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

Merge pull request #1841 from pipecat-ai/aleix/base-text-aggregator-async

Browse Source 
make BaseTextAggregator and BaseTextFilter functions async
This commit is contained in:
Aleix Conchillo Flaqué
2025-05-20 13:13:54 -07:00
committed by GitHub
parent 54388c0d9b cbccbcd9e7
commit 609ff4e66c
15 changed files with 102 additions and 99 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
CHANGELOG.md
View File

@@ -68,6 +68,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
### Changed
- `BaseTextFilter` methods `filter()`, `update_settings()`,
`handle_interruption()` and `reset_interruption()` are now async.
- `BaseTextAggregator` methods `aggregate()`, `handle_interruption()` and
`reset()` are now async.
- The API version for `CartesiaTTSService` and `CartesiaHttpTTSService` has
been updated. Also, the `cartesia` dependency has been updated to 2.x.

19
examples/foundational/35-pattern-pair-voice-switching.py
View File

@@ -99,21 +99,14 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection, _: argparse.Namespac
)
# Register handler for voice switching
def on_voice_tag(match: PatternMatch):
async def on_voice_tag(match: PatternMatch):
voice_name = match.content.strip().lower()
if voice_name in VOICE_IDS:
voice_id = VOICE_IDS[voice_name]
# Create task to reset the TTS context after voice change
async def change_voice():
# First flush any existing audio to finish the current context
await tts.flush_audio()
# Then set the new voice
tts.set_voice(voice_id)
logger.info(f"Switched to {voice_name} voice")
# Schedule the voice change task
asyncio.create_task(change_voice())
# First flush any existing audio to finish the current context
await tts.flush_audio()
# Then set the new voice
tts.set_voice(VOICE_IDS[voice_name])
logger.info(f"Switched to {voice_name} voice")
else:
logger.warning(f"Unknown voice: {voice_name}")

6
examples/word-wrangler-gemini-live/server/bot_phone_local.py
View File

@@ -188,7 +188,7 @@ class HostResponseTextFilter(BaseTextFilter):
# No settings to update for this filter
pass
def filter(self, text: str) -> str:
async def filter(self, text: str) -> str:
# Remove case and whitespace for comparison
clean_text = text.strip().upper()
@@ -198,10 +198,10 @@ class HostResponseTextFilter(BaseTextFilter):
return text
def handle_interruption(self):
async def handle_interruption(self):
self._interrupted = True
def reset_interruption(self):
async def reset_interruption(self):
self._interrupted = False

6
examples/word-wrangler-gemini-live/server/bot_phone_twilio.py
View File

@@ -178,7 +178,7 @@ class HostResponseTextFilter(BaseTextFilter):
# No settings to update for this filter
pass
def filter(self, text: str) -> str:
async def filter(self, text: str) -> str:
# Remove case and whitespace for comparison
clean_text = text.strip().upper()
@@ -188,10 +188,10 @@ class HostResponseTextFilter(BaseTextFilter):
return text
def handle_interruption(self):
async def handle_interruption(self):
self._interrupted = True
def reset_interruption(self):
async def reset_interruption(self):
self._interrupted = False

14
src/pipecat/services/tts_service.py
View File

@@ -157,7 +157,7 @@ class TTSService(AIService):
self.set_voice(value)
elif key == "text_filter":
for filter in self._text_filters:
filter.update_settings(value)
await filter.update_settings(value)
else:
logger.warning(f"Unknown setting for TTS service: {key}")
@@ -183,7 +183,7 @@ class TTSService(AIService):
await self._maybe_pause_frame_processing()
sentence = self._text_aggregator.text
self._text_aggregator.reset()
await self._text_aggregator.reset()
self._processing_text = False
await self._push_tts_frames(sentence)
if isinstance(frame, LLMFullResponseEndFrame):
@@ -234,9 +234,9 @@ class TTSService(AIService):
async def _handle_interruption(self, frame: StartInterruptionFrame, direction: FrameDirection):
self._processing_text = False
self._text_aggregator.handle_interruption()
await self._text_aggregator.handle_interruption()
for filter in self._text_filters:
filter.handle_interruption()
await filter.handle_interruption()
async def _maybe_pause_frame_processing(self):
if self._processing_text and self._pause_frame_processing:
@@ -251,7 +251,7 @@ class TTSService(AIService):
if not self._aggregate_sentences:
text = frame.text
else:
text = self._text_aggregator.aggregate(frame.text)
text = await self._text_aggregator.aggregate(frame.text)
if text:
await self._push_tts_frames(text)
@@ -274,8 +274,8 @@ class TTSService(AIService):
# Process all filter.
for filter in self._text_filters:
filter.reset_interruption()
text = filter.filter(text)
await filter.reset_interruption()
text = await filter.filter(text)
if text:
await self.process_generator(self.run_tts(text))

