[Frontend] Support scores endpoint in run_batch (vllm-project#12430)

Signed-off-by: Pooya Davoodi <[email protected]>

examples/offline_inference/openai/openai_batch.md

@@ -13,7 +13,7 @@ The OpenAI batch file format consists of a series of json objects on new lines.
 Each line represents a separate request. See the [OpenAI package reference](https://platform.openai.com/docs/api-reference/batch/requestInput) for more details.
 
 ```{note}
-We currently only support `/v1/chat/completions` and `/v1/embeddings` endpoints (completions coming soon).
+We currently support `/v1/chat/completions`, `/v1/embeddings`, and `/v1/score` endpoints (completions coming soon).
 ```
 
 ## Pre-requisites
@@ -203,3 +203,34 @@ $ cat results.jsonl
 {"id":"vllm-db0f71f7dec244e6bce530e0b4ef908b","custom_id":"request-1","response":{"status_code":200,"request_id":"vllm-batch-3580bf4d4ae54d52b67eee266a6eab20","body":{"id":"embd-33ac2efa7996430184461f2e38529746","object":"list","created":444647,"model":"intfloat/e5-mistral-7b-instruct","data":[{"index":0,"object":"embedding","embedding":[0.016204833984375,0.0092010498046875,0.0018358230590820312,-0.0028228759765625,0.001422882080078125,-0.0031147003173828125,...]}],"usage":{"prompt_tokens":8,"total_tokens":8,"completion_tokens":0}}},"error":null}
 ...
 ```
+
+## Example 5: Using score endpoint
+
+### Additional prerequisites
+
+* Ensure you are using `vllm >= 0.7.0`.
+
+### Step 1: Create your batch file
+
+Add score requests to your batch file. The following is an example:
+
+```
+{"custom_id": "request-1", "method": "POST", "url": "/v1/score", "body": {"model": "BAAI/bge-reranker-v2-m3", "text_1": "What is the capital of France?", "text_2": ["The capital of Brazil is Brasilia.", "The capital of France is Paris."]}}
+{"custom_id": "request-2", "method": "POST", "url": "/v1/score", "body": {"model": "BAAI/bge-reranker-v2-m3", "text_1": "What is the capital of France?", "text_2": ["The capital of Brazil is Brasilia.", "The capital of France is Paris."]}}
+```
+
+You can mix chat completion, embedding, and score requests in the batch file, as long as the model you are using supports them all (note that all requests must use the same model).
+
+### Step 2: Run the batch
+
+You can run the batch using the same command as in earlier examples.
+
+### Step 3: Check your results
+
+You can check your results by running `cat results.jsonl`
+
+```
+$ cat results.jsonl
+{"id":"vllm-f87c5c4539184f618e555744a2965987","custom_id":"request-1","response":{"status_code":200,"request_id":"vllm-batch-806ab64512e44071b37d3f7ccd291413","body":{"id":"score-4ee45236897b4d29907d49b01298cdb1","object":"list","created":1737847944,"model":"BAAI/bge-reranker-v2-m3","data":[{"index":0,"object":"score","score":0.0010900497436523438},{"index":1,"object":"score","score":1.0}],"usage":{"prompt_tokens":37,"total_tokens":37,"completion_tokens":0,"prompt_tokens_details":null}}},"error":null}
+{"id":"vllm-41990c51a26d4fac8419077f12871099","custom_id":"request-2","response":{"status_code":200,"request_id":"vllm-batch-73ce66379026482699f81974e14e1e99","body":{"id":"score-13f2ffe6ba40460fbf9f7f00ad667d75","object":"list","created":1737847944,"model":"BAAI/bge-reranker-v2-m3","data":[{"index":0,"object":"score","score":0.001094818115234375},{"index":1,"object":"score","score":1.0}],"usage":{"prompt_tokens":37,"total_tokens":37,"completion_tokens":0,"prompt_tokens_details":null}}},"error":null}
+```

tests/entrypoints/openai/test_run_batch.py

@@ -1,3 +1,4 @@
+import json
 import subprocess
 import sys
 import tempfile
@@ -21,6 +22,9 @@
 {"custom_id": "request-3", "method": "POST", "url": "/v1/embeddings", "body": {"model": "intfloat/e5-mistral-7b-instruct", "input": "Hello world!"}}
 {"custom_id": "request-4", "method": "POST", "url": "/v1/embeddings", "body": {"model": "NonExistModel", "input": "Hello world!"}}"""
 
+INPUT_SCORE_BATCH = """{"custom_id": "request-1", "method": "POST", "url": "/v1/score", "body": {"model": "BAAI/bge-reranker-v2-m3", "text_1": "What is the capital of France?", "text_2": ["The capital of Brazil is Brasilia.", "The capital of France is Paris."]}}
+{"custom_id": "request-2", "method": "POST", "url": "/v1/score", "body": {"model": "BAAI/bge-reranker-v2-m3", "text_1": "What is the capital of France?", "text_2": ["The capital of Brazil is Brasilia.", "The capital of France is Paris."]}}"""
+
 
 def test_empty_file():
     with tempfile.NamedTemporaryFile(
@@ -102,3 +106,36 @@ def test_embeddings():
             # Ensure that the output format conforms to the openai api.
             # Validation should throw if the schema is wrong.
             BatchRequestOutput.model_validate_json(line)
+
+
+def test_score():
+    with tempfile.NamedTemporaryFile(
+            "w") as input_file, tempfile.NamedTemporaryFile(
+                "r") as output_file:
+        input_file.write(INPUT_SCORE_BATCH)
+        input_file.flush()
