wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor(gemini-live): bring tool-result handling in line with the canonical realtime pattern

Browse Source 
Lays groundwork for cancel_on_interruption=False support on Gemini Live by
restructuring _process_completed_function_calls to match the shape used by
AWSNovaSonicLLMService and OpenAIRealtimeLLMService in #4441: a single-pass
forward iteration over raw context messages that detects async-tool
messages via async_tool_messages.parse_message and routes them — started
skipped silently, intermediate logged-as-error and surfaced via push_error,
final delivered via the formal FunctionResponse channel.

Replaces the prior two-pass structure that went through the adapter for
sync results — the service now uses a lightweight self._tool_call_id_to_name
map (populated when the model issues tool calls) for the name lookup the
adapter used to provide. Extracts a new GeminiLLMAdapter.to_function_response_dict
static method for the dict-coercion logic that wraps non-dict tool returns
as {value: <result>} for Gemini's FunctionResponse.response field; the
adapter's existing inline copy in _from_standard_message uses it too.

Example consolidation:

- Folds realtime-gemini-live-function-calling.py into the base
  realtime-gemini-live.py example so the base exercises function calling
  out of the box (matching realtime-openai.py and realtime-aws-nova-sonic.py).
- Renames realtime-gemini-live-vertex-function-calling.py to
  realtime-gemini-live-vertex.py, mirroring the consolidation.
- Adds realtime-gemini-live-async-tool.py.
- Updates scripts/evals/run-release-evals.py for the renames.

This commit alone doesn't make cancel_on_interruption=False fully work on
Gemini Live — additional investigation is pending. This is foundational
work to be built on.
This commit is contained in:
Paul Kompfner
2026-05-08 13:55:49 -04:00
parent ff80cde44e
commit 1a4a6f4edf
6 changed files with 227 additions and 103 deletions
Download Patch File Download Diff File Expand all files Collapse all files

109
examples/realtime/realtime-gemini-live-function-calling.py → examples/realtime/realtime-gemini-live-async-tool.py
View File

@@ -4,15 +4,25 @@
# SPDX-License-Identifier: BSD 2-Clause License
#
"""Example: async function call with the Gemini Live LLM service.
The ``get_current_weather`` tool is registered with
``cancel_on_interruption=False`` and simulates a slow API call (10s sleep).
While the call is in flight the conversation continues; the result arrives
later via the async-tool mechanism and is forwarded to Gemini Live as a
FunctionResponse so the model can integrate it naturally into its next turn.
"""
import asyncio
import os
import random
from datetime import datetime
from dotenv import load_dotenv
from loguru import logger
from pipecat.adapters.schemas.function_schema import FunctionSchema
from pipecat.adapters.schemas.tools_schema import AdapterType, ToolsSchema
from pipecat.adapters.schemas.tools_schema import ToolsSchema
from pipecat.frames.frames import LLMRunFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
@@ -31,33 +41,55 @@ load_dotenv(override=True)
async def fetch_weather_from_api(params: FunctionCallParams):
temperature = 75 if params.arguments["format"] == "fahrenheit" else 24
# Simulate a long-running API call so we can demonstrate that the
# conversation continues while the tool is in flight.
await asyncio.sleep(10)
temperature = (
random.randint(60, 85)
if params.arguments["format"] == "fahrenheit"
else random.randint(15, 30)
)
await params.result_callback(
{
"conditions": "nice",
"temperature": temperature,
"location": params.arguments["location"],
"format": params.arguments["format"],
"timestamp": datetime.now().strftime("%Y%m%d_%H%M%S"),
}
)
async def fetch_restaurant_recommendation(params: FunctionCallParams):
await params.result_callback({"name": "The Golden Dragon"})
weather_function = FunctionSchema(
name="get_current_weather",
description="Get the current weather",
properties={
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
},
"format": {
"type": "string",
"enum": ["celsius", "fahrenheit"],
"description": "The temperature unit to use. Infer this from the user's location.",
},
},
required=["location", "format"],
)
tools = ToolsSchema(standard_tools=[weather_function])
system_instruction = """
You are a helpful assistant who can answer questions and use tools.
You have three tools available to you:
1. get_current_weather: Use this tool to get the current weather in a specific location.
2. get_restaurant_recommendation: Use this tool to get a restaurant recommendation in a specific location.
3. google_search: Use this tool to search the web for information.
"""
system_instruction = (
"You are a friendly assistant. The user and you will engage in a spoken "
"dialog exchanging the transcripts of a natural real-time conversation. "
"Keep your responses short, generally two or three sentences for chatty "
"scenarios. When the user asks for the weather, call get_current_weather. "
"While you wait for the result, keep chatting with the user. When the "
"result arrives, share it with the user naturally."
)
# We use lambdas to defer transport parameter creation until the transport
# type is selected at runtime.
transport_params = {
"daily": lambda: DailyParams(
audio_in_enabled=True,
@@ -77,42 +109,6 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
weather_function = FunctionSchema(
name="get_current_weather",
description="Get the current weather",
properties={
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
},
"format": {
"type": "string",
"enum": ["celsius", "fahrenheit"],
"description": "The temperature unit to use. Infer this from the user's location.",
},
},
required=["location", "format"],
)
restaurant_function = FunctionSchema(
name="get_restaurant_recommendation",
description="Get a restaurant recommendation",
properties={
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
},
},
required=["location"],
)
search_tool = {"google_search": {}}
# KNOWN ISSUE: If using GeminiVertexLiveLLMService, it appears
# you cannot use the "google_search" tool alongside other tools.
# See https://github.com/googleapis/python-genai/issues/941.
tools = ToolsSchema(
standard_tools=[weather_function, restaurant_function],
custom_tools={AdapterType.GEMINI: [search_tool]},
)
llm = GeminiLiveLLMService(
api_key=os.environ["GOOGLE_API_KEY"],
settings=GeminiLiveLLMService.Settings(
@@ -121,13 +117,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tools=tools,
)
llm.register_function("get_current_weather", fetch_weather_from_api)
llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation)
llm.register_function(
"get_current_weather",
fetch_weather_from_api,
cancel_on_interruption=False,
)
# You can provide the system instructions and tools in the context rather
# than as arguments to GeminiLiveLLMService, but note that doing so will
# trigger a (fast) reconnection when the GeminiLiveLLMService first
# receives the context (i.e. when we send the LLMRunFrame below).
context = LLMContext()
# Server-side VAD is enabled by default; no local VAD is added.
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(context)
@@ -154,7 +149,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):
logger.info(f"Client connected")
# Kick off the conversation.
context.add_message(
{"role": "developer", "content": "Please introduce yourself to the user."}
)
@@ -166,7 +160,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
await task.cancel()
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
await runner.run(task)