6
src/pipecat/utils/text/base_text_aggregator.py
View File

@@ -25,7 +25,7 @@ class BaseTextAggregator(ABC):
pass
@abstractmethod
def aggregate(self, text: str) -> Optional[str]:
async def aggregate(self, text: str) -> Optional[str]:
"""Aggregates the specified text with the currently accumulated text.
This method should be implemented to define how the new text contributes
@@ -43,7 +43,7 @@ class BaseTextAggregator(ABC):
pass
@abstractmethod
def handle_interruption(self):
async def handle_interruption(self):
"""Handles interruptions. When an interruption occurs it is possible
that we might want to discard the aggregated text or do some internal
modifications to the aggregated text.
@@ -52,6 +52,6 @@ class BaseTextAggregator(ABC):
pass
@abstractmethod
def reset(self):
async def reset(self):
"""Clears the internally aggregated text."""
pass

8
src/pipecat/utils/text/base_text_filter.py
View File

@@ -10,17 +10,17 @@ from typing import Any, Mapping
class BaseTextFilter(ABC):
@abstractmethod
def update_settings(self, settings: Mapping[str, Any]):
async def update_settings(self, settings: Mapping[str, Any]):
pass
@abstractmethod
def filter(self, text: str) -> str:
async def filter(self, text: str) -> str:
pass
@abstractmethod
def handle_interruption(self):
async def handle_interruption(self):
pass
@abstractmethod
def reset_interruption(self):
async def reset_interruption(self):
pass

8
src/pipecat/utils/text/markdown_text_filter.py
View File

@@ -33,12 +33,12 @@ class MarkdownTextFilter(BaseTextFilter):
self._in_table = False
self._interrupted = False
def update_settings(self, settings: Mapping[str, Any]):
async def update_settings(self, settings: Mapping[str, Any]):
for key, value in settings.items():
if hasattr(self._settings, key):
setattr(self._settings, key, value)
def filter(self, text: str) -> str:
async def filter(self, text: str) -> str:
if self._settings.enable_text_filter:
# Remove newlines and replace with a space only when there's no text before or after
filtered_text = re.sub(r"^\s*\n", " ", text, flags=re.MULTILINE)
@@ -104,12 +104,12 @@ class MarkdownTextFilter(BaseTextFilter):
else:
return text
def handle_interruption(self):
async def handle_interruption(self):
self._interrupted = True
self._in_code_block = False
self._in_table = False
def reset_interruption(self):
async def reset_interruption(self):
self._interrupted = False
#

