Merge pull request #198 from pipecat-ai/aleix/websocket-transport

websocket transport support

CHANGELOG.md

@@ -9,6 +9,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- Added WebsocketServerTransport. This will create a websocket server and will
+  read messages coming from a client. The messages are serialized/deserialized
+  with protobufs. See `examples/websocket-server` for a detailed example.
+
 - Added function calling (LLMService.register_function()). This will allow the
   LLM to call functions you have registered when needed. For example, if you
   register a function to get the weather in Los Angeles and ask the LLM about
@@ -24,6 +28,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Fixed an issue where `camera_out_enabled` would cause the highg CPU usage if
   no image was provided.
 
+### Performance
+
+- Removed unnecessary audio input tasks.
 
 ## [0.0.24] - 2024-05-29
 

LICENSE

@@ -1,6 +1,6 @@
 BSD 2-Clause License
 
-Copyright (c) 2024, Kwindla Hultman Kramer
+Copyright (c) 2024, Daily
 
 Redistribution and use in source and binary forms, with or without
 modification, are permitted provided that the following conditions are met:

dev-requirements.txt

@@ -1,5 +1,6 @@
 autopep8~=2.1.0
 build~=1.2.1
+grpcio-tools~=1.62.2
 pip-tools~=7.4.1
 pytest~=8.2.0
 setuptools~=69.5.1

examples/foundational/02-llm-say-one-thing.py

@@ -44,7 +44,7 @@ async def main(room_url):
 
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
-            model="gpt-4-turbo-preview")
+            model="gpt-4o")
 
         messages = [
             {

examples/foundational/05-sync-speech-and-image.py

@@ -93,7 +93,7 @@ async def main(room_url):
 
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
-            model="gpt-4-turbo-preview")
+            model="gpt-4o")
 
         imagegen = FalImageGenService(
             params=FalImageGenService.InputParams(

examples/foundational/05a-local-sync-speech-and-image.py

@@ -76,7 +76,7 @@ async def process_frame(self, frame: Frame, direction: FrameDirection):
 
             llm = OpenAILLMService(
                 api_key=os.getenv("OPENAI_API_KEY"),
-                model="gpt-4-turbo-preview")
+                model="gpt-4o")
 
             tts = ElevenLabsTTSService(
                 aiohttp_session=session,

examples/foundational/06a-image-sync.py

@@ -81,7 +81,7 @@ async def main(room_url: str, token):
 
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
-            model="gpt-4-turbo-preview")
+            model="gpt-4o")
 
         messages = [
             {

examples/foundational/07-interruptible.py

@@ -53,7 +53,7 @@ async def main(room_url: str, token):
 
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
-            model="gpt-4-turbo-preview")
+            model="gpt-4o")
 
         messages = [
             {

examples/foundational/07c-interruptible-deepgram.py

@@ -53,7 +53,7 @@ async def main(room_url: str, token):
 
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
-            model="gpt-4-turbo-preview")
+            model="gpt-4o")
 
         messages = [
             {

examples/foundational/11-sound-effects.py

@@ -95,7 +95,7 @@ async def main(room_url: str, token):
 
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
-            model="gpt-4-turbo-preview")
+            model="gpt-4o")
 
         tts = ElevenLabsTTSService(
             aiohttp_session=session,

examples/foundational/14-function-calling.py

@@ -66,7 +66,7 @@ async def main(room_url: str, token):
 
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
-            model="gpt-4-turbo-preview")
+            model="gpt-4o")
         llm.register_function(
             "get_current_weather",
             fetch_weather_from_api,

examples/moondream-chatbot/bot.py

@@ -145,7 +145,7 @@ async def main(room_url: str, token):
 
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
-            model="gpt-4-turbo-preview")
+            model="gpt-4o")
 
         ta = TalkingAnimation()
 

examples/simple-chatbot/bot.py

@@ -117,7 +117,7 @@ async def main(room_url: str, token):
 
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
-            model="gpt-4-turbo-preview")
+            model="gpt-4o")
 
         messages = [
             {

examples/storytelling-chatbot/src/bot.py

@@ -56,7 +56,7 @@ async def main(room_url, token=None):
 
         llm_service = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
-            model="gpt-4-turbo"
+            model="gpt-4o"
         )
 
         tts_service = ElevenLabsTTSService(

examples/translation-chatbot/bot.py

@@ -97,7 +97,8 @@ async def main(room_url: str, token):
         )
 
         llm = OpenAILLMService(
-            api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4-turbo-preview"
+            api_key=os.getenv("OPENAI_API_KEY"),
+            model="gpt-4o"
         )
 
         sa = SentenceAggregator()

examples/websocket-server/README.md

@@ -0,0 +1,27 @@
+# Websocket Server
+
+This is an example that shows how to use `WebsocketServerTransport` to communicate with a web client.
+
+## Get started
+
+```python
+python3 -m venv venv
+source venv/bin/activate
+pip install -r requirements.txt
+```
+
+## Run the bot
+
+```bash
+python bot.py
+```
+
+## Run the HTTP server
+
+This will host the static web client:
+
+```bash
+python -m http.server
+```
+
+Then, visit `http://localhost:8000` in your browser to start a session.