livekit-plugins-google 0.3.0__py3-none-any.whl → 1.3.11__py3-none-any.whl

livekit/plugins/google/utils.py

@@ -0,0 +1,220 @@
+from __future__ import annotations
+
+import re
+from copy import deepcopy
+from typing import Any
+
+from pydantic import TypeAdapter
+
+from google.genai import types
+from livekit.agents import llm
+from livekit.agents.llm import utils as llm_utils
+from livekit.agents.types import NOT_GIVEN, NotGivenOr
+from livekit.agents.utils import is_given
+
+from .tools import GeminiTool
+
+__all__ = ["create_tools_config"]
+
+
+def create_tools_config(
+    tool_ctx: llm.ToolContext,
+    *,
+    tool_behavior: NotGivenOr[types.Behavior] = NOT_GIVEN,
+    _only_single_type: bool = False,
+) -> list[types.Tool]:
+    gemini_tools: list[types.Tool] = []
+
+    function_tools = [
+        types.FunctionDeclaration.model_validate(schema)
+        for schema in tool_ctx.parse_function_tools(
+            "google", tool_behavior=tool_behavior.value if tool_behavior else None
+        )
+    ]
+    if function_tools:
+        gemini_tools.append(types.Tool(function_declarations=function_tools))
+
+    # Some Google LLMs do not support multiple tool types (either function tools or builtin tools).
+    if _only_single_type and gemini_tools:
+        return gemini_tools
+
+    for tool in tool_ctx.provider_tools:
+        if isinstance(tool, GeminiTool):
+            gemini_tools.append(tool.to_tool_config())
+
+    return gemini_tools
+
+
+def get_tool_results_for_realtime(
+    chat_ctx: llm.ChatContext,
+    *,
+    vertexai: bool = False,
+    tool_response_scheduling: NotGivenOr[types.FunctionResponseScheduling] = NOT_GIVEN,
+) -> types.LiveClientToolResponse | None:
+    function_responses: list[types.FunctionResponse] = []
+    for msg in chat_ctx.items:
+        if msg.type == "function_call_output":
+            res = types.FunctionResponse(
+                name=msg.name,
+                response={"output": msg.output},
+            )
+            if is_given(tool_response_scheduling):
+                # vertexai currently doesn't support the scheduling parameter, gemini api defaults to idle
+                # it's the user's responsibility to avoid this parameter when using vertexai
+                res.scheduling = tool_response_scheduling
+            if not vertexai:
+                # vertexai does not support id in FunctionResponse
+                # see: https://github.com/googleapis/python-genai/blob/85e00bc/google/genai/_live_converters.py#L1435
+                res.id = msg.call_id
+            function_responses.append(res)
+    return (
+        types.LiveClientToolResponse(function_responses=function_responses)
+        if function_responses
+        else None
+    )
+
+
+def to_response_format(response_format: type | dict) -> types.SchemaUnion:
+    _, json_schema_type = llm_utils.to_response_format_param(response_format)
+    if isinstance(json_schema_type, TypeAdapter):
+        schema = json_schema_type.json_schema()
+    else:
+        schema = json_schema_type.model_json_schema()
+
+    return _GeminiJsonSchema(schema).simplify()
+
+
+class _GeminiJsonSchema:
+    """
+    Transforms the JSON Schema from Pydantic to be suitable for Gemini.
+    based on pydantic-ai implementation
+    https://github.com/pydantic/pydantic-ai/blob/085a9542a7360b7e388ce575323ce189b397d7ad/pydantic_ai_slim/pydantic_ai/models/gemini.py#L809
+    """
+
+    # Type mapping from JSON Schema to Gemini Schema
+    TYPE_MAPPING: dict[str, types.Type] = {
+        "string": types.Type.STRING,
+        "number": types.Type.NUMBER,
+        "integer": types.Type.INTEGER,
+        "boolean": types.Type.BOOLEAN,
+        "array": types.Type.ARRAY,
+        "object": types.Type.OBJECT,
+    }
+
+    def __init__(self, schema: dict[str, Any]):
+        self.schema = deepcopy(schema)
+        self.defs = self.schema.pop("$defs", {})
+
+    def simplify(self) -> dict[str, Any] | None:
+        self._simplify(self.schema, refs_stack=())
+        # If the schema is an OBJECT with no properties, return None.
+        if self.schema.get("type") == types.Type.OBJECT and not self.schema.get("properties"):
+            return None
+        return self.schema
+