16
src/pipecat/utils/text/pattern_pair_aggregator.py
View File

@@ -5,7 +5,7 @@
#
import re
from typing import Callable, Optional, Tuple
from typing import Awaitable, Callable, Optional, Tuple
from loguru import logger
@@ -106,7 +106,7 @@ class PatternPairAggregator(BaseTextAggregator):
return self
def on_pattern_match(
self, pattern_id: str, handler: Callable[[PatternMatch], None]
self, pattern_id: str, handler: Callable[[PatternMatch], Awaitable[None]]
) -> "PatternPairAggregator":
"""Register a handler for when a pattern pair is matched.
@@ -124,7 +124,7 @@ class PatternPairAggregator(BaseTextAggregator):
self._handlers[pattern_id] = handler
return self
def _process_complete_patterns(self, text: str) -> Tuple[str, bool]:
async def _process_complete_patterns(self, text: str) -> Tuple[str, bool]:
"""Process all complete pattern pairs in the text.
Searches for all complete pattern pairs in the text, calls the
@@ -167,7 +167,7 @@ class PatternPairAggregator(BaseTextAggregator):
# Call the appropriate handler if registered
if pattern_id in self._handlers:
try:
self._handlers[pattern_id](pattern_match)
await self._handlers[pattern_id](pattern_match)
except Exception as e:
logger.error(f"Error in pattern handler for {pattern_id}: {e}")
@@ -204,7 +204,7 @@ class PatternPairAggregator(BaseTextAggregator):
return False
def aggregate(self, text: str) -> Optional[str]:
async def aggregate(self, text: str) -> Optional[str]:
"""Aggregate text and process pattern pairs.
This method adds the new text to the buffer, processes any complete pattern
@@ -223,7 +223,7 @@ class PatternPairAggregator(BaseTextAggregator):
self._text += text
# Process any complete patterns in the buffer
processed_text, modified = self._process_complete_patterns(self._text)
processed_text, modified = await self._process_complete_patterns(self._text)
# Only update the buffer if modifications were made
if modified:
@@ -245,7 +245,7 @@ class PatternPairAggregator(BaseTextAggregator):
# No complete sentence found yet
return None
def handle_interruption(self):
async def handle_interruption(self):
"""Handle interruptions by clearing the buffer.
Called when an interruption occurs in the processing pipeline,
@@ -253,7 +253,7 @@ class PatternPairAggregator(BaseTextAggregator):
"""
self._text = ""
def reset(self):
async def reset(self):
"""Clear the internally aggregated text.
Resets the aggregator to its initial state, discarding any

6
src/pipecat/utils/text/simple_text_aggregator.py
View File

@@ -23,7 +23,7 @@ class SimpleTextAggregator(BaseTextAggregator):
def text(self) -> str:
return self._text
def aggregate(self, text: str) -> Optional[str]:
async def aggregate(self, text: str) -> Optional[str]:
result: Optional[str] = None
self._text += text
@@ -35,8 +35,8 @@ class SimpleTextAggregator(BaseTextAggregator):
return result
def handle_interruption(self):
async def handle_interruption(self):
self._text = ""
def reset(self):
async def reset(self):
self._text = ""

6
src/pipecat/utils/text/skip_tags_aggregator.py
View File

@@ -43,7 +43,7 @@ class SkipTagsAggregator(BaseTextAggregator):
"""
return self._text
def aggregate(self, text: str) -> Optional[str]:
async def aggregate(self, text: str) -> Optional[str]:
"""Aggregate text and process pattern pairs.
This method adds the new text to the buffer, processes any complete pattern
@@ -77,7 +77,7 @@ class SkipTagsAggregator(BaseTextAggregator):
# No complete sentence found yet
return None
def handle_interruption(self):
async def handle_interruption(self):
"""Handle interruptions by clearing the buffer.
Called when an interruption occurs in the processing pipeline,
@@ -85,7 +85,7 @@ class SkipTagsAggregator(BaseTextAggregator):
"""
self._text = ""
def reset(self):
async def reset(self):
"""Clear the internally aggregated text.
Resets the aggregator to its initial state, discarding any

