From 2f53be05db2791c11b69e93a44cafebee1d40148 Mon Sep 17 00:00:00 2001 From: Ben Xu Date: Mon, 9 Dec 2024 13:34:44 -0800 Subject: [PATCH] update livekit server and profile docs --- docs/server/configure.mdx | 76 +++++++++++++++++---------------------- docs/server/livekit.mdx | 18 ++++++---- 2 files changed, 45 insertions(+), 49 deletions(-) diff --git a/docs/server/configure.mdx b/docs/server/configure.mdx index e40efd6..6319374 100644 --- a/docs/server/configure.mdx +++ b/docs/server/configure.mdx @@ -23,9 +23,9 @@ poetry run 01 --profile ### Standard Profiles -`default.py` is the default profile that is used when no profile is specified. The default TTS is OpenAI. +`default.py` is the default profile that is used when no profile is specified. The default TTS service is Elevenlabs. -`fast.py` uses elevenlabs and groq, which are the fastest providers. +`fast.py` uses Cartesia for TTS and Cerebras Llama3.1-8b, which are the fastest providers. `local.py` uses coqui TTS and runs the --local explorer from Open Interpreter. @@ -46,38 +46,16 @@ poetry run 01 --profile ### Example Profile ````python -from interpreter import AsyncInterpreter -interpreter = AsyncInterpreter() +from interpreter import Interpreter +interpreter = Interpreter() # This is an Open Interpreter compatible profile. # Visit https://01.openinterpreter.com/profile for all options. -# 01 supports OpenAI, ElevenLabs, and Coqui (Local) TTS providers +# 01 supports OpenAI, ElevenLabs, Cartesia, and Coqui (Local) TTS providers # {OpenAI: "openai", ElevenLabs: "elevenlabs", Coqui: "coqui"} -interpreter.tts = "openai" - -# Connect your 01 to a language model -interpreter.llm.model = "gpt-4o" -interpreter.llm.context_window = 100000 -interpreter.llm.max_tokens = 4096 -# interpreter.llm.api_key = "" - -# Tell your 01 where to find and save skills -interpreter.computer.skills.path = "./skills" - -# Extra settings -interpreter.computer.import_computer_api = True -interpreter.computer.import_skills = True -interpreter.computer.run("python", "computer") # This will trigger those imports -interpreter.auto_run = True -interpreter.loop = True -interpreter.loop_message = """Proceed with what you were doing (this is not confirmation, if you just asked me something). You CAN run code on my machine. If you want to run code, start your message with "```"! If the entire task is done, say exactly 'The task is done.' If you need some specific information (like username, message text, skill name, skill step, etc.) say EXACTLY 'Please provide more information.' If it's impossible, say 'The task is impossible.' (If I haven't provided a task, say exactly 'Let me know what you'd like to do next.') Otherwise keep going. CRITICAL: REMEMBER TO FOLLOW ALL PREVIOUS INSTRUCTIONS. If I'm teaching you something, remember to run the related `computer.skills.new_skill` function.""" -interpreter.loop_breakers = [ - "The task is done.", - "The task is impossible.", - "Let me know what you'd like to do next.", - "Please provide more information.", -] +interpreter.tts = "elevenlabs" +interpreter.stt = "deepgram" # Set the identity and personality of your 01 interpreter.system_message = """ @@ -89,17 +67,37 @@ You can install new packages. Be concise. Your messages are being read aloud to the user. DO NOT MAKE PLANS. RUN CODE QUICKLY. Try to spread complex tasks over multiple code blocks. Don't try to complex tasks in one go. Manually summarize text.""" + +# Add additional instructions for the 01 +interpreter.instructions = "Be very concise in your responses." + + +# Connect your 01 to a language model +interpreter.model = "claude-3-5-sonnet-20240620" +interpreter.provider = "anthropic" +interpreter.max_tokens = 4096 +interpreter.temperature = 0 +interpreter.api_key = "" + +# Extra settings +interpreter.tools = ["interpreter", "editor"] # Enabled tool modules +interpreter.auto_run = True # Whether to auto-run tools without confirmation +interpreter.tool_calling = True # Whether to allow tool/function calling + +interpreter.allowed_paths = [] # List of allowed paths +interpreter.allowed_commands = [] # List of allowed commands ```` ### Hosted LLMs -The default LLM for 01 is GPT-4-Turbo. You can find this in the default profile in `software/source/server/profiles/default.py`. +The default LLM for 01 is Claude 3.5 Sonnet. You can find this in the default profile in `software/source/server/profiles/default.py`. -The fast profile uses Llama3-8b served by Groq. You can find this in the fast profile in `software/source/server/profiles/fast.py`. +The fast profile uses Llama3.1-8b served by Cerebras. You can find this in the fast profile in `software/source/server/profiles/fast.py`. ```python # Set your profile with a hosted LLM -interpreter.llm.model = "gpt-4o" +interpreter.model = "claude-3-5-sonnet-20240620" +interpreter.provider = "anthropic" ``` ### Local LLMs @@ -110,7 +108,7 @@ Using the local profile launches the Local Explorer where you can select your in ```python # Set your profile with a local LLM -interpreter.llm.model = "ollama/codestral" +interpreter.model = "ollama/codestral" # You can also use the Local Explorer to interactively select your model interpreter.local_setup() @@ -118,7 +116,7 @@ interpreter.local_setup() ### Hosted TTS -01 supports OpenAI and Elevenlabs for hosted TTS. +01 supports OpenAI, Elevenlabs, and Cartesia for hosted TTS. ```python # Set your profile with a hosted TTS service @@ -132,12 +130,4 @@ For local TTS, Coqui is used. ```python # Set your profile with a local TTS service interpreter.tts = "coqui" -``` - - - When using the Livekit server, the interpreter.tts setting in your profile - will be ignored. The Livekit server currently only works with Deepgram for - speech recognition and Eleven Labs for text-to-speech. We are working on - introducing all-local functionality for the Livekit server as soon as - possible. - +``` \ No newline at end of file diff --git a/docs/server/livekit.mdx b/docs/server/livekit.mdx index f39d55c..2c9d423 100644 --- a/docs/server/livekit.mdx +++ b/docs/server/livekit.mdx @@ -69,6 +69,18 @@ Replace the placeholders with your actual API keys. ### Starting the Server +**To use the mobile app, run the following command** + +```bash +poetry run 01 --server livekit --qr --expose +``` + +To customize the profile, append the --profile flag with the profile name: + +```bash +poetry run 01 --server livekit --qr --expose --profile fast +``` + To start the Livekit server, run the following command: ```bash @@ -87,12 +99,6 @@ To expose over the internet via ngrok poetry run 01 --server livekit --expose ``` -In order to use the mobile app over the web, use both flags - -```bash -poetry run 01 --server livekit --qr --expose -``` - Currently, our Livekit server only works with Deepgram and Eleven Labs. We are working to introduce all-local functionality as soon as possible. By setting