[Frontend] Automatic detection of chat content format from AST (vllm-…

…project#9919)

Signed-off-by: DarkLight1337 <[email protected]>

docs/source/serving/openai_compatible_server.md

@@ -172,12 +172,20 @@ completion = client.chat.completions.create(
   ]
 )
 ```
-Most chat templates for LLMs expect the `content` to be a `string` but there are some newer models like
-`meta-llama/Llama-Guard-3-1B` that expect the content to be parsed with the new OpenAI spec. In order to choose which
-format the content needs to be parsed in by vLLM, please use the `--chat-template-text-format` argument to specify
-between `string` or `openai`. The default value is `string` and vLLM internally converts both spec formats to match
-this, unless explicitly specified.
 
+Most chat templates for LLMs expect the `content` field to be a string, but there are some newer models like 
+`meta-llama/Llama-Guard-3-1B` that expect the content to be formatted according to the OpenAI schema in the
+request. vLLM provides best-effort support to detect this automatically, which is logged as a string like
+*"Detected the chat template content format to be..."*, and internally converts incoming requests to match
+the detected format, which can be one of:
+
+- `"string"`: A string.
+  - Example: `"Hello world"`
+- `"openai"`: A list of dictionaries, similar to OpenAI schema.
+  - Example: `[{"type": "text", "text": "Hello world!"}]`
+
+If the result is not what you expect, you can set the `--chat-template-content-format` CLI argument
+to override which format to use.
 
 ## Command line arguments for the server
 

tests/entrypoints/openai/test_serving_chat.py

@@ -26,7 +26,6 @@ class MockModelConfig:
     tokenizer = MODEL_NAME
     trust_remote_code = False
     tokenizer_mode = "auto"
-    chat_template_text_format = "string"
     max_model_len = 100
     tokenizer_revision = None
     multimodal_config = MultiModalConfig()
@@ -49,6 +48,7 @@ async def _async_serving_chat_init():
                                            BASE_MODEL_PATHS,
                                            response_role="assistant",
                                            chat_template=CHAT_TEMPLATE,
+                                           chat_template_content_format="auto",
                                            lora_modules=None,
                                            prompt_adapters=None,
                                            request_logger=None)
@@ -70,6 +70,7 @@ def test_serving_chat_should_set_correct_max_tokens():
                                      BASE_MODEL_PATHS,
                                      response_role="assistant",
                                      chat_template=CHAT_TEMPLATE,
+                                     chat_template_content_format="auto",
                                      lora_modules=None,
                                      prompt_adapters=None,
                                      request_logger=None)