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

Updated the BaseTextAggregator to categorize aggregations

Browse Source 
Modified the BaseTextAggregator type so that when text gets aggregated, metadata can
be associated with it. Currently, that just means a `type`, so that the aggregation
can be classified or described. Changes made to support this:
  - **IMPORTANT**: Aggregators are now expected to strip leading/trailing white space
    characters before returning their aggregation from `aggregation()` or `.text`. This
    way all aggregators have a consistent contract allowing downstream use to know how
    to stitch aggregations back together
  - Introduced a new `Aggregation` dataclass to represent both the aggregated `text` and
    a string identifying the `type` of aggregation (ex. "sentence", "word", "my custom
    aggregation")
  - **BREAKING**: `BaseTextAggregator.text` now returns an `Aggregation` (instead of `str`).
    To update: `aggregated_text = myAggregator.text` -> `aggregated_text = myAggregator.text.text`
  - **BREAKING**: `BaseTextAggregator.aggregate()` now returns `Optional[Aggregation]`
    (instead of `Optional[str]`). To update:
      ```
      aggregation = myAggregator.aggregate(text)
      if (aggregation):
        print(f"successfully aggregated text: {aggregation.text}") // instead of {aggregation}
      ```
  - `SimpleTextAggregator`, `SkipTagsAggregator`, `PatternPairAggregator` updated to
     produce/consume `Aggregation` objects.
  - All uses of the above Aggregators have been updated accordingly.
This commit is contained in:
mattie ruth backman
2025-11-14 18:11:55 -05:00
committed by Mattie Ruth
parent 26918728df
commit dcc20f86e1
11 changed files with 166 additions and 75 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
tests/test_pattern_pair_aggregator.py
View File

@@ -30,7 +30,7 @@ class TestPatternPairAggregator(unittest.IsolatedAsyncioTestCase):
# First part doesn't complete the pattern
result = await self.aggregator.aggregate("Hello <test>pattern")
self.assertIsNone(result)
self.assertEqual(self.aggregator.text, "Hello <test>pattern")
self.assertEqual(self.aggregator.text.text, "Hello <test>pattern")
# Second part completes the pattern and includes an exclamation point
result = await self.aggregator.aggregate(" content</test>!")
@@ -45,14 +45,16 @@ class TestPatternPairAggregator(unittest.IsolatedAsyncioTestCase):
# The exclamation point should be treated as a sentence boundary,
# so the result should include just text up to and including "!"
self.assertEqual(result, "Hello !")
self.assertEqual(result.text, "Hello !")
self.assertEqual(result.type, "sentence")
# Next sentence should be processed separately
# Next sentence should be processed separately. Spaces around the sentence
# should be stripped in the returned Aggregation.
result = await self.aggregator.aggregate(" This is another sentence.")
self.assertEqual(result, " This is another sentence.")
self.assertEqual(result.text, "This is another sentence.")
self.assertEqual(result.type, "sentence")
# Buffer should be empty after returning a complete sentence
self.assertEqual(self.aggregator.text, "")
self.assertEqual(self.aggregator.text.text, "")
async def test_incomplete_pattern(self):
# Add text with incomplete pattern
@@ -65,11 +67,11 @@ class TestPatternPairAggregator(unittest.IsolatedAsyncioTestCase):
self.test_handler.assert_not_called()
# Buffer should contain the incomplete text
self.assertEqual(self.aggregator.text, "Hello <test>pattern content")
self.assertEqual(self.aggregator.text.text, "Hello <test>pattern content")
# Reset and confirm buffer is cleared
await self.aggregator.reset()
self.assertEqual(self.aggregator.text, "")
self.assertEqual(self.aggregator.text.text, "")
async def test_multiple_patterns(self):
# Set up multiple patterns and handlers
@@ -106,10 +108,11 @@ class TestPatternPairAggregator(unittest.IsolatedAsyncioTestCase):
self.assertEqual(emphasis_match.content, "very")
# Voice pattern should be removed, emphasis pattern should remain
self.assertEqual(result, "Hello I am <em>very</em> excited to meet you!")
self.assertEqual(result.text, "Hello I am <em>very</em> excited to meet you!")
self.assertEqual(result.type, "sentence")
# Buffer should be empty
self.assertEqual(self.aggregator.text, "")
self.assertEqual(self.aggregator.text.text, "")
async def test_handle_interruption(self):
# Start with incomplete pattern
@@ -120,7 +123,7 @@ class TestPatternPairAggregator(unittest.IsolatedAsyncioTestCase):
await self.aggregator.handle_interruption()
# Buffer should be cleared
self.assertEqual(self.aggregator.text, "")
self.assertEqual(self.aggregator.text.text, "")
# Handler should not have been called
self.test_handler.assert_not_called()
@@ -141,7 +144,8 @@ class TestPatternPairAggregator(unittest.IsolatedAsyncioTestCase):
self.assertEqual(call_args.content, "This is sentence one. This is sentence two.")
# Pattern should be removed, resulting in text with sentences merged
self.assertEqual(result, "Hello Final sentence.")
self.assertEqual(result.text, "Hello Final sentence.")
self.assertEqual(result.type, "sentence")
# Buffer should be empty
self.assertEqual(self.aggregator.text, "")
self.assertEqual(self.aggregator.text.text, "")