+        proc = subprocess.Popen([
+            sys.executable,
+            "-m",
+            "vllm.entrypoints.openai.run_batch",
+            "-i",
+            input_file.name,
+            "-o",
+            output_file.name,
+            "--model",
+            "BAAI/bge-reranker-v2-m3",
+        ], )
+        proc.communicate()
+        proc.wait()
+        assert proc.returncode == 0, f"{proc=}"
+
+        contents = output_file.read()
+        for line in contents.strip().split("\n"):
+            # Ensure that the output format conforms to the openai api.
+            # Validation should throw if the schema is wrong.
+            BatchRequestOutput.model_validate_json(line)
+
+            # Ensure that there is no error in the response.
+            line_dict = json.loads(line)
+            assert isinstance(line_dict, dict)
+            assert line_dict["error"] is None

vllm/entrypoints/openai/protocol.py

@@ -1283,7 +1283,7 @@ class BatchRequestInput(OpenAIBaseModel):
     url: str
 
     # The parameters of the request.
-    body: Union[ChatCompletionRequest, EmbeddingRequest]
+    body: Union[ChatCompletionRequest, EmbeddingRequest, ScoreRequest]
 
 
 class BatchResponseData(OpenAIBaseModel):
@@ -1294,7 +1294,8 @@ class BatchResponseData(OpenAIBaseModel):
     request_id: str
 
     # The body of the response.
-    body: Optional[Union[ChatCompletionResponse, EmbeddingResponse]] = None
+    body: Optional[Union[ChatCompletionResponse, EmbeddingResponse,
+                         ScoreResponse]] = None
 
 
 class BatchRequestOutput(OpenAIBaseModel):

vllm/entrypoints/openai/run_batch.py

@@ -16,12 +16,14 @@
                                               BatchRequestOutput,
                                               BatchResponseData,
                                               ChatCompletionResponse,
-                                              EmbeddingResponse, ErrorResponse)
+                                              EmbeddingResponse, ErrorResponse,
+                                              ScoreResponse)
 # yapf: enable
 from vllm.entrypoints.openai.serving_chat import OpenAIServingChat
 from vllm.entrypoints.openai.serving_embedding import OpenAIServingEmbedding
 from vllm.entrypoints.openai.serving_models import (BaseModelPath,
                                                     OpenAIServingModels)
+from vllm.entrypoints.openai.serving_score import OpenAIServingScores
 from vllm.usage.usage_lib import UsageContext
 from vllm.utils import FlexibleArgumentParser, random_uuid
 from vllm.version import __version__ as VLLM_VERSION
@@ -167,7 +169,8 @@ async def run_request(serving_engine_func: Callable,
                       tracker: BatchProgressTracker) -> BatchRequestOutput:
     response = await serving_engine_func(request.body)
 
-    if isinstance(response, (ChatCompletionResponse, EmbeddingResponse)):
+    if isinstance(response,
+                  (ChatCompletionResponse, EmbeddingResponse, ScoreResponse)):
         batch_output = BatchRequestOutput(
             id=f"vllm-{random_uuid()}",
             custom_id=request.custom_id,
@@ -239,6 +242,12 @@ async def main(args):
         chat_template=None,
         chat_template_content_format="auto",
     ) if model_config.task == "embed" else None
+    openai_serving_scores = (OpenAIServingScores(
+        engine,
+        model_config,
+        openai_serving_models,
+        request_logger=request_logger,
+    ) if model_config.task == "score" else None)
 
     tracker = BatchProgressTracker()
     logger.info("Reading batch from %s...", args.input_file)
@@ -279,14 +288,28 @@ async def main(args):
                     ))
                 continue
 
+            response_futures.append(run_request(handler_fn, request, tracker))
+            tracker.submitted()
+        elif request.url == "/v1/score":
+            handler_fn = (None if openai_serving_scores is None else
+                          openai_serving_scores.create_score)
+            if handler_fn is None:
+                response_futures.append(
+                    make_async_error_request_output(
+                        request,
+                        error_msg="The model does not support Scores API",
+                    ))
+                continue
+
             response_futures.append(run_request(handler_fn, request, tracker))
             tracker.submitted()
         else:
             response_futures.append(
                 make_async_error_request_output(
                     request,
-                    error_msg="Only /v1/chat/completions and "
-                    "/v1/embeddings are supported in the batch endpoint.",
+                    error_msg=
+                    "Only /v1/chat/completions, /v1/embeddings, and /v1/score "
+                    "are supported in the batch endpoint.",
                 ))
 
     with tracker.pbar():