github: add linting workflow

.github/workflows/lint.yaml

@@ -0,0 +1,32 @@
+name: lint
+
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - "**"
+    paths-ignore:
+      - "docs/**"
+
+concurrency:
+  group: build-lint-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  autopep8:
+    name: "Formatting lints"
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v4
+      - name: autopep8
+        id: autopep8
+        uses: peter-evans/autopep8@v2
+        with:
+          args: --exit-code -r -d -a -a src/
+      - name: Fail if autopep8 requires changes
+        if: steps.autopep8.outputs.exit-code == 2
+        run: exit 1

src/dailyai/pipeline/aggregators.py

@@ -57,7 +57,8 @@ async def process_frame(self, frame: Frame) -> AsyncGenerator[Frame, None]:
             # Sometimes VAD triggers quickly on and off. If we don't get any transcription,
             # it creates empty LLM message queue frames
             if len(self.aggregation) > 0:
-                self.messages.append({"role": self._role, "content": self.aggregation})
+                self.messages.append(
+                    {"role": self._role, "content": self.aggregation})
                 self.aggregation = ""
                 yield self._end_frame()
                 yield LLMMessagesQueueFrame(self.messages)
@@ -110,7 +111,8 @@ def __init__(
         self.pass_through = pass_through
 
     async def process_frame(self, frame: Frame) -> AsyncGenerator[Frame, None]:
-        # We don't do anything with non-text frames, pass it along to next in the pipeline.
+        # We don't do anything with non-text frames, pass it along to next in
+        # the pipeline.
         if not isinstance(frame, TextFrame):
             yield frame
             return
@@ -132,7 +134,8 @@ async def process_frame(self, frame: Frame) -> AsyncGenerator[Frame, None]:
             # though we check it above
             self.sentence += frame.text
             if self.sentence.endswith((".", "?", "!")):
-                self.messages.append({"role": self.role, "content": self.sentence})
+                self.messages.append(
+                    {"role": self.role, "content": self.sentence})
                 self.sentence = ""
                 yield LLMMessagesQueueFrame(self.messages)
         else:
@@ -144,17 +147,24 @@ async def process_frame(self, frame: Frame) -> AsyncGenerator[Frame, None]:
 
 class LLMUserContextAggregator(LLMContextAggregator):
     def __init__(
-        self, messages: list[dict], bot_participant_id=None, complete_sentences=True
-    ):
+            self,
+            messages: list[dict],
+            bot_participant_id=None,
+            complete_sentences=True):
         super().__init__(
-            messages, "user", bot_participant_id, complete_sentences, pass_through=False
-        )
+            messages,
+            "user",
+            bot_participant_id,
+            complete_sentences,
+            pass_through=False)
 
 
 class LLMAssistantContextAggregator(LLMContextAggregator):
     def __init__(
-        self, messages: list[dict], bot_participant_id=None, complete_sentences=True
-    ):
+            self,
+            messages: list[dict],
+            bot_participant_id=None,
+            complete_sentences=True):
         super().__init__(
             messages,
             "assistant",
@@ -328,7 +338,8 @@ async def process_frame(self, frame: Frame) -> AsyncGenerator[Frame, None]:
                 continue
             seen_ids.add(id(frame))
 
-            # Skip passing along EndParallelPipeQueueFrame, because we use them for our own flow control.
+            # Skip passing along EndParallelPipeQueueFrame, because we use them
+            # for our own flow control.
             if not isinstance(frame, EndPipeFrame):
                 yield frame
 

src/dailyai/pipeline/frames.py

@@ -13,7 +13,7 @@ class ControlFrame(Frame):
     # Control frames should contain no instance data, so
     # equality is based solely on the class.
     def __eq__(self, other):
-        return type(other) == self.__class__
+        return isinstance(other, self.__class__)
 
 
 class StartFrame(ControlFrame):

src/dailyai/pipeline/merge_pipeline.py

@@ -6,15 +6,18 @@
 class SequentialMergePipeline(Pipeline):
     """This class merges the sink queues from a list of pipelines. Frames from
     each pipeline's sink are merged in the order of pipelines in the list."""
-    def __init__(self, pipelines:List[Pipeline]):
+
+    def __init__(self, pipelines: List[Pipeline]):
         super().__init__([])
         self.pipelines = pipelines
 
     async def run_pipeline(self):
         for pipeline in self.pipelines:
             while True:
                 frame = await pipeline.sink.get()
-                if isinstance(frame, EndFrame) or isinstance(frame, EndPipeFrame):
+                if isinstance(
+                        frame, EndFrame) or isinstance(
+                        frame, EndPipeFrame):
                     break
                 await self.sink.put(frame)
 

src/dailyai/pipeline/opeanai_llm_aggregator.py

@@ -69,7 +69,10 @@ async def process_frame(self, frame: Frame) -> AsyncGenerator[Frame, None]:
         else:
             yield frame
 