40
tests/test_markdown_text_filter.py
View File

@@ -30,7 +30,7 @@ class TestMarkdownTextFilter(unittest.IsolatedAsyncioTestCase):
Some inline code here
"""
result = self.filter.filter(input_text)
result = await self.filter.filter(input_text)
self.assertEqual(result.strip(), expected_text.strip())
async def test_space_preservation(self):
@@ -45,7 +45,7 @@ class TestMarkdownTextFilter(unittest.IsolatedAsyncioTestCase):
]
for text in input_text:
result = self.filter.filter(text)
result = await self.filter.filter(text)
self.assertEqual(
len(result), len(text), f"Space preservation failed for: '{text}'\nGot: '{result}'"
)
@@ -71,7 +71,7 @@ class TestMarkdownTextFilter(unittest.IsolatedAsyncioTestCase):
}
for input_text, expected in test_cases.items():
result = self.filter.filter(input_text)
result = await self.filter.filter(input_text)
self.assertEqual(
result,
expected,
@@ -88,7 +88,7 @@ class TestMarkdownTextFilter(unittest.IsolatedAsyncioTestCase):
2. Second item
3. Third item with bold"""
result = self.filter.filter(input_text)
result = await self.filter.filter(input_text)
self.assertEqual(
result.strip(),
expected.strip(),
@@ -106,7 +106,7 @@ class TestMarkdownTextFilter(unittest.IsolatedAsyncioTestCase):
}
for input_text, expected in test_cases.items():
result = self.filter.filter(input_text)
result = await self.filter.filter(input_text)
self.assertEqual(result, expected, f"HTML entity conversion failed for: '{input_text}'")
async def test_asterisk_removal(self):
@@ -120,7 +120,7 @@ class TestMarkdownTextFilter(unittest.IsolatedAsyncioTestCase):
}
for input_text, expected in test_cases.items():
result = self.filter.filter(input_text)
result = await self.filter.filter(input_text)
self.assertEqual(result, expected, f"Asterisk removal failed for: '{input_text}'")
async def test_newline_handling(self):
@@ -132,7 +132,7 @@ class TestMarkdownTextFilter(unittest.IsolatedAsyncioTestCase):
}
for input_text, expected in test_cases.items():
result = self.filter.filter(input_text)
result = await self.filter.filter(input_text)
self.assertEqual(
result, expected, f"Newline handling failed for:\n{input_text}\nGot:\n{result}"
)
@@ -148,7 +148,7 @@ class TestMarkdownTextFilter(unittest.IsolatedAsyncioTestCase):
}
for input_text, expected in test_cases.items():
result = self.filter.filter(input_text)
result = await self.filter.filter(input_text)
self.assertEqual(
result,
expected,
@@ -166,7 +166,7 @@ class TestMarkdownTextFilter(unittest.IsolatedAsyncioTestCase):
}
for input_text, expected in test_cases.items():
result = self.filter.filter(input_text)
result = await self.filter.filter(input_text)
self.assertEqual(result, expected, f"Inline code handling failed for: '{input_text}'")
async def test_simple_table_removal(self):
@@ -177,7 +177,7 @@ class TestMarkdownTextFilter(unittest.IsolatedAsyncioTestCase):
expected = ""
result = filter.filter(input_text)
result = await filter.filter(input_text)
self.assertEqual(
result.strip(),
expected.strip(),
@@ -198,15 +198,15 @@ class TestMarkdownTextFilter(unittest.IsolatedAsyncioTestCase):
# Test with text filtering disabled
text_with_markdown = "**bold** and *italic* with `code`"
self.assertEqual(
filter.filter(text_with_markdown),
await filter.filter(text_with_markdown),
text_with_markdown,
"Disabled filter should not modify text",
)
# Enable just text filtering
filter.update_settings({"enable_text_filter": True})
await filter.update_settings({"enable_text_filter": True})
self.assertEqual(
filter.filter(text_with_markdown),
await filter.filter(text_with_markdown),
"bold and italic with code",
"Enabled filter should remove markdown",
)
@@ -217,14 +217,18 @@ class TestMarkdownTextFilter(unittest.IsolatedAsyncioTestCase):
# Initial state - formatting should be removed
input_text = "**bold** and *italic*"
self.assertEqual(filter.filter(input_text), "bold and italic")
self.assertEqual(await filter.filter(input_text), "bold and italic")
# Disable text filtering
filter.update_settings({"enable_text_filter": False})
self.assertEqual(filter.filter(input_text), input_text, "Text filtering should be disabled")
await filter.update_settings({"enable_text_filter": False})
self.assertEqual(
await filter.filter(input_text), input_text, "Text filtering should be disabled"
)
# Re-enable text filtering
filter.update_settings({"enable_text_filter": True})
await filter.update_settings({"enable_text_filter": True})
self.assertEqual(
filter.filter(input_text), "bold and italic", "Text filtering should be re-enabled"
await filter.filter(input_text),
"bold and italic",
"Text filtering should be re-enabled",
)