18
tests/test_simple_text_aggregator.py
View File

@@ -15,15 +15,21 @@ class TestSimpleTextAggregator(unittest.IsolatedAsyncioTestCase):
async def test_reset_aggregations(self):
assert await self.aggregator.aggregate("Hello ") == None
assert self.aggregator.text == "Hello "
assert self.aggregator.text.text == "Hello"
await self.aggregator.reset()
assert self.aggregator.text == ""
assert self.aggregator.text.text == ""
async def test_simple_sentence(self):
assert await self.aggregator.aggregate("Hello ") == None
assert await self.aggregator.aggregate("Pipecat!") == "Hello Pipecat!"
assert self.aggregator.text == ""
aggregate = await self.aggregator.aggregate("Pipecat!")
assert aggregate.text == "Hello Pipecat!"
assert aggregate.type == "sentence"
assert self.aggregator.text.text == ""
async def test_multiple_sentences(self):
assert await self.aggregator.aggregate("Hello Pipecat! How are ") == "Hello Pipecat!"
assert await self.aggregator.aggregate("you?") == " How are you?"
aggregate = await self.aggregator.aggregate("Hello Pipecat! How are ")
assert aggregate.text == "Hello Pipecat!"
# Aggregators should strip leading/trailing spaces when returning text
assert self.aggregator.text.text == "How are"
aggregate = await self.aggregator.aggregate("you?")
assert aggregate.text == "How are you?"

24
tests/test_skip_tags_aggregator.py
View File

@@ -18,16 +18,18 @@ class TestSkipTagsAggregator(unittest.IsolatedAsyncioTestCase):
# No tags involved, aggregate at end of sentence.
result = await self.aggregator.aggregate("Hello Pipecat!")
self.assertEqual(result, "Hello Pipecat!")
self.assertEqual(self.aggregator.text, "")
self.assertEqual(result.text, "Hello Pipecat!")
self.assertEqual(result.type, "sentence")
self.assertEqual(self.aggregator.text.text, "")
async def test_basic_tags(self):
await self.aggregator.reset()
# Tags involved, avoid aggregation during tags.
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, "")
self.assertEqual(result.text, "My email is <spell>foo@pipecat.ai</spell>.")
self.assertEqual(result.type, "sentence")
self.assertEqual(self.aggregator.text.text, "")
async def test_streaming_tags(self):
await self.aggregator.reset()
@@ -35,20 +37,22 @@ class TestSkipTagsAggregator(unittest.IsolatedAsyncioTestCase):
# Tags involved, stream small chunk of texts.
result = await self.aggregator.aggregate("My email is <sp")
self.assertIsNone(result)
self.assertEqual(self.aggregator.text, "My email is <sp")
self.assertEqual(self.aggregator.text.text, "My email is <sp")
result = await self.aggregator.aggregate("ell>foo.")
self.assertIsNone(result)
self.assertEqual(self.aggregator.text, "My email is <spell>foo.")
self.assertEqual(self.aggregator.text.text, "My email is <spell>foo.")
result = await self.aggregator.aggregate("bar@pipecat.")
self.assertIsNone(result)
self.assertEqual(self.aggregator.text, "My email is <spell>foo.bar@pipecat.")
self.assertEqual(self.aggregator.text.text, "My email is <spell>foo.bar@pipecat.")
result = await self.aggregator.aggregate("ai</spe")
self.assertIsNone(result)
self.assertEqual(self.aggregator.text, "My email is <spell>foo.bar@pipecat.ai</spe")
self.assertEqual(self.aggregator.text.text, "My email is <spell>foo.bar@pipecat.ai</spe")
self.assertEqual(self.aggregator.text.type, "sentence")
result = await self.aggregator.aggregate("ll>.")
self.assertEqual(result, "My email is <spell>foo.bar@pipecat.ai</spell>.")
self.assertEqual(self.aggregator.text, "")
self.assertEqual(result.text, "My email is <spell>foo.bar@pipecat.ai</spell>.")
self.assertEqual(self.aggregator.text.text, "")
self.assertEqual(self.aggregator.text.type, "sentence")