SDK regeneration

reference.md

@@ -27,11 +27,16 @@ Create and start a Conversational AI agent instance.
 <dd>
 
 ```python
-from agora_agent import Agora, MicrosoftTtsParams, Tts_Microsoft
+from agora_agent import (
+    Agora,
+    Asr_Ares,
+    Llm,
+    LlmParams,
+    MicrosoftTtsParams,
+    Tts_Microsoft,
+)
 from agora_agent.agents import (
     StartAgentsRequestProperties,
-    StartAgentsRequestPropertiesAsr,
-    StartAgentsRequestPropertiesLlm,
     StartAgentsRequestPropertiesTurnDetection,
     StartAgentsRequestPropertiesTurnDetectionConfig,
     StartAgentsRequestPropertiesTurnDetectionConfigEndOfSpeech,
@@ -51,23 +56,23 @@ client.agents.start(
         agent_rtc_uid="1001",
         remote_rtc_uids=["1002"],
         idle_timeout=120,
-        asr=StartAgentsRequestPropertiesAsr(
-            language="en-US",
-        ),
+        asr=Asr_Ares(),
         tts=Tts_Microsoft(
             params=MicrosoftTtsParams(
                 key="key",
                 region="region",
                 voice_name="voice_name",
             ),
         ),
-        llm=StartAgentsRequestPropertiesLlm(
+        llm=Llm(
             url="https://api.openai.com/v1/chat/completions",
             api_key="<your_llm_key>",
             system_messages=[
                 {"role": "system", "content": "You are a helpful chatbot."}
             ],
-            params={"model": "gpt-4o-mini"},
+            params=LlmParams(
+                model="gpt-4o-mini",
+            ),
             max_history=32,
             greeting_message="Hello, how can I assist you today?",
             failure_message="Please hold on a second.",

src/agora_agent/agentkit/agent.py

@@ -67,6 +67,8 @@
 from ..agents.types.start_agents_request_properties_filler_words_content_static_config import StartAgentsRequestPropertiesFillerWordsContentStaticConfig
 from ..agents.types.start_agents_request_properties_filler_words_content_static_config_selection_rule import StartAgentsRequestPropertiesFillerWordsContentStaticConfigSelectionRule
 from ..types.tts import Tts
+from ..agents.types.start_agents_request_properties_filler_words_content_static_config_selection_rule import StartAgentsRequestPropertiesFillerWordsContentStaticConfigSelectionRule
+from ..types.tts import Tts
 from ..agent_management.types.agent_think_agent_management_request_on_listening_action import (
     AgentThinkAgentManagementRequestOnListeningAction,
 )

src/agora_agent/agentkit/agent_session.py

@@ -24,6 +24,7 @@
     is_generic_avatar,
     is_heygen_avatar,
     is_live_avatar_avatar,
+    is_rtc_avatar,
     validate_avatar_config,
     validate_tts_sample_rate,
 )

src/agora_agent/agentkit/vendors/avatar.py

@@ -177,6 +177,49 @@ def to_config(self) -> Dict[str, Any]:
         return {"enable": enable, "vendor": "generic", "params": params}
 
 
+class GenericAvatarOptions(BaseModel):
+    model_config = ConfigDict(extra="forbid")
+
+    api_key: str = Field(..., description="Generic avatar provider API key")
+    api_base_url: str = Field(..., description="Avatar provider API base URL")
+    avatar_id: str = Field(..., description="Avatar ID")
+    agora_uid: str = Field(..., description="Agora UID for the avatar video stream")
+    agora_appid: Optional[str] = Field(default=None, description="Agora App ID; filled by AgentSession when omitted")
+    agora_token: Optional[str] = Field(default=None, description="RTC token; generated by AgentSession when omitted")
+    agora_channel: Optional[str] = Field(default=None, description="Agora channel; filled by AgentSession when omitted")
+    enable: Optional[bool] = Field(default=None, description="Enable avatar (default: true)")
+    additional_params: Optional[Dict[str, Any]] = Field(default=None, description="Additional vendor-specific parameters")
+
+
+class GenericAvatar(BaseAvatar):
+    def __init__(self, **kwargs: Any):
