diff --git a/docs/bodies/01-light.mdx b/docs/bodies/01-light.mdx index ed27f1c..4bf8f3a 100644 --- a/docs/bodies/01-light.mdx +++ b/docs/bodies/01-light.mdx @@ -3,6 +3,10 @@ title: "01 Light" description: "Build your 01 Light" --- -01 Light (one pager that points to the STL, wiring diagrams, and points to the ESP32 client setup page^) +## ESP32 client + +Instructions to set up your ESP32 client can be found here + +## Suppliementary files For CAD files, wiring diagram, and images, please visit the [01 Light hardware repository](https://github.com/OpenInterpreter/01/tree/main/hardware/light). diff --git a/docs/getting-started/setup.mdx b/docs/getting-started/setup.mdx index cbc529b..0f18339 100644 --- a/docs/getting-started/setup.mdx +++ b/docs/getting-started/setup.mdx @@ -3,4 +3,69 @@ title: "Setup" description: "Get your 01 up and running" --- -Setup (breaks down the basic steps of the following and links to the pages for more info) +## Captive portal + +To connect your 01, you will use the captive portal. + +1. Turn on your computer or laptop and connect to the '01 light' Wi-Fi network. +2. Enter your Wi-Fi/hotspot name and password in the captive portal page. +3. Enter the server URL generated on their computer and hit 'Connect'. + +Now you're connected and ready to go! + +# Local 01OS + +## Prerequisites + +There are a few packages that need to be installed in order to run 01OS on your computer + +```bash +# MacOS +brew install portaudio ffmpeg cmake + +# Ubuntu +sudo apt-get install portaudio19-dev ffmpeg cmake +``` + +## Install 01 + +To install the 01 CLI + +```bash +# Clone the repo and navigate into the 01OS directory +git clone https://github.com/OpenInterpreter/01.git +``` + +## Run the 01 + +In order to run 01 on your computer, use [Poetry](https://python-poetry.org/docs/#installing-with-the-official-installer) + +Navigate to the project's 01OS directory: + +```bash +cd 01OS +``` + +Install your project along with its dependencies in a virtual environment managed by Poetry. + +```bash +poetry install +``` + +Run your local version of 01 with: + +```bash +poetry run 01 +``` + +## Swap out service providers + +You have the ability to set your LLM, STT, and TTS service providers + +## Server setup + +You are able to run just the server + +## Client setup + +You are able to run just the client diff --git a/docs/server/setup.mdx b/docs/server/setup.mdx index bb03b64..deff6ac 100644 --- a/docs/server/setup.mdx +++ b/docs/server/setup.mdx @@ -3,18 +3,46 @@ title: "Setup" description: "Get your 01 server up and running" --- -- Interpreter - - Open Interpreter (explains i.py, how you configure your interpreter, cover the basic settings of OI (that file is literally just modifying an interpreter from OI) - - Language Model (LLM setup via interpreter.model in i.py or from the command line via start.py --server --llm-service llamafile) -- Voice Interface (explains that you can run --tts-service and --stt-service to swap out for different services, which are in /Services/Speech-to-text and /Services/Text-to-text) - ## Run Server ```bash poetry run 01 --server ``` -## Flags +## Configure + +A core part of the 01 server is the interpreter which is an instance of Open Interpreter. +Open Interpreter is highly configurable and only requires updating a single file. + +```bash +# Edit i.py +01OS/01OS/server/i.py +``` + +Properties such as `model`, `context_window`, and many more can be updated here. + +### LLM service provider + +If you wish to use a local model, you can use the `--llm-service` flag: + +```bash +# use llamafile +poetry run 01 --server --llm-service llamafile +``` + +For more information about LLM service providers, check out the page on Language Models. + +### Voice Interface + +Both speech-to-text and text-to-speech can be configured in 01OS. + +You are able to pass CLI flags `--tts-service` and/or `--stt-service` with the desired service provider to swap out different services + +These different service providers can be found in `/services/stt` and `/services/tts` + +For more information, please read about speech-to-text and text-to-speech + +## CLI Flags - `--server` Run server. diff --git a/docs/services/language-model.mdx b/docs/services/language-model.mdx index 7d2f1d8..eb0aa8d 100644 --- a/docs/services/language-model.mdx +++ b/docs/services/language-model.mdx @@ -3,13 +3,24 @@ title: "Language Model" description: "The LLM that powers your 01" --- -## Llamafile +## llamafile -Llamafile is cool! +llamafile lets you distribute and run LLMs with a single file. Read more about llamafile [here](https://github.com/Mozilla-Ocho/llamafile) + +```bash +# Set the LLM service to llamafile +poetry run 01 --llm-service llamafile +``` ## Llamaedge -Llamaedge is also cool! +llamaedge makes it easy for you to run LLM inference apps and create OpenAI-compatible API services for the Llama2 series of LLMs locally. +Read more about Llamaedge [here](https://github.com/LlamaEdge/LlamaEdge) + +```bash +# Set the LLM service to Llamaedge +poetry run 01 --llm-service llamaedge +``` ## Hosted Models diff --git a/docs/services/speech-to-text.mdx b/docs/services/speech-to-text.mdx index a7ece79..d4dc044 100644 --- a/docs/services/speech-to-text.mdx +++ b/docs/services/speech-to-text.mdx @@ -3,20 +3,21 @@ title: "Speech To Text" description: "Converts your voice into text" --- -To select your Speech-To-Text provider: +## Whisper (Local) + +This option installs whisper-rust to allow all speech to text to be done locally on device. ```bash -# Set STT service -01 --stt-service openai +# Set a local STT service +01 --stt-service local-whisper ``` -## Whisper (Local) - -Local, nice! - ## Whisper (Hosted) -Still cool! +```bash +# Set STT service +01 --stt-service openai +``` ## Other Models diff --git a/docs/services/text-to-speech.mdx b/docs/services/text-to-speech.mdx index 3babbe2..4a6688e 100644 --- a/docs/services/text-to-speech.mdx +++ b/docs/services/text-to-speech.mdx @@ -1,22 +1,23 @@ --- title: "Text To Speech" -description: "Converts the text into audio" +description: "The service to speak the text" --- -To select your Text-To-Speech provider: +## Piper (Local) + +This option installs piper to allow all text to speech to be done locally on device. ```bash -# Set TTS service -01 