Draft: Consolidate External Service Plugins and Refactor code

livekit-agents/livekit/agents/embedder/__init__.py

@@ -0,0 +1,3 @@
+from livekit.agents.embedder.base import Embedder
+
+__all__ = ["Embedder"]

livekit-agents/livekit/agents/embedder/base.py

@@ -0,0 +1,17 @@
+from typing import Dict, List, Optional, Tuple
+
+from pydantic import BaseModel, ConfigDict
+
+
+class Embedder(BaseModel):
+    """Base class for managing embedders"""
+
+    dimensions: Optional[int] = 1536
+
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+
+    def get_embedding(self, text: str) -> List[float]:
+        raise NotImplementedError
+
+    def get_embedding_and_usage(self, text: str) -> Tuple[List[float], Optional[Dict]]:
+        raise NotImplementedError

livekit-agents/livekit/agents/embedder/openai.py

@@ -0,0 +1,71 @@
+from typing import Any, Dict, List, Optional, Tuple
+
+from livekit.agents.embedder.base import Embedder
+from livekit.agents.utils.log import logger
+from typing_extensions import Literal
+
+try:
+    from openai import OpenAI as OpenAIClient
+    from openai.types.create_embedding_response import CreateEmbeddingResponse
+except ImportError:
+    raise ImportError("`openai` not installed. Please install it using `pip install openai`.")
+
+
+class OpenAIEmbedder(Embedder):
+    model: str = "text-embedding-3-small"
+    dimensions: int = 1536
+    encoding_format: Literal["float", "base64"] = "float"
+    user: Optional[str] = None
+    api_key: Optional[str] = None
+    organization: Optional[str] = None
+    base_url: Optional[str] = None
+    request_params: Optional[Dict[str, Any]] = None
+    client_params: Optional[Dict[str, Any]] = None
+    openai_client: Optional[OpenAIClient] = None
+
+    @property
+    def client(self) -> OpenAIClient:
+        if self.openai_client:
+            return self.openai_client
+
+        _client_params: Dict[str, Any] = {}
+        if self.api_key:
+            _client_params["api_key"] = self.api_key
+        if self.organization:
+            _client_params["organization"] = self.organization
+        if self.base_url:
+            _client_params["base_url"] = self.base_url
+        if self.client_params:
+            _client_params.update(self.client_params)
+        return OpenAIClient(**_client_params)
+
+    def _response(self, text: str) -> CreateEmbeddingResponse:
+        _request_params: Dict[str, Any] = {
+            "input": text,
+            "model": self.model,
+            "encoding_format": self.encoding_format,
+        }
+        if self.user is not None:
+            _request_params["user"] = self.user
+        if self.model.startswith("text-embedding-3"):
+            _request_params["dimensions"] = self.dimensions
+        if self.request_params:
+            _request_params.update(self.request_params)
+        return self.client.embeddings.create(**_request_params)
+
+    def get_embedding(self, text: str) -> List[float]:
+        response: CreateEmbeddingResponse = self._response(text=text)
+        try:
+            return response.data[0].embedding
+        except Exception as e:
+            logger.warning(e)
+            return []
+
+    def get_embedding_and_usage(self, text: str) -> Tuple[List[float], Optional[Dict]]:
+        response: CreateEmbeddingResponse = self._response(text=text)
+
+        embedding = response.data[0].embedding
+        usage = response.usage
+        if usage:
+            return embedding, usage.model_dump()
+        return embedding, None

livekit-agents/livekit/agents/llm/__init__.py

@@ -1,4 +1,5 @@
 from . import _oai_api
+from .base import LLM, ChatChunk, Choice, ChoiceDelta, LLMStream
 from .chat_context import ChatAudio, ChatContext, ChatImage, ChatMessage, ChatRole
 from .function_context import (
     USE_DOCSTRING,
@@ -10,7 +11,6 @@
     TypeInfo,
     ai_callable,
 )
-from .llm import LLM, ChatChunk, Choice, ChoiceDelta, LLMStream
 
 __all__ = [
     "LLM",

livekit-plugins/livekit-plugins-deepgram/livekit/plugins/deepgram/version.py → livekit-agents/livekit/agents/llm/anthropic/__init_.py

@@ -12,4 +12,10 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = "0.6.8"
+
+from .base import LLM, LLMStream
+
+__all__ = [
+    "LLM",
+    "LLMStream",
+]

livekit-plugins/livekit-plugins-anthropic/livekit/plugins/anthropic/llm.py → livekit-agents/livekit/agents/llm/anthropic/anthropic.py

@@ -24,10 +24,14 @@
 import httpx
 from livekit import rtc
 from livekit.agents import llm, utils
+from livekit.agents.utils.log import logger
 
-import anthropic
+try:
+    import anthropic
+except ImportError:
+    logger.error("`anthropic` not installed. Please install it using `pip install anthropic`")
+    raise ImportError
 
-from .log import logger
 from .models import (
     ChatModels,
 )
@@ -508,4 +512,4 @@ def _sanitize_primitive(
     if choices and value not in choices:
         raise ValueError(f"invalid value {value}, not in {choices}")
 
-    return value
+    return value

livekit-agents/livekit/agents/llm/llm.py → livekit-agents/livekit/agents/llm/base.py

@@ -1,3 +1,17 @@
+# Copyright 2023 LiveKit, Inc.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
 from __future__ import annotations
 
 import abc

livekit-plugins/livekit-plugins-anthropic/livekit/plugins/anthropic/version.py → livekit-agents/livekit/agents/llm/openai/__init__.py

@@ -12,4 +12,13 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = "0.2.1"
+
+from . import beta, realtime
+from .openai import LLM, LLMStream
+
+__all__ = [
+    "LLM",
+    "LLMStream",
+    "beta",
+    "realtime"
+]