+    def _simplify(self, schema: dict[str, Any], refs_stack: tuple[str, ...]) -> None:
+        schema.pop("title", None)
+        schema.pop("default", None)
+        schema.pop("additionalProperties", None)
+        schema.pop("$schema", None)
+
+        if (const := schema.pop("const", None)) is not None:
+            # Gemini doesn't support const, but it does support enum with a single value
+            schema["enum"] = [const]
+
+        schema.pop("discriminator", None)
+        schema.pop("examples", None)
+
+        if ref := schema.pop("$ref", None):
+            key = re.sub(r"^#/\$defs/", "", ref)
+            if key in refs_stack:
+                raise ValueError("Recursive `$ref`s in JSON Schema are not supported by Gemini")
+            refs_stack += (key,)
+            schema_def = self.defs[key]
+            self._simplify(schema_def, refs_stack)
+            schema.update(schema_def)
+            return
+
+        if "enum" in schema and "type" not in schema:
+            schema["type"] = self._infer_type(schema["enum"][0])
+
+        # Convert type value to Gemini format
+        if "type" in schema and schema["type"] != "null":
+            json_type = schema["type"]
+            if json_type in self.TYPE_MAPPING:
+                schema["type"] = self.TYPE_MAPPING[json_type]
+            elif isinstance(json_type, types.Type):
+                schema["type"] = json_type
+            else:
+                raise ValueError(f"Unsupported type in JSON Schema: {json_type}")
+
+        # Map field names that differ between JSON Schema and Gemini
+        self._map_field_names(schema)
+
+        # Handle anyOf - map to any_of
+        if any_of := schema.pop("anyOf", None):
+            if any_of:
+                mapped_any_of = []
+                has_null = False
+                non_null_schema = None
+
+                for item_schema in any_of:
+                    self._simplify(item_schema, refs_stack)
+                    if item_schema == {"type": "null"}:
+                        has_null = True
+                    else:
+                        non_null_schema = item_schema
+                        mapped_any_of.append(item_schema)
+
+                if has_null and len(any_of) == 2 and non_null_schema:
+                    schema.update(non_null_schema)
+                    schema["nullable"] = True
+                else:
+                    schema["any_of"] = mapped_any_of
+
+        type_ = schema.get("type")
+
+        if type_ == types.Type.OBJECT:
+            self._object(schema, refs_stack)
+        elif type_ == types.Type.ARRAY:
+            self._array(schema, refs_stack)
+
+    def _infer_type(self, value: Any) -> str:
+        if isinstance(value, int):
+            return "integer"
+        elif isinstance(value, float):
+            return "number"
+        elif isinstance(value, str):
+            return "string"
+        elif isinstance(value, bool):
+            return "boolean"
+        else:
+            raise ValueError(f"Unsupported type in Schema: {type(value)}")
+
+    def _map_field_names(self, schema: dict[str, Any]) -> None:
+        """Map JSON Schema field names to Gemini Schema field names."""
+        mappings = {
+            "minLength": "min_length",
+            "maxLength": "max_length",
+            "minItems": "min_items",
+            "maxItems": "max_items",
+            "minProperties": "min_properties",
+            "maxProperties": "max_properties",
+        }
+
+        for json_name, gemini_name in mappings.items():
+            if json_name in schema:
+                schema[gemini_name] = schema.pop(json_name)
+
+    def _object(self, schema: dict[str, Any], refs_stack: tuple[str, ...]) -> None:
+        if properties := schema.get("properties"):
+            for value in properties.values():
+                self._simplify(value, refs_stack)
+
+    def _array(self, schema: dict[str, Any], refs_stack: tuple[str, ...]) -> None:
+        if prefix_items := schema.get("prefixItems"):
+            for prefix_item in prefix_items:
+                self._simplify(prefix_item, refs_stack)
+
+        if items_schema := schema.get("items"):
+            self._simplify(items_schema, refs_stack)

