Merge branch 'main' into cb/09-bots-arguing

src/dailyai/services/daily_transport_service.py

@@ -62,7 +62,7 @@ class DailyTransportService(EventHandler):
         self.camera_height = 768
         self.camera_enabled = False
 
-        self.send_queue = asyncio.Queue()
+        self.send_queue = asyncio.Queue(maxsize=5)
         self.receive_queue = asyncio.Queue()
 
         self.other_participant_has_joined = False

src/dailyai/services/fal_ai_services.py

@@ -24,8 +24,7 @@ class FalImageGenService(ImageGenService):
             print("past fal handler init, about to wait for iter_events...")
             for event in handler.iter_events():
                 if isinstance(event, fal.apps.InProgress):
-                    print('Request in progress')
-                    print(event.logs)
+                    pass
 
             result = handler.get()
 

src/samples/foundational/01a-greet-user.py

@@ -1,3 +1,4 @@
+import argparse
 import asyncio
 import time
 from typing import AsyncGenerator
@@ -38,10 +39,7 @@ async def main(room_url):
         print(f"participant joined: {participant['info']['userName']}")
         if participant["info"]["isLocal"]:
             return
-        audio_generator: AsyncGenerator[bytes, None] = tts.run_tts(f"Hello there, {participant['info']['userName']}!")
-
-        async for audio in audio_generator:
-            transport.output_queue.put(QueueFrame(FrameType.AUDIO, audio))
+        await tts.say(f"Hello there, {participant['info']['userName']}!", transport.send_queue)
 
     print("setting up call state handler")
     @transport.event_handler("on_call_state_updated")
@@ -52,4 +50,10 @@ async def main(room_url):
 
 
 if __name__ == "__main__":
-    asyncio.run(main("https://chad-hq.daily.co/howdy"))
+    parser = argparse.ArgumentParser(description="Simple Daily Bot Sample")
+    parser.add_argument(
+        "-u", "--url", type=str, required=True, help="URL of the Daily room to join"
+    )
+
+    args, unknown = parser.parse_known_args()
+    asyncio.run(main(args.url))

src/samples/foundational/05-sync-speech-and-text.py

@@ -16,8 +16,9 @@ async def main(room_url):
         meeting_duration_minutes,
     )
     transport.mic_enabled = True
-    transport.camera_enabled = True
     transport.mic_sample_rate = 16000
+    
+    transport.camera_enabled = True
     transport.camera_width = 1024
     transport.camera_height = 1024
 

src/samples/foundational/09-bots-arguing.py

@@ -0,0 +1,67 @@
+import argparse
+import asyncio
+import requests
+import time
+import urllib.parse
+
+from dailyai.services.daily_transport_service import DailyTransportService
+from dailyai.services.azure_ai_services import AzureLLMService, AzureTTSService
+from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
+from dailyai.queue_frame import QueueFrame, FrameType
+
+async def main(room_url:str):
+    global transport
+    global llm
+    global tts
+
+    transport = DailyTransportService(
+        room_url,
+        None,
+        "Respond bot",
+        5,
+    )
+    transport.mic_enabled = True
+    transport.mic_sample_rate = 16000
+    transport.camera_enabled = False
+
+    llm = AzureLLMService()
+    tts1 = AzureTTSService()
+    tts2 = ElevenLabsTTSService()
+
+    async def argue():
+        bot1_messages = [
+            {"role": "system", "content": "You strongly believe that a hot dog is a sandwich. Start by stating this fact in a few sentences, then be prepared to debate this with the user. Your responses should only be a few sentences long."},
+        ]
+        bot2_messages = [
+            {"role": "system", "content": "You strongly believe that a hot dog is not a sandwich. Debate this with the user, only responding with a few sentences."},
+        ]
+
+        for i in range(1, 5):
+            print(f"In iteration {i}")
+            # Run the LLMs synchronously for the back-and-forth
+            bot1_msg = await llm.run_llm(bot1_messages)
+            print(f"bot1_msg: {bot1_msg}")
+            bot1_messages.append({"role": "assistant", "content": bot1_msg})
+            bot2_messages.append({"role": "user", "content": bot1_msg})
+
+            await tts1.say(bot1_msg, transport.send_queue)
+
+            bot2_msg = await llm.run_llm(bot2_messages)
+            print(f"bot2_msg: {bot2_msg}")
+            bot2_messages.append({"role": "assistant", "content": bot2_msg})
+            bot1_messages.append({"role": "user", "content": bot2_msg})
+
+            await tts2.say(bot2_msg, transport.send_queue)
+
+    await asyncio.gather(transport.run(), argue())
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Simple Daily Bot Sample")
+    parser.add_argument(
+        "-u", "--url", type=str, required=True, help="URL of the Daily room to join"
+    )
+
+    args, unknown = parser.parse_known_args()
+
+    asyncio.run(main(args.url))