28
tests/test_pattern_pair_aggregator.py
View File

@@ -5,7 +5,7 @@
#
import unittest
from unittest.mock import Mock
from unittest.mock import AsyncMock
from pipecat.utils.text.pattern_pair_aggregator import PatternMatch, PatternPairAggregator
@@ -13,7 +13,7 @@ from pipecat.utils.text.pattern_pair_aggregator import PatternMatch, PatternPair
class TestPatternPairAggregator(unittest.IsolatedAsyncioTestCase):
def setUp(self):
self.aggregator = PatternPairAggregator()
self.test_handler = Mock()
self.test_handler = AsyncMock()
# Add a test pattern
self.aggregator.add_pattern_pair(
@@ -28,12 +28,12 @@ class TestPatternPairAggregator(unittest.IsolatedAsyncioTestCase):
async def test_pattern_match_and_removal(self):
# First part doesn't complete the pattern
result = self.aggregator.aggregate("Hello <test>pattern")
result = await self.aggregator.aggregate("Hello <test>pattern")
self.assertIsNone(result)
self.assertEqual(self.aggregator.text, "Hello <test>pattern")
# Second part completes the pattern and includes an exclamation point
result = self.aggregator.aggregate(" content</test>!")
result = await self.aggregator.aggregate(" content</test>!")
# Verify the handler was called with correct PatternMatch object
self.test_handler.assert_called_once()
@@ -48,7 +48,7 @@ class TestPatternPairAggregator(unittest.IsolatedAsyncioTestCase):
self.assertEqual(result, "Hello !")
# Next sentence should be processed separately
result = self.aggregator.aggregate(" This is another sentence.")
result = await self.aggregator.aggregate(" This is another sentence.")
self.assertEqual(result, " This is another sentence.")
# Buffer should be empty after returning a complete sentence
@@ -56,7 +56,7 @@ class TestPatternPairAggregator(unittest.IsolatedAsyncioTestCase):
async def test_incomplete_pattern(self):
# Add text with incomplete pattern
result = self.aggregator.aggregate("Hello <test>pattern content")
result = await self.aggregator.aggregate("Hello <test>pattern content")
# No complete pattern yet, so nothing should be returned
self.assertIsNone(result)
@@ -68,13 +68,13 @@ class TestPatternPairAggregator(unittest.IsolatedAsyncioTestCase):
self.assertEqual(self.aggregator.text, "Hello <test>pattern content")
# Reset and confirm buffer is cleared
self.aggregator.reset()
await self.aggregator.reset()
self.assertEqual(self.aggregator.text, "")
async def test_multiple_patterns(self):
# Set up multiple patterns and handlers
voice_handler = Mock()
emphasis_handler = Mock()
voice_handler = AsyncMock()
emphasis_handler = AsyncMock()
self.aggregator.add_pattern_pair(
pattern_id="voice", start_pattern="<voice>", end_pattern="</voice>", remove_match=True
@@ -92,7 +92,7 @@ class TestPatternPairAggregator(unittest.IsolatedAsyncioTestCase):
# Test with multiple patterns in one text block
text = "Hello <voice>female</voice> I am <em>very</em> excited to meet you!"
result = self.aggregator.aggregate(text)
result = await self.aggregator.aggregate(text)
# Both handlers should be called with correct data
voice_handler.assert_called_once()
@@ -113,11 +113,11 @@ class TestPatternPairAggregator(unittest.IsolatedAsyncioTestCase):
async def test_handle_interruption(self):
# Start with incomplete pattern
result = self.aggregator.aggregate("Hello <test>pattern")
result = await self.aggregator.aggregate("Hello <test>pattern")
self.assertIsNone(result)
# Simulate interruption
self.aggregator.handle_interruption()
await self.aggregator.handle_interruption()
# Buffer should be cleared
self.assertEqual(self.aggregator.text, "")
@@ -127,13 +127,13 @@ class TestPatternPairAggregator(unittest.IsolatedAsyncioTestCase):
async def test_pattern_across_sentences(self):
# Test pattern that spans multiple sentences
result = self.aggregator.aggregate("Hello <test>This is sentence one.")
result = await self.aggregator.aggregate("Hello <test>This is sentence one.")
# First sentence contains start of pattern but no end, so no complete pattern yet
self.assertIsNone(result)
# Add second part with pattern end
result = self.aggregator.aggregate(" This is sentence two.</test> Final sentence.")
result = await self.aggregator.aggregate(" This is sentence two.</test> Final sentence.")
# Handler should be called with entire content
self.test_handler.assert_called_once()