livekit/plugins/google/version.py

@@ -12,4 +12,4 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = "0.3.0"
+__version__ = "1.3.11"

livekit_plugins_google-1.3.11.dist-info/METADATA

@@ -0,0 +1,63 @@
+Metadata-Version: 2.4
+Name: livekit-plugins-google
+Version: 1.3.11
+Summary: Agent Framework plugin for services from Google Cloud
+Project-URL: Documentation, https://docs.livekit.io
+Project-URL: Website, https://livekit.io/
+Project-URL: Source, https://github.com/livekit/agents
+Author: LiveKit
+License-Expression: Apache-2.0
+Keywords: ai,audio,gemini,google,livekit,realtime,video,voice
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Topic :: Multimedia :: Sound/Audio
+Classifier: Topic :: Multimedia :: Video
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Requires-Dist: google-auth<3,>=2
+Requires-Dist: google-cloud-speech<3,>=2
+Requires-Dist: google-cloud-texttospeech<3,>=2.32
+Requires-Dist: google-genai>=1.55; python_version >= '3.10'
+Requires-Dist: livekit-agents>=1.3.6
+Description-Content-Type: text/markdown
+
+# Google AI plugin for LiveKit Agents
+
+Support for Gemini, Gemini Live, Cloud Speech-to-Text, and Cloud Text-to-Speech.
+
+See [https://docs.livekit.io/agents/integrations/google/](https://docs.livekit.io/agents/integrations/google/) for more information.
+
+## Installation
+
+```bash
+pip install livekit-plugins-google
+```
+
+## Pre-requisites
+
+For credentials, you'll need a Google Cloud account and obtain the correct credentials. Credentials can be passed directly or via Application Default Credentials as specified in [How Application Default Credentials works](https://cloud.google.com/docs/authentication/application-default-credentials).
+
+To use the STT and TTS API, you'll need to enable the respective services for your Google Cloud project.
+
+- Cloud Speech-to-Text API
+- Cloud Text-to-Speech API
+
+## Live API model support
+
+LiveKit supports both Gemini Live API on both Gemini Developer API as well as Vertex AI. However, be aware they have slightly different behavior and use different model names.
+
+The following models are supported by Gemini Developer API:
+
+- gemini-2.0-flash-live-001
+- gemini-live-2.5-flash-preview
+- gemini-2.5-flash-native-audio-preview-09-2025
+
+And these on Vertex AI:
+
+- gemini-2.0-flash-exp
+- gemini-live-2.5-flash-preview-native-audio
+- gemini-live-2.5-flash-preview-native-audio-09-2025

livekit_plugins_google-1.3.11.dist-info/RECORD

@@ -0,0 +1,18 @@
+livekit/plugins/google/__init__.py,sha256=21ZYfsz4d4a5tP_po9WPtIv552gYh6thg7mcnkYA9vc,1445
+livekit/plugins/google/llm.py,sha256=eLLuXQZ0GMrl8blfb2staHr2ClAsYroJRydt0arT1Uk,24386
+livekit/plugins/google/log.py,sha256=GI3YWN5YzrafnUccljzPRS_ZALkMNk1i21IRnTl2vNA,69
+livekit/plugins/google/models.py,sha256=NOkEJVTmvZ7A6TSVCACoaST-qM84YSPwo_HkM5ct1mY,3171
+livekit/plugins/google/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+livekit/plugins/google/stt.py,sha256=Q3-gEAV5xykTLfmkj8bPq6mHdx4cn6W7_-fQrI7n85o,35246
+livekit/plugins/google/tools.py,sha256=cH8qXkQj6zQ_cWUV-4apjSeQaMhfK6907XKPAs9PVNo,1956
+livekit/plugins/google/tts.py,sha256=dVhGDN0Q-b_tGKdridkb5grl8YhBMcxTc_kIdcg4gQ8,19251
+livekit/plugins/google/utils.py,sha256=MSMsmPBsmxL-rSi5mc8d7ViI5bHgNEOO4Em0yHLhNyQ,8128
+livekit/plugins/google/version.py,sha256=Db2pVVYNC02fj0G6tMcFzTjBbAxJWVcZ5l1gTIq9VU4,601
+livekit/plugins/google/beta/__init__.py,sha256=4q5dx-Y6o9peCDziB03Skf5ngH4PTBsZC86ZawWrgnk,271
+livekit/plugins/google/beta/gemini_tts.py,sha256=SpKorOteQ7GYoGWsxV5YPuGeMexoosmtDXQVz_1ZeLA,8743
+livekit/plugins/google/realtime/__init__.py,sha256=_fW2NMN22F-hnQ4xAJ_g5lPbR7CvM_xXzSWlUQY-E-U,188
+livekit/plugins/google/realtime/api_proto.py,sha256=n6Rb-3qrZyByp8MSkBHA3TIW2E0IGKH1Xj7hKJM029M,2290
+livekit/plugins/google/realtime/realtime_api.py,sha256=_eCRUK2Bi4ypBEPcCzK9ym_isO8BAvmlXkgW1cO4P8w,54723
+livekit_plugins_google-1.3.11.dist-info/METADATA,sha256=sQqXHcC_xM0n6_MNZYlJJq61WRG4y422eYFDy0YeXD4,2467
+livekit_plugins_google-1.3.11.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+livekit_plugins_google-1.3.11.dist-info/RECORD,,

