code updates for 0.1.112 (vocodedev#555)

* Update Readme with Preview Info (#1)

* Update Readme with Preview Info

* We're not quite that far along

* Update Structure to be more Pleasing to the Eyes

* Add changelog to readme

---------

Co-authored-by: srhinos <[email protected]>
Co-authored-by: Adnaan Sachidanandan <[email protected]>

* The Big Diff (#2)

* The Big Diff

* remove tests on 3.8 and 3.9

* Update README.md

* Update README.md

* fix turn based quickstart (#3)

* [hotfix] remove unused import (#4)

* Update README.md

* Update README.md

* Remove create_speech() from rime synthesizer (#6)

* Fix default factory for elevenlabs WS (#12)

* dispatch into elvenlabsws if experimental_websocket is on

* fix mypy

* Merge In Recent Fixes (#14)

* [docs sprint] Updates docs for using transcribers (#9)

* [docs sprint] phrase trigger documentation (#16)

* [docs sprint] update open source quickstarts (#15)

* [docs sprint] Add Documentation on Using Vocode's Loguru Implementation (#19)

* [docs sprint] Add Documentation on Using Vocode's Loguru Implementation

* Remove Tracing

---------

Co-authored-by: srhinos <[email protected]>

* [docs sprint] Updates docs for using synthesizers (#8)

* [docs sprint] using synthesizers docs update

* update docs for elevenlabs ws

* Apply suggestions from code review

Co-authored-by: Adnaan Sachidanandan <[email protected]>

---------

Co-authored-by: Adnaan Sachidanandan <[email protected]>

* [docs sprint] Updates docs for react quickstart (#10)

* [docs sprint] Updates docs for react quickstart

* PR feedback

* changes azure to override create_speech_uncached (#21)

* [docs sprint] Adds docs for conversation mechanics and moves endpointing docs from transcribers (#11)

* [docs sprint] Updates docs for using transcribers

* Adds docs for conversation mechanics and moves endpointing docs from transcribers

* Update docs/open-source/conversation-mechanics.md

Co-authored-by: Adnaan Sachidanandan <[email protected]>

* use mdx

* PR feedback

---------

Co-authored-by: Adnaan Sachidanandan <[email protected]>

* updates docs for events manager (#7)

* add cartesia synthesizer (#17)

* add cartesia synthesizer

* make Cartesia dependency optional, add it to the synthesizers extra group

* lazy import cartesia

* improved lazy loading, and added api_key as a config parameter

* improvements to cartesia synth
* use create_speech_uncached
* use existing abstractions default encoding and sample rates

* Remove redundant api_key assignment

Co-authored-by: Ajay Raj <[email protected]>

* Remove default setting of sampling rate

Co-authored-by: Ajay Raj <[email protected]>

* Remove default setting of audio_encoding

Co-authored-by: Ajay Raj <[email protected]>

* remove default setting of sampling rate

Co-authored-by: Ajay Raj <[email protected]>

* Remove redundant setting of audio enconding

the output device handles this

Co-authored-by: Ajay Raj <[email protected]>

* build failed with poetry.lock file. re-updating it

---------

Co-authored-by: Ajay Raj <[email protected]>

* Unset docs / README changes

* Unset docs changes (cont.)

* unset poetry version change

* update poetry.lock

---------

Co-authored-by: Mac Wilkinson <[email protected]>
Co-authored-by: srhinos <[email protected]>
Co-authored-by: Adnaan Sachidanandan <[email protected]>
Co-authored-by: rjheeta <[email protected]>

Author: 5 people

.github/workflows/test.yml

@@ -12,8 +12,6 @@ jobs:
       fail-fast: false
       matrix:
         python-version:
-          - "3.8"
-          - "3.9"
           - "3.10"
           - "3.11"
         poetry-version:

Makefile

@@ -9,6 +9,12 @@ transcribe:
 synthesize:
 	poetry run python playground/streaming/synthesizer/synthesize.py
 