+        self.options = GenericAvatarOptions(**kwargs)
+
+    @property
+    def required_sample_rate(self) -> int:
+        return 0
+
+    def to_config(self) -> Dict[str, Any]:
+        params: Dict[str, Any] = {
+            "api_key": self.options.api_key,
+            "api_base_url": self.options.api_base_url,
+            "avatar_id": self.options.avatar_id,
+            "agora_uid": self.options.agora_uid,
+        }
+
+        if self.options.agora_appid is not None:
+            params["agora_appid"] = self.options.agora_appid
+        if self.options.agora_token is not None:
+            params["agora_token"] = self.options.agora_token
+        if self.options.agora_channel is not None:
+            params["agora_channel"] = self.options.agora_channel
+        if self.options.additional_params is not None:
+            params = {**self.options.additional_params, **params}
+
+        enable = self.options.enable if self.options.enable is not None else True
+        return {"enable": enable, "vendor": "generic", "params": params}
+
+
 class AnamAvatarOptions(BaseModel):
     model_config = ConfigDict(extra="forbid")
 

src/agora_agent/agentkit/vendors/mllm.py

@@ -1,3 +1,4 @@
+import warnings
 from typing import Any, Dict, List, Optional
 
 from pydantic import BaseModel, ConfigDict, Field

src/agora_agent/agents/client.py

@@ -84,11 +84,16 @@ def start(
 
         Examples
         --------
-        from agora_agent import Agora, MicrosoftTtsParams, Tts_Microsoft
+        from agora_agent import (
+            Agora,
+            Asr_Ares,
+            Llm,
+            LlmParams,
+            MicrosoftTtsParams,
+            Tts_Microsoft,
+        )
         from agora_agent.agents import (
             StartAgentsRequestProperties,
-            StartAgentsRequestPropertiesAsr,
-            StartAgentsRequestPropertiesLlm,
             StartAgentsRequestPropertiesTurnDetection,
             StartAgentsRequestPropertiesTurnDetectionConfig,
             StartAgentsRequestPropertiesTurnDetectionConfigEndOfSpeech,
@@ -108,23 +113,23 @@ def start(
                 agent_rtc_uid="1001",
                 remote_rtc_uids=["1002"],
                 idle_timeout=120,
-                asr=StartAgentsRequestPropertiesAsr(
-                    language="en-US",
-                ),
+                asr=Asr_Ares(),
                 tts=Tts_Microsoft(
                     params=MicrosoftTtsParams(
                         key="key",
                         region="region",
                         voice_name="voice_name",
                     ),
                 ),
-                llm=StartAgentsRequestPropertiesLlm(
+                llm=Llm(
                     url="https://api.openai.com/v1/chat/completions",
                     api_key="<your_llm_key>",
                     system_messages=[
                         {"role": "system", "content": "You are a helpful chatbot."}
                     ],
-                    params={"model": "gpt-4o-mini"},
+                    params=LlmParams(
+                        model="gpt-4o-mini",
+                    ),
                     max_history=32,
                     greeting_message="Hello, how can I assist you today?",
                     failure_message="Please hold on a second.",
@@ -641,11 +646,16 @@ async def start(
         --------
         import asyncio
 
-        from agora_agent import AsyncAgora, MicrosoftTtsParams, Tts_Microsoft
+        from agora_agent import (
+            Asr_Ares,
+            AsyncAgora,
+            Llm,
+            LlmParams,
+            MicrosoftTtsParams,
+            Tts_Microsoft,
+        )
         from agora_agent.agents import (
             StartAgentsRequestProperties,
-            StartAgentsRequestPropertiesAsr,
-            StartAgentsRequestPropertiesLlm,
             StartAgentsRequestPropertiesTurnDetection,
