Implemented BLEU score, wrote unit tests and documentation for it.

apps/opik-documentation/documentation/docs/cookbook/dspy.ipynb

@@ -37,17 +37,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "OPIK: Opik is already configured. You can check the settings by viewing the config file at /Users/jacquesverre/.opik.config\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "import opik\n",
     "\n",
@@ -56,7 +48,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -78,7 +70,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -95,31 +87,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "WARNING:langfuse:Langfuse client is disabled since no public_key was provided as a parameter or environment variable 'LANGFUSE_PUBLIC_KEY'. See our docs: https://langfuse.com/docs/sdk/python/low-level-sdk#initialize-client\n",
-      "OPIK: Started logging traces to the \"DSPY\" project at https://www.comet.com/opik/jacques-comet/redirect/projects?name=DSPY.\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "Prediction(\n",
-       "    reasoning='The meaning of life is a philosophical question that has been contemplated by humans for centuries. Different cultures, religions, and individuals have proposed various interpretations. Some suggest that the meaning of life is to seek happiness, fulfillment, and personal growth, while others believe it is about serving a higher purpose or contributing to the well-being of others. Ultimately, the meaning of life may vary from person to person, shaped by personal experiences, beliefs, and values.',\n",
-       "    answer=\"The meaning of life is subjective and can vary greatly among individuals. It may involve seeking happiness, personal growth, and contributing to the well-being of others, or fulfilling a higher purpose, depending on one's beliefs and experiences.\"\n",
-       ")"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "cot = dspy.ChainOfThought(\"question -> answer\")\n",
     "cot(question=\"What is the meaning of life?\")"

apps/opik-documentation/documentation/docs/evaluation/metrics/heuristic_metrics.md

@@ -16,6 +16,7 @@ You can use the following heuristic metrics:
 | RegexMatch  | Checks if the output matches a specified regular expression pattern                               |
 | IsJson      | Checks if the output is a valid JSON object                                                       |
 | Levenshtein | Calculates the Levenshtein distance between the output and an expected string                     |
+| BLEU        | Calculates the BLEU score for output text against one or more reference texts                     |
 
 ## Score an LLM response
 
@@ -97,3 +98,64 @@ metric = LevenshteinRatio()
 score = metric.score(output="Hello world !", reference="hello")
 print(score)
 ```
+
+### BLEU
+
+The BLEU metric calculates how close the LLM output is to one or more reference translations. This single metric class can compute:
+- Single-sentence BLEU: Pass a single output string and one or more reference strings.
+- Corpus-level BLEU: Pass a list of output strings and a parallel list of reference strings (or lists of references).
+
+Single-Sentence BLEU
+
+```python
+from opik.evaluation.metrics import BLEU
+
+bleu_metric = BLEU()
+
+score = bleu_metric.score(
+    output="Hello world!",
+    reference="Hello world"
+)
+print(score.value, score.reason)
+
+score = bleu_metric.score(
+    output="Hello world!",
+    reference=["Hello planet", "Hello world"]
+)
+print(score.value, score.reason)
+```
+
+Corpus-Level BLEU
+
+```python
+from opik.evaluation.metrics import BLEU
+
+bleu_metric = BLEU()
+
+outputs = ["Hello there", "This is a test."]
+references = [
+    ["Hello world", "Hello there"],
+    "This is a test."
+]
+
+result = bleu_metric.score(output=outputs, reference=references)
+print(result.value, result.reason)
+```
+
+You can also customize n-grams, smoothing methods, or weights:
+
+```python
+from opik.evaluation.metrics import BLEU
+
+metric = BLEU(
+    n_grams=4,
+    smoothing_method="method1",
+    weights=[0.25, 0.25, 0.25, 0.25]
+)
+
+score = metric.score(
+    output="The cat sat on the mat",
+    reference=["The cat is on the mat", "A cat sat here on the mat"]
+)
+print(score.value, score.reason)
+```

sdks/python/src/opik/evaluation/metrics/__init__.py

@@ -3,6 +3,7 @@
 from .heuristics.is_json import IsJson
 from .heuristics.levenshtein_ratio import LevenshteinRatio
 from .heuristics.regex_match import RegexMatch
+from .heuristics.bleu import BLEU
 from .llm_judges.answer_relevance.metric import AnswerRelevance
 from .llm_judges.context_precision.metric import ContextPrecision
 from .llm_judges.context_recall.metric import ContextRecall
@@ -29,4 +30,5 @@
     "RegexMatch",
     "MetricComputationError",
     "BaseMetric",
+    "BLEU",
 ]