+turn_based_conversation:
+	poetry run python quickstarts/turn_based_conversation.py
+
+streaming_conversation:
+	poetry run python quickstarts/streaming_conversation.py
+
 PYTHON_FILES=.
 lint: PYTHON_FILES=vocode/ quickstarts/ playground/
 lint_diff typecheck_diff: PYTHON_FILES=$(shell git diff --name-only --diff-filter=d main | grep -E '\.py$$')

apps/client_backend/Dockerfile

@@ -15,4 +15,4 @@ RUN poetry config virtualenvs.create false
 RUN poetry install --no-dev --no-interaction --no-ansi
 COPY main.py /code/main.py
 
-CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "3000"]
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "3000"]

apps/client_backend/main.py

@@ -1,23 +1,19 @@
-import logging
+from dotenv import load_dotenv
 from fastapi import FastAPI
 
-from vocode.streaming.models.agent import ChatGPTAgentConfig
-from vocode.streaming.models.synthesizer import AzureSynthesizerConfig
-from vocode.streaming.synthesizer.azure_synthesizer import AzureSynthesizer
-
+from vocode.logging import configure_pretty_logging
 from vocode.streaming.agent.chat_gpt_agent import ChatGPTAgent
 from vocode.streaming.client_backend.conversation import ConversationRouter
+from vocode.streaming.models.agent import ChatGPTAgentConfig
 from vocode.streaming.models.message import BaseMessage
-
-from dotenv import load_dotenv
+from vocode.streaming.models.synthesizer import AzureSynthesizerConfig
+from vocode.streaming.synthesizer.azure_synthesizer import AzureSynthesizer
 
 load_dotenv()
 
 app = FastAPI(docs_url=None)
 
-logging.basicConfig()
-logger = logging.getLogger(__name__)
-logger.setLevel(logging.DEBUG)
+configure_pretty_logging()
 
 conversation_router = ConversationRouter(
     agent_thunk=lambda: ChatGPTAgent(
@@ -31,7 +27,6 @@
             output_audio_config, voice_name="en-US-SteffanNeural"
         )
     ),
-    logger=logger,
 )
 
 app.include_router(conversation_router.get_router())

apps/client_backend/poetry.lock

@@ -7,9 +7,11 @@ readme = "README.md"
 
 [tool.poetry.dependencies]
 python = ">=3.9,<3.12"
-python-dotenv = "^1.0.0"
-vocode = "0.1.111"
-elevenlabs = "^0.2.23"
+python-dotenv = "^1.0.1"
+vocode = { path = "../..", extras = [
+    "all",
+], develop = true, python = ">=3.11,<3.12" }
+elevenlabs = "^1.2.2"
 
 
 [build-system]

apps/client_backend/pyproject.toml

@@ -16,4 +16,4 @@ RUN poetry install --no-dev --no-interaction --no-ansi
 COPY main.py /code/main.py
 COPY speller_agent.py /code/speller_agent.py
 
-CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "3000"]
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "3000"]

apps/telephony_app/Dockerfile

@@ -3,14 +3,14 @@ services:
     image: redis:7.0.9-alpine
     command: redis-server --bind 0.0.0.0
     ports:
-      - 6379:6379
+    - 6379:6379
   app:
     image: vocode-telephony-app
     env_file:
-      - .env
+    - .env
     ports:
-      - 3000:3000
+    - 3000:3000
     depends_on:
-      - redis
+    - redis
     environment:
-      - REDISHOST=redis
+    - REDISHOST=redis

apps/telephony_app/docker-compose.yml

@@ -1,42 +1,33 @@
 # Standard library imports
-import logging
 import os
 import sys
 