src/samples/foundational/09a-characters-arguing.py

@@ -0,0 +1,109 @@
+import argparse
+import asyncio
+import requests
+import time
+import urllib.parse
+
+from dailyai.services.daily_transport_service import DailyTransportService
+from dailyai.services.azure_ai_services import AzureLLMService, AzureTTSService
+from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
+from dailyai.services.fal_ai_services import FalImageGenService
+from dailyai.services.open_ai_services import OpenAIImageGenService
+from dailyai.queue_frame import QueueFrame, FrameType
+
+async def main(room_url:str):
+    global transport
+    global llm
+    global tts
+
+    transport = DailyTransportService(
+        room_url,
+        None,
+        "Respond bot",
+        600,
+    )
+    transport.mic_enabled = True
+    transport.mic_sample_rate = 16000
+    transport.camera_enabled = True
+    transport.camera_width = 1024
+    transport.camera_height = 1024
+
+    llm = AzureLLMService()
+    tts1 = AzureTTSService()
+    tts2 = ElevenLabsTTSService()
+    dalle = FalImageGenService(image_size="1024x1024")
+    # dalle = OpenAIImageGenService(image_size="1024x1024")
+
+    bot1_messages = [
+        {"role": "system", "content": "You are a stern librarian. You strongly believe that a hot dog is a sandwich. Start by stating this fact in a few sentences, then be prepared to debate this with the user. You shouldn't ever compromise on the fundamental truth that a hot dog is a sandwich. Your responses should only be a few sentences long."},
+    ]
+    bot2_messages = [
+        {"role": "system", "content": "You are a silly cat, and you strongly believe that a hot dog is not a sandwich. Debate this with the user, only responding with a few sentences. Don't ever accept that a hot dog is a sandwich."},
+    ]
+    
+    async def get_bot1_statement():
+        # Run the LLMs synchronously for the back-and-forth
+        bot1_msg = await llm.run_llm(bot1_messages)
+        print(f"bot1_msg: {bot1_msg}")
+        bot1_messages.append({"role": "assistant", "content": bot1_msg})
+        bot2_messages.append({"role": "user", "content": bot1_msg})
+
+        all_audio = bytearray()
+        async for audio in tts1.run_tts(bot1_msg):
+            all_audio.extend(audio)
+
+        return all_audio
+    
+    async def get_bot2_statement():
+        # Run the LLMs synchronously for the back-and-forth
+        bot2_msg = await llm.run_llm(bot2_messages)
+        print(f"bot2_msg: {bot2_msg}")
+        bot2_messages.append({"role": "assistant", "content": bot2_msg})
+        bot1_messages.append({"role": "user", "content": bot2_msg})
+
+        all_audio = bytearray()
+        async for audio in tts2.run_tts(bot2_msg):
+            all_audio.extend(audio)
+
+        return all_audio
+
+    async def argue():
+        for i in range(100):
+            print(f"In iteration {i}")
+
+            bot1_description = "A woman conservatively dressed as a librarian in a library surrounded by books, cartoon, serious, highly detailed"
+
+            (audio1, image_data1) = await asyncio.gather(
+                get_bot1_statement(), dalle.run_image_gen(bot1_description)
+            )
+            await transport.send_queue.put(
+                [
+                    QueueFrame(FrameType.IMAGE, image_data1[1]),
+                    QueueFrame(FrameType.AUDIO, audio1),
+                ]
+            )
+
+            bot2_description = "A cat dressed in a hot dog costume, cartoon, bright colors, funny, highly detailed"
+
+            (audio2, image_data2) = await asyncio.gather(
+                get_bot2_statement(), dalle.run_image_gen(bot2_description)
+            )
+            await transport.send_queue.put(
+                [
+                    QueueFrame(FrameType.IMAGE, image_data2[1]),
+                    QueueFrame(FrameType.AUDIO, audio2),
+                ]
+            )
+
+    await asyncio.gather(transport.run(), argue())
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Simple Daily Bot Sample")
+    parser.add_argument(
+        "-u", "--url", type=str, required=True, help="URL of the Daily room to join"
+    )
+
+    args, unknown = parser.parse_known_args()
+
+    asyncio.run(main(args.url))

