for ref in references:
+          _, _, F1 = score([output], [ref], lang='en', verbose=False)
+          scores.append(F1.item())
+      return max(scores)  # Use best match
+```
+
+Run: `promptfoo eval -c promptfooconfig-advanced.yaml`
+
+## How It Works
+
+BERTScore returns a similarity score from 0 to 1:
+
+- 0.9+ = Nearly identical meaning
+- 0.7-0.9 = Similar meaning
+- <0.7 = Different meaning
+
+[Learn more](https://arxiv.org/abs/1904.09675)

examples/eval-bert-score/bertscore_check.py

@@ -0,0 +1,26 @@
+"""
+BERTScore - measure semantic similarity between generated and reference text.
+"""
+
+import logging
+
+from bert_score import score
+
+logger = logging.getLogger(__name__)
+
+
+def get_assert(output, context):
+    """
+    Returns BERTScore F1 as a number (0-1).
+    Promptfoo will compare against threshold automatically.
+    """
+    reference = context.get("vars", {}).get("reference", "")
+    if not reference:
+        return 0
+
+    try:
+        _, _, F1 = score([output], [reference], lang="en", verbose=False)
+        return F1.item()
+    except Exception:
+        logger.debug("BERTScore calculation failed", exc_info=True)
+        return 0

examples/eval-bert-score/promptfooconfig-advanced.yaml

@@ -0,0 +1,32 @@
+# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
+description: Advanced BERTScore with multiple references
+
+prompts:
+  - 'Explain: {{topic}}'
+
+providers:
+  - openai:gpt-4.1-nano
+
+tests:
+  - vars:
+      topic: 'gradient descent'
+      reference: 'An optimization algorithm that adjusts parameters to minimize error'
+    assert:
+      - type: python
+        value: |
+          # Compare against multiple valid answers
+          from bert_score import score
+
+          references = [
+              context['vars']['reference'],
+              "A method for finding the minimum of a function by moving in the direction of steepest descent",
+              "Like rolling a ball down a hill to find the lowest point"
+          ]
+
+          # Get best score across all references
+          scores = []
+          for ref in references:
+              _, _, F1 = score([output], [ref], lang='en', verbose=False)
+              scores.append(F1.item())
+
+          return max(scores)

examples/eval-bert-score/promptfooconfig.yaml

@@ -0,0 +1,25 @@
+# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
+description: BERTScore semantic similarity evaluation
+
+prompts:
+  - 'Paraphrase: {{text}}'
+
+providers:
+  - openai:gpt-4.1-nano
+
+tests:
+  - vars:
+      text: 'The quick brown fox jumps over the lazy dog'
+      reference: 'A fast brown fox leaps over a sleepy dog'
+    assert:
+      - type: python
+        value: file://bertscore_check.py
+        threshold: 0.75
+
+  - vars:
+      text: 'Hello, how are you?'
+      reference: "Hi, how's it going?"
+    assert:
+      - type: python
+        value: file://bertscore_check.py
+        threshold: 0.7

examples/eval-bert-score/requirements.txt

@@ -0,0 +1,3 @@
+bert-score>=0.3.13
+torch>=1.0.0
+transformers>=4.0.0