0
examples/realtime/realtime-gemini-live-vertex-function-calling.py → examples/realtime/realtime-gemini-live-vertex.py
View File

85
examples/realtime/realtime-gemini-live.py
View File

@@ -6,10 +6,13 @@
import os
from datetime import datetime
from dotenv import load_dotenv
from loguru import logger
from pipecat.adapters.schemas.function_schema import FunctionSchema
from pipecat.adapters.schemas.tools_schema import AdapterType, ToolsSchema
from pipecat.frames.frames import LLMRunFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
@@ -23,6 +26,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -30,6 +34,32 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
load_dotenv(override=True)
async def fetch_weather_from_api(params: FunctionCallParams):
temperature = 75 if params.arguments["format"] == "fahrenheit" else 24
await params.result_callback(
{
"conditions": "nice",
"temperature": temperature,
"format": params.arguments["format"],
"timestamp": datetime.now().strftime("%Y%m%d_%H%M%S"),
}
)
async def fetch_restaurant_recommendation(params: FunctionCallParams):
await params.result_callback({"name": "The Golden Dragon"})
system_instruction = """
You are a helpful assistant who can answer questions and use tools.
You have three tools available to you:
1. get_current_weather: Use this tool to get the current weather in a specific location.
2. get_restaurant_recommendation: Use this tool to get a restaurant recommendation in a specific location.
3. google_search: Use this tool to search the web for information.
"""
# We use lambdas to defer transport parameter creation until the transport
# type is selected at runtime.
transport_params = {
@@ -51,23 +81,55 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
weather_function = FunctionSchema(
name="get_current_weather",
description="Get the current weather",
properties={
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
},
"format": {
"type": "string",
"enum": ["celsius", "fahrenheit"],
"description": "The temperature unit to use. Infer this from the user's location.",
},
},
required=["location", "format"],
)
restaurant_function = FunctionSchema(
name="get_restaurant_recommendation",
description="Get a restaurant recommendation",
properties={
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
},
},
required=["location"],
)
search_tool = {"google_search": {}}
# KNOWN ISSUE: If using GeminiVertexLiveLLMService, it appears
# you cannot use the "google_search" tool alongside other tools.
# See https://github.com/googleapis/python-genai/issues/941.
tools = ToolsSchema(
standard_tools=[weather_function, restaurant_function],
custom_tools={AdapterType.GEMINI: [search_tool]},
)
llm = GeminiLiveLLMService(
api_key=os.environ["GOOGLE_API_KEY"],
settings=GeminiLiveLLMService.Settings(
system_instruction=system_instruction,
voice="Aoede", # Puck, Charon, Kore, Fenrir, Aoede
# system_instruction="Talk like a pirate."
),
# inference_on_context_initialization=False,
tools=tools,
)
context = LLMContext(
[
{
"role": "user",
"content": "Say hello. Then ask if I want to hear a joke.",
},
],
)
llm.register_function("get_current_weather", fetch_weather_from_api)
llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation)
context = LLMContext()
# Server-side VAD is enabled by default; no local VAD is added.
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(context)
@@ -94,6 +156,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
async def on_client_connected(transport, client):
logger.info(f"Client connected")
# Kick off the conversation.
context.add_message(
{"role": "developer", "content": "Please introduce yourself to the user."}
)
await task.queue_frames([LLMRunFrame()])
@transport.event_handler("on_client_disconnected")