src/samples/foundational/09b-debate-generator.py

@@ -0,0 +1,119 @@
+import argparse
+import asyncio
+import requests
+import time
+import urllib.parse
+
+from dailyai.services.daily_transport_service import DailyTransportService
+from dailyai.services.azure_ai_services import AzureLLMService, AzureTTSService
+from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
+from dailyai.services.fal_ai_services import FalImageGenService
+from dailyai.services.open_ai_services import OpenAIImageGenService
+from dailyai.queue_frame import QueueFrame, FrameType
+
+async def main(room_url:str):
+    global transport
+    global llm
+    global tts
+
+    transport = DailyTransportService(
+        room_url,
+        None,
+        "Respond bot",
+        600,
+    )
+    transport.mic_enabled = True
+    transport.mic_sample_rate = 16000
+    transport.camera_enabled = True
+    transport.camera_width = 1024
+    transport.camera_height = 1024
+
+    llm = AzureLLMService()
+    tts1 = AzureTTSService()
+    tts2 = ElevenLabsTTSService()
+    dalle = FalImageGenService(image_size="1024x1024")
+    # dalle = OpenAIImageGenService(image_size="1024x1024")
+
+    topic = "Are pokemon edible?"
+    affirmative = "A woman dressed as a cowboy, outside on a ranch"
+    negative = "Pikachu in a business suit"
+    
+    topic = "Is a hot dog a sandwich?"
+    affirmative = "A woman conservatively dressed as a librarian in a library surrounded by books"
+    negative = "A cat dressed in a hot dog costume"
+
+
+
+    bot1_messages = [
+        {"role": "system", "content": f"You are {affirmative}. You're in a debate, and the topic is: '{topic}'. You're arguing the affirmative. Start by stating this fact in a few sentences, then be prepared to debate this with the user. You shouldn't ever agree with the user. Your responses should only be a few sentences long."},
+    ]
+    bot2_messages = [
+        {"role": "system", "content": f"You are {negative}. You're in a debate, and the topic is: '{topic}'. You're arguing the negative.  Debate this with the user, only responding with a few sentences. Don't ever agree with the user."},
+    ]
+    
+    async def get_bot1_statement():
+        # Run the LLMs synchronously for the back-and-forth
+        bot1_msg = await llm.run_llm(bot1_messages)
+        print(f"bot1_msg: {bot1_msg}")
+        bot1_messages.append({"role": "assistant", "content": bot1_msg})
+        bot2_messages.append({"role": "user", "content": bot1_msg})
+
+        all_audio = bytearray()
+        async for audio in tts1.run_tts(bot1_msg):
+            all_audio.extend(audio)
+
+        return all_audio
+    
+    async def get_bot2_statement():
+        # Run the LLMs synchronously for the back-and-forth
+        bot2_msg = await llm.run_llm(bot2_messages)
+        print(f"bot2_msg: {bot2_msg}")
+        bot2_messages.append({"role": "assistant", "content": bot2_msg})
+        bot1_messages.append({"role": "user", "content": bot2_msg})
+
+        all_audio = bytearray()
+        async for audio in tts2.run_tts(bot2_msg):
+            all_audio.extend(audio)
+
+        return all_audio
+
+    async def argue():
+        for i in range(100):
+            print(f"In iteration {i}")
+
+            bot1_description = f"{affirmative}, cartoon, highly detailed"
+
+            (audio1, image_data1) = await asyncio.gather(
+                get_bot1_statement(), dalle.run_image_gen(bot1_description)
+            )
+            await transport.send_queue.put(
+                [
+                    QueueFrame(FrameType.IMAGE, image_data1[1]),
+                    QueueFrame(FrameType.AUDIO, audio1),
+                ]
+            )
+
+            bot2_description = f"{negative}, cartoon, bright colors, funny, highly detailed"
+
+            (audio2, image_data2) = await asyncio.gather(
+                get_bot2_statement(), dalle.run_image_gen(bot2_description)
+            )
+            await transport.send_queue.put(
+                [
+                    QueueFrame(FrameType.IMAGE, image_data2[1]),
+                    QueueFrame(FrameType.AUDIO, audio2),
+                ]
+            )
+
+    await asyncio.gather(transport.run(), argue())
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Simple Daily Bot Sample")
+    parser.add_argument(
+        "-u", "--url", type=str, required=True, help="URL of the Daily room to join"
+    )
+
+    args, unknown = parser.parse_known_args()
+
+    asyncio.run(main(args.url))