482 unify version across demos (vocodedev#489)

* Update vocode version in apps/client_backend/pyproject.toml last stable vocode Version

* Update langchain_agent README and pyproject.toml to last stable vocode version

* Update apps/telegram_bot Python version and Vocode dependency vocodedev#482

* Update apps/telephony_app dependencies and fix documentation links vocodedev#482

* Update vocode version in apps/voice_rag vocodedev#482

Author: arpagon

apps/client_backend/poetry.lock

@@ -8,7 +8,7 @@ readme = "README.md"
 [tool.poetry.dependencies]
 python = ">=3.9,<3.12"
 python-dotenv = "^1.0.0"
-vocode = "0.1.111a3"
+vocode = "0.1.111"
 elevenlabs = "^0.2.23"
 
 

apps/client_backend/pyproject.toml

@@ -1,3 +1,3 @@
 # langchain_agent
 
-See https://docs.vocode.dev/langchain-agent for setup steps!
+See https://docs.vocode.dev/open-source/langchain-agent for setup steps!

apps/langchain_agent/README.md

@@ -11,7 +11,7 @@ redis = "^4.5.4"
 twilio = "^8.1.0"
 vonage = "^3.5.1"
 python-dotenv = "^1.0.0"
-vocode = "0.1.111a3"
+vocode = "0.1.111"
 google-cloud-texttospeech = "^2.14.1"
 
 

apps/langchain_agent/poetry.lock

@@ -1,4 +1,4 @@
-FROM python:3.11
+FROM python:3.9-bullseye
 
 # get portaudio and ffmpeg
 RUN apt-get update \

apps/langchain_agent/pyproject.toml

@@ -28,6 +28,10 @@
     BaseSynthesizer,
 )
 
+from dotenv import load_dotenv
+
+load_dotenv()
+
 logging.basicConfig(
     format="%(asctime)s - %(name)s - %(levelname)s - %(message)s", level=logging.INFO
 )
@@ -46,7 +50,7 @@
 # Required environment variables containing API key: OPENAI_API_KEY, TELEGRAM_BOT_KEY, and your Vocode synthesizers classes corresponding API key variable
 
 # Your chosen synthesizer provider's corresponding Vocode turn_based class instance
-SYNTH = CoquiSynthesizer(use_xtts=True)
+SYNTH = AzureSynthesizer(voice_name="en-US-SteffanNeural")
 
 # Instructions to the language model responsible for generating response transcript.
 SYSTEM_PROMPT = "You are having a voice-to-voice conversation with a user. Always pretend you are a real human. Do not avoid or decline to answer questions because you are not human."
@@ -153,7 +157,8 @@ async def get_response(
             setattr(self.synthesizer, voice_attr_of[type(self.synthesizer)], voice_id)
 
         # Synthesize response
-        synth_response = await self.synthesizer.async_synthesize(agent_response)
+        # TODO make async
+        synth_response = self.synthesizer.synthesize(agent_response)
 
         # Save conversation to DB
         self.db[chat_id].current_conversation = pickle.dumps(agent.memory)

apps/telegram_bot/Dockerfile

@@ -6,11 +6,11 @@ authors = ["Your Name <[email protected]>"]
 readme = "README.md"
 
 [tool.poetry.dependencies]
-python = ">=3.11,<3.12"
+python = ">=3.9,<3.12"
 python-telegram-bot = "^20.3"
 mypy = "^1.3.0"
 black = "^23.3.0"
-vocode = {git = "https://github.com/vocodedev/vocode-python.git", rev = "zaptrem/turn-based-improvements", extras=["all"]}
+vocode = "0.1.111"
 
 
 [build-system]

apps/telegram_bot/main.py

@@ -1,7 +1,22 @@
+# The base URL for the application. This is used in the main.py file.
+# If BASE_URL is not set, you need to set the NGROK_AUTH_TOKEN for creating a tunnel to the dev server.
+# example: 
+# BASE_URL=telephony-app.ngrok.io
 BASE_URL=
+# The authentication token for ngrok. This is used in the main.py file for creating a tunnel to the dev server.
+# This needs to be set if BASE_URL is not set.
+# NGROK_AUTH_TOKEN=
+
+# The API key for Deepgram. This is used for speech recognition.
 DEEPGRAM_API_KEY=
+
+# The API key for OpenAI. This is used for natural language processing tasks.
 OPENAI_API_KEY=
+
+# The API key and region for Azure Speech Service, used for speech-to-text services.
 AZURE_SPEECH_KEY=
 AZURE_SPEECH_REGION=
+
+# The account SID and authentication token for Twilio. These are used for making API requests to Twilio.
 TWILIO_ACCOUNT_SID=
 TWILIO_AUTH_TOKEN=