12
tests/test_simple_text_aggregator.py
View File

@@ -14,16 +14,16 @@ class TestSimpleTextAggregator(unittest.IsolatedAsyncioTestCase):
self.aggregator = SimpleTextAggregator()
async def test_reset_aggregations(self):
assert self.aggregator.aggregate("Hello ") == None
assert await self.aggregator.aggregate("Hello ") == None
assert self.aggregator.text == "Hello "
self.aggregator.reset()
await self.aggregator.reset()
assert self.aggregator.text == ""
async def test_simple_sentence(self):
assert self.aggregator.aggregate("Hello ") == None
assert self.aggregator.aggregate("Pipecat!") == "Hello Pipecat!"
assert await self.aggregator.aggregate("Hello ") == None
assert await self.aggregator.aggregate("Pipecat!") == "Hello Pipecat!"
assert self.aggregator.text == ""
async def test_multiple_sentences(self):
assert self.aggregator.aggregate("Hello Pipecat! How are ") == "Hello Pipecat!"
assert self.aggregator.aggregate("you?") == " How are you?"
assert await self.aggregator.aggregate("Hello Pipecat! How are ") == "Hello Pipecat!"
assert await self.aggregator.aggregate("you?") == " How are you?"

20
tests/test_skip_tags_aggregator.py
View File

@@ -14,41 +14,41 @@ class TestSkipTagsAggregator(unittest.IsolatedAsyncioTestCase):
self.aggregator = SkipTagsAggregator([("<spell>", "</spell>")])
async def test_no_tags(self):
self.aggregator.reset()
await self.aggregator.reset()
# No tags involved, aggregate at end of sentence.
result = self.aggregator.aggregate("Hello Pipecat!")
result = await self.aggregator.aggregate("Hello Pipecat!")
self.assertEqual(result, "Hello Pipecat!")
self.assertEqual(self.aggregator.text, "")
async def test_basic_tags(self):
self.aggregator.reset()
await self.aggregator.reset()
# Tags involved, avoid aggregation during tags.
result = self.aggregator.aggregate("My email is <spell>foo@pipecat.ai</spell>.")
result = await self.aggregator.aggregate("My email is <spell>foo@pipecat.ai</spell>.")
self.assertEqual(result, "My email is <spell>foo@pipecat.ai</spell>.")
self.assertEqual(self.aggregator.text, "")
async def test_streaming_tags(self):
self.aggregator.reset()
await self.aggregator.reset()
# Tags involved, stream small chunk of texts.
result = self.aggregator.aggregate("My email is <sp")
result = await self.aggregator.aggregate("My email is <sp")
self.assertIsNone(result)
self.assertEqual(self.aggregator.text, "My email is <sp")
result = self.aggregator.aggregate("ell>foo.")
result = await self.aggregator.aggregate("ell>foo.")
self.assertIsNone(result)
self.assertEqual(self.aggregator.text, "My email is <spell>foo.")
result = self.aggregator.aggregate("bar@pipecat.")
result = await self.aggregator.aggregate("bar@pipecat.")
self.assertIsNone(result)
self.assertEqual(self.aggregator.text, "My email is <spell>foo.bar@pipecat.")
result = self.aggregator.aggregate("ai</spe")
result = await self.aggregator.aggregate("ai</spe")
self.assertIsNone(result)
self.assertEqual(self.aggregator.text, "My email is <spell>foo.bar@pipecat.ai</spe")
result = self.aggregator.aggregate("ll>.")
result = await self.aggregator.aggregate("ll>.")
self.assertEqual(result, "My email is <spell>foo.bar@pipecat.ai</spell>.")
self.assertEqual(self.aggregator.text, "")