[Bugfix] Refactor /invocations to be task-agnostic (#20764)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

tests/entrypoints/openai/test_embedding.py

@@ -296,3 +296,63 @@ async def test_single_embedding_truncation_invalid(client: openai.AsyncOpenAI,
         assert "error" in response.object
         assert "truncate_prompt_tokens value is greater than max_model_len. "\
                "Please, select a smaller truncation size." in response.message
+
+
+@pytest.mark.asyncio
+async def test_invocations(server: RemoteOpenAIServer,
+                           client: openai.AsyncOpenAI):
+    input_texts = [
+        "The chef prepared a delicious meal.",
+    ]
+
+    request_args = {
+        "model": MODEL_NAME,
+        "input": input_texts,
+        "encoding_format": "float",
+    }
+
+    completion_response = await client.embeddings.create(**request_args)
+
+    invocation_response = requests.post(server.url_for("invocations"),
+                                        json=request_args)
+    invocation_response.raise_for_status()
+
+    completion_output = completion_response.model_dump()
+    invocation_output = invocation_response.json()
+
+    assert completion_output.keys() == invocation_output.keys()
+    assert completion_output["data"] == invocation_output["data"]
+
+
+@pytest.mark.asyncio
+async def test_invocations_conversation(server: RemoteOpenAIServer):
+    messages = [{
+        "role": "user",
+        "content": "The cat sat on the mat.",
+    }, {
+        "role": "assistant",
+        "content": "A feline was resting on a rug.",
+    }, {
+        "role": "user",
+        "content": "Stars twinkle brightly in the night sky.",
+    }]
+
+    request_args = {
+        "model": MODEL_NAME,
+        "messages": messages,
+        "encoding_format": "float",
+    }
+
+    chat_response = requests.post(server.url_for("v1/embeddings"),
+                                  json=request_args)
+    chat_response.raise_for_status()
+
+    invocation_response = requests.post(server.url_for("invocations"),
+                                        json=request_args)
+    invocation_response.raise_for_status()
+
+    chat_output = chat_response.json()
+    invocation_output = invocation_response.json()
+
+    assert chat_output.keys() == invocation_output.keys()
+    assert chat_output["data"] == invocation_output["data"]