+from dotenv import load_dotenv
+
 # Third-party imports
 from fastapi import FastAPI
-from vocode.streaming.models.telephony import TwilioConfig
+from loguru import logger
 from pyngrok import ngrok
-from vocode.streaming.telephony.config_manager.redis_config_manager import (
-    RedisConfigManager,
-)
-from vocode.streaming.models.agent import ChatGPTAgentConfig
-from vocode.streaming.models.message import BaseMessage
-from vocode.streaming.telephony.server.base import (
-    TwilioInboundCallConfig,
-    TelephonyServer,
-)
-from dotenv import load_dotenv
 
 # Local application/library specific imports
-from speller_agent import (
-    SpellerAgentFactory,
-    SpellerAgentConfig,
-)
+from speller_agent import SpellerAgentFactory
+
+from vocode.logging import configure_pretty_logging
+from vocode.streaming.models.agent import ChatGPTAgentConfig
+from vocode.streaming.models.message import BaseMessage
+from vocode.streaming.models.telephony import TwilioConfig
+from vocode.streaming.telephony.config_manager.redis_config_manager import RedisConfigManager
+from vocode.streaming.telephony.server.base import TelephonyServer, TwilioInboundCallConfig
 
 # if running from python, this will load the local .env
 # docker-compose will load the .env file by itself
 load_dotenv()
 
-app = FastAPI(docs_url=None)
+configure_pretty_logging()
 
-logging.basicConfig()
-logger = logging.getLogger(__name__)
-logger.setLevel(logging.DEBUG)
+app = FastAPI(docs_url=None)
 
-config_manager = RedisConfigManager(
-    logger=logger,
-)
+config_manager = RedisConfigManager()
 
 BASE_URL = os.getenv("BASE_URL")
 
@@ -66,7 +57,9 @@
             ),
             # uncomment this to use the speller agent instead
             # agent_config=SpellerAgentConfig(
-            #     initial_message=BaseMessage(text="im a speller agent, say something to me and ill spell it out for you"),
+            #     initial_message=BaseMessage(
+            #         text="im a speller agent, say something to me and ill spell it out for you"
+            #     ),
             #     generate_responses=False,
             # ),
             twilio_config=TwilioConfig(
@@ -76,7 +69,6 @@
         )
     ],
     agent_factory=SpellerAgentFactory(),
-    logger=logger,
 )
 
 app.include_router(telephony_server.get_router())

apps/telephony_app/main.py

@@ -1,15 +1,18 @@
 import os
+
 from dotenv import load_dotenv
 
-load_dotenv()
+from vocode.streaming.models.agent import ChatGPTAgentConfig
+from vocode.streaming.models.message import BaseMessage
+from vocode.streaming.models.telephony import TwilioConfig
 
-from vocode.streaming.telephony.conversation.outbound_call import OutboundCall
-from vocode.streaming.telephony.config_manager.redis_config_manager import (
-    RedisConfigManager,
-)
+load_dotenv()
 
 from speller_agent import SpellerAgentConfig
 
+from vocode.streaming.telephony.config_manager.redis_config_manager import RedisConfigManager
+from vocode.streaming.telephony.conversation.outbound_call import OutboundCall
+
 BASE_URL = os.environ["BASE_URL"]
 
 
@@ -21,12 +24,22 @@ async def main():
         to_phone="+15555555555",
         from_phone="+15555555555",
         config_manager=config_manager,
-        agent_config=SpellerAgentConfig(generate_responses=False),
+        agent_config=ChatGPTAgentConfig(
+            initial_message=BaseMessage(text="What up"),
+            prompt_preamble="Have a pleasant conversation about life",
+            generate_responses=True,
+        ),
+        telephony_config=TwilioConfig(
+            account_sid=os.environ["TWILIO_ACCOUNT_SID"],
+            auth_token=os.environ["TWILIO_AUTH_TOKEN"],
+        ),
     )
 
     input("Press enter to start call...")
     await outbound_call.start()
 
+
 if __name__ == "__main__":
     import asyncio
+
     asyncio.run(main())