Support OpenAI Assistants API

examples/voice-assistant/minimal_assistant.py

@@ -10,20 +10,20 @@
 
 
 async def entrypoint(ctx: JobContext):
-    initial_ctx = llm.ChatContext().append(
-        role="system",
-        text=(
-            "You are a voice assistant created by LiveKit. Your interface with users will be voice. "
-            "You should use short and concise responses, and avoiding usage of unpronouncable punctuation."
-        ),
-    )
+    initial_ctx = llm.ChatContext()
 
     await ctx.connect(auto_subscribe=AutoSubscribe.AUDIO_ONLY)
 
     assistant = VoiceAssistant(
         vad=silero.VAD.load(),
         stt=deepgram.STT(),
-        llm=openai.LLM(),
+        llm=openai.AssistantLLM(
+            assistant_opts=openai.AssistantCreateOptions(
+                model="gpt-4o",
+                instructions="You are a voice assistant created by LiveKit. Your interface with users will be voice.",
+                name="KITT",
+            )
+        ),
         tts=openai.TTS(),
         chat_ctx=initial_ctx,
     )

livekit-agents/livekit/agents/llm/chat_context.py

@@ -41,6 +41,7 @@ class ChatMessage:
     content: str | list[str | ChatImage] | None = None
     tool_calls: list[function_context.FunctionCallInfo] | None = None
     tool_call_id: str | None = None
+    _metadata: dict[str, Any] = field(default_factory=dict, repr=False, init=False)
 
     @staticmethod
     def create_tool_from_called_function(
@@ -104,6 +105,7 @@ def copy(self):
 @dataclass
 class ChatContext:
     messages: list[ChatMessage] = field(default_factory=list)
+    _metadata: dict[str, Any] = field(default_factory=dict, repr=False, init=False)
 
     def append(
         self, *, text: str = "", images: list[ChatImage] = [], role: ChatRole = "system"

livekit-plugins/livekit-plugins-openai/livekit/plugins/openai/__init__.py

@@ -12,6 +12,13 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+from .assistant_llm import (
+    AssistantCreateOptions,
+    AssistantLLM,
+    AssistantLLMStream,
+    AssistantLoadOptions,
+    AssistantOptions,
+)
 from .embeddings import EmbeddingData, create_embeddings
 from .llm import LLM, LLMStream
 from .models import TTSModels, TTSVoices, WhisperModels
@@ -24,6 +31,11 @@
     "TTS",
     "LLM",
     "LLMStream",
+    "AssistantOptions",
+    "AssistantCreateOptions",
+    "AssistantLoadOptions",
+    "AssistantLLM",
+    "AssistantLLMStream",
     "WhisperModels",
     "TTSModels",
     "TTSVoices",