add chat template test

Author: ngxson

examples/server/tests/unit/test_chat_completion.py

@@ -100,6 +100,23 @@ def test_chat_completion_with_openai_library():
     assert match_regex("(Suddenly)+", res.choices[0].message.content)
 
 
+def test_chat_template():
+    global server
+    server.chat_template = "llama3"
+    server.debug = True  # to get the "__verbose" object in the response
+    server.start()
+    res = server.make_request("POST", "/chat/completions", data={
+        "max_tokens": 8,
+        "messages": [
+            {"role": "system", "content": "Book"},
+            {"role": "user", "content": "What is the best book"},
+        ]
+    })
+    assert res.status_code == 200
+    assert "__verbose" in res.body
+    assert res.body["__verbose"]["prompt"] == "<s> <|start_header_id|>system<|end_header_id|>\n\nBook<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nWhat is the best book<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"
+
+
 @pytest.mark.parametrize("response_format,n_predicted,re_content", [
     ({"type": "json_object", "schema": {"const": "42"}}, 6, "\"42\""),
     ({"type": "json_object", "schema": {"items": [{"type": "integer"}]}}, 10, "[ -3000 ]"),

examples/server/tests/utils.py

@@ -74,6 +74,7 @@ class ServerProcess:
     draft_min: int | None = None
     draft_max: int | None = None
     no_webui: bool | None = None
+    chat_template: str | None = None
 
     # session variables
     process: subprocess.Popen | None = None
@@ -164,6 +165,8 @@ def start(self, timeout_seconds: int = 10) -> None:
             server_args.extend(["--draft-min", self.draft_min])
         if self.no_webui:
             server_args.append("--no-webui")
+        if self.chat_template:
+            server_args.extend(["--chat-template", self.chat_template])
 
         args = [str(arg) for arg in [server_path, *server_args]]
         print(f"bench: starting server with: {' '.join(args)}")