             StartAgentsRequestPropertiesTurnDetectionConfig,
             StartAgentsRequestPropertiesTurnDetectionConfigEndOfSpeech,
@@ -668,23 +678,23 @@ async def main() -> None:
                     agent_rtc_uid="1001",
                     remote_rtc_uids=["1002"],
                     idle_timeout=120,
-                    asr=StartAgentsRequestPropertiesAsr(
-                        language="en-US",
-                    ),
+                    asr=Asr_Ares(),
                     tts=Tts_Microsoft(
                         params=MicrosoftTtsParams(
                             key="key",
                             region="region",
                             voice_name="voice_name",
                         ),
                     ),
-                    llm=StartAgentsRequestPropertiesLlm(
+                    llm=Llm(
                         url="https://api.openai.com/v1/chat/completions",
                         api_key="<your_llm_key>",
                         system_messages=[
                             {"role": "system", "content": "You are a helpful chatbot."}
                         ],
-                        params={"model": "gpt-4o-mini"},
+                        params=LlmParams(
+                            model="gpt-4o-mini",
+                        ),
                         max_history=32,
                         greeting_message="Hello, how can I assist you today?",
                         failure_message="Please hold on a second.",

src/agora_agent/agents/types/start_agents_request_properties.py

@@ -5,15 +5,15 @@
 import pydantic
 from ...core.pydantic_utilities import IS_PYDANTIC_V2
 from ...core.unchecked_base_model import UncheckedBaseModel
+from ...types.asr import Asr
+from ...types.llm import Llm
+from ...types.mllm import Mllm
 from ...types.tts import Tts
 from .start_agents_request_properties_advanced_features import StartAgentsRequestPropertiesAdvancedFeatures
-from .start_agents_request_properties_asr import StartAgentsRequestPropertiesAsr
 from .start_agents_request_properties_avatar import StartAgentsRequestPropertiesAvatar
 from .start_agents_request_properties_filler_words import StartAgentsRequestPropertiesFillerWords
 from .start_agents_request_properties_geofence import StartAgentsRequestPropertiesGeofence
 from .start_agents_request_properties_interruption import StartAgentsRequestPropertiesInterruption
-from .start_agents_request_properties_llm import StartAgentsRequestPropertiesLlm
-from .start_agents_request_properties_mllm import StartAgentsRequestPropertiesMllm
 from .start_agents_request_properties_parameters import StartAgentsRequestPropertiesParameters
 from .start_agents_request_properties_rtc import StartAgentsRequestPropertiesRtc
 from .start_agents_request_properties_sal import StartAgentsRequestPropertiesSal
@@ -67,7 +67,7 @@ class StartAgentsRequestProperties(UncheckedBaseModel):
     Advanced features configuration.
     """
 
-    asr: typing.Optional[StartAgentsRequestPropertiesAsr] = pydantic.Field(default=None)
+    asr: typing.Optional[Asr] = pydantic.Field(default=None)
     """
     Automatic Speech Recognition (ASR) configuration.
     """
@@ -77,12 +77,12 @@ class StartAgentsRequestProperties(UncheckedBaseModel):
     Text-to-speech (TTS) module configuration.
     """
 
-    llm: typing.Optional[StartAgentsRequestPropertiesLlm] = pydantic.Field(default=None)
+    llm: typing.Optional[Llm] = pydantic.Field(default=None)
     """
     Large language model (LLM) configuration.
     """
 
-    mllm: typing.Optional[StartAgentsRequestPropertiesMllm] = pydantic.Field(default=None)
+    mllm: typing.Optional[Mllm] = pydantic.Field(default=None)
     """
     Multimodal Large Language Model (MLLM) configuration for real-time audio and text processing. `mllm` is an exclusive alternative to the standard `asr` + `llm` + `tts` pipeline.
     """