-    def string_aggregator(self, frame: Frame, aggregation: str | None) -> str | None:
+    def string_aggregator(
+            self,
+            frame: Frame,
+            aggregation: str | None) -> str | None:
         if not isinstance(frame, TextFrame):
             raise TypeError(
                 "Frame must be a TextFrame instance to be aggregated by a string aggregator."
@@ -94,7 +97,7 @@ def __init__(self, context: OpenAILLMContext):
 
 class OpenAIAssistantContextAggregator(OpenAIContextAggregator):
 
-    def __init__(self, context:OpenAILLMContext):
+    def __init__(self, context: OpenAILLMContext):
         super().__init__(
             context,
             aggregator=self.string_aggregator,

src/dailyai/pipeline/pipeline.py

@@ -89,7 +89,8 @@ async def run_pipeline(self):
                 ):
                     break
         except asyncio.CancelledError:
-            # this means there's been an interruption, do any cleanup necessary here.
+            # this means there's been an interruption, do any cleanup necessary
+            # here.
             for processor in self.processors:
                 await processor.interrupted()
             pass
@@ -107,4 +108,3 @@ async def _run_pipeline_recursively(
                     yield final_frame
         else:
             yield initial_frame
-

src/dailyai/services/ai_services.py

@@ -28,6 +28,7 @@ class AIService(FrameProcessor):
     def __init__(self):
         self.logger = logging.getLogger("dailyai")
 
+
 class LLMService(AIService):
     """This class is a no-op but serves as a base class for LLM services."""
 
@@ -76,7 +77,8 @@ async def process_frame(self, frame: Frame) -> AsyncGenerator[Frame, None]:
             async for audio_chunk in self.run_tts(text):
                 yield AudioFrame(audio_chunk)
 
-            # note we pass along the text frame *after* the audio, so the text frame is completed after the audio is processed.
+            # note we pass along the text frame *after* the audio, so the text
+            # frame is completed after the audio is processed.
             yield TextFrame(text)
 
 

src/dailyai/services/anthropic_llm_service.py

@@ -9,7 +9,11 @@
 
 class AnthropicLLMService(LLMService):
 
-    def __init__(self, api_key, model="claude-3-opus-20240229", max_tokens=1024):
+    def __init__(
+            self,
+            api_key,
+            model="claude-3-opus-20240229",
+            max_tokens=1024):
         super().__init__()
         self.client = AsyncAnthropic(api_key=api_key)
         self.model = model

src/dailyai/services/azure_ai_services.py

@@ -44,8 +44,7 @@ async def run_tts(self, sentence) -> AsyncGenerator[bytes, None]:
             "<mstts:express-as style='lyrical' styledegree='2' role='SeniorFemale'>"
             "<prosody rate='1.05'>"
             f"{sentence}"
-            "</prosody></mstts:express-as></voice></speak> "
-        )
+            "</prosody></mstts:express-as></voice></speak> ")
         result = await asyncio.to_thread(self.speech_synthesizer.speak_ssml, (ssml))
         self.logger.info("Got azure tts result")
         if result.reason == ResultReason.SynthesizingAudioCompleted:
@@ -55,16 +54,22 @@ async def run_tts(self, sentence) -> AsyncGenerator[bytes, None]:
         elif result.reason == ResultReason.Canceled:
             cancellation_details = result.cancellation_details
             self.logger.info(
-                "Speech synthesis canceled: {}".format(cancellation_details.reason)
-            )
+                "Speech synthesis canceled: {}".format(
+                    cancellation_details.reason))
             if cancellation_details.reason == CancellationReason.Error:
                 self.logger.info(
-                    "Error details: {}".format(cancellation_details.error_details)
-                )
+                    "Error details: {}".format(
+                        cancellation_details.error_details))
 
 
 class AzureLLMService(BaseOpenAILLMService):
-    def __init__(self, *, api_key, endpoint, api_version="2023-12-01-preview", model):
+    def __init__(
+            self,
+            *,
+            api_key,
+            endpoint,
+            api_version="2023-12-01-preview",
+            model):
         self._endpoint = endpoint
         self._api_version = api_version
 
@@ -101,7 +106,9 @@ def __init__(
 
     async def run_image_gen(self, sentence) -> tuple[str, bytes]:
         url = f"{self._azure_endpoint}openai/images/generations:submit?api-version={self._api_version}"
-        headers = {"api-key": self._api_key, "Content-Type": "application/json"}
+        headers = {
+            "api-key": self._api_key,
+            "Content-Type": "application/json"}
         body = {
             # Enter your prompt text here
             "prompt": sentence,
@@ -112,7 +119,8 @@ async def run_image_gen(self, sentence) -> tuple[str, bytes]:
             url, headers=headers, json=body
         ) as submission:
             # We never get past this line, because this header isn't
-            # defined on a 429 response, but something is eating our exceptions!
+            # defined on a 429 response, but something is eating our
+            # exceptions!
             operation_location = submission.headers["operation-location"]
             status = ""
             attempts_left = 120
@@ -130,8 +138,7 @@ async def run_image_gen(self, sentence) -> tuple[str, bytes]:
                 status = json_response["status"]
 
             image_url = (
-                json_response["result"]["data"][0]["url"] if json_response else None
-            )
+                json_response["result"]["data"][0]["url"] if json_response else None)
             if not image_url:
                 raise Exception("Image generation failed")
             # Load the image from the url