{livekit_plugins_google-0.3.0.dist-info → livekit_plugins_google-1.3.11.dist-info}/WHEEL

@@ -1,5 +1,4 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.43.0)
+Generator: hatchling 1.28.0
 Root-Is-Purelib: true
 Tag: py3-none-any
-

livekit_plugins_google-0.3.0.dist-info/METADATA

@@ -1,47 +0,0 @@
-Metadata-Version: 2.1
-Name: livekit-plugins-google
-Version: 0.3.0
-Summary: Agent Framework plugin for services from Google Cloud
-Home-page: https://github.com/livekit/agents
-License: Apache-2.0
-Project-URL: Documentation, https://docs.livekit.io
-Project-URL: Website, https://livekit.io/
-Project-URL: Source, https://github.com/livekit/agents
-Keywords: webrtc,realtime,audio,video,livekit
-Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: Apache Software License
-Classifier: Topic :: Multimedia :: Sound/Audio
-Classifier: Topic :: Multimedia :: Video
-Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.7
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3 :: Only
-Requires-Python: >=3.7.0
-Description-Content-Type: text/markdown
-Requires-Dist: numpy <2,>=1
-Requires-Dist: google-api-core <3,>=2
-Requires-Dist: google-auth <3,>=2
-Requires-Dist: google-cloud-core <3,>=2
-Requires-Dist: google-cloud-speech <3,>=2
-Requires-Dist: google-cloud-texttospeech <3,>=2
-Requires-Dist: google-cloud-translate <4,>=3
-Requires-Dist: googleapis-common-protos <2,>=1
-Requires-Dist: livekit >=0.9.2
-Requires-Dist: livekit-agents ~=0.5.dev0
-
-# LiveKit Plugins Google
-
-Agent Framework plugin for services from Google Cloud. Currently supporting Google's [Speech-to-Text](https://cloud.google.com/speech-to-text) API.
-
-## Installation
-
-```bash
-pip install livekit-plugins-google
-```
-
-## Pre-requisites
-
-For credentials, you'll need a Google Cloud account and obtain the correct credentials. Credentials can be passed directly or set as [GOOGLE_APPLICATION_CREDENTIALS](https://cloud.google.com/docs/authentication/application-default-credentials) environment variable.

livekit_plugins_google-0.3.0.dist-info/RECORD

@@ -1,9 +0,0 @@
-livekit/plugins/google/__init__.py,sha256=snPMHNLrurYbLWQOkV_o6qG1CEWsOCZ8ZfPMvmh5ejY,931
-livekit/plugins/google/models.py,sha256=DgiXOvGDO8D9rfCKHJL28lbyQR8mXXB2kpku-szXLRs,1185
-livekit/plugins/google/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-livekit/plugins/google/stt.py,sha256=lYA8hlkxG3YSw1Q34j8hgs4us5Ij-TLBQTRwtGPN9MY,15025
-livekit/plugins/google/version.py,sha256=G5iYozum4q7UpHwW43F7QfhzUfwcncPxBZ0gmUGsd5I,600
-livekit_plugins_google-0.3.0.dist-info/METADATA,sha256=sPd3OZxViD0Aq1uF1qJpbsYeqLAlq8tB720JXk-_RKw,1945
-livekit_plugins_google-0.3.0.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-livekit_plugins_google-0.3.0.dist-info/top_level.txt,sha256=OoDok3xUmXbZRvOrfvvXB-Juu4DX79dlq188E19YHoo,8
-livekit_plugins_google-0.3.0.dist-info/RECORD,,

livekit_plugins_google-0.3.0.dist-info/top_level.txt

@@ -1 +0,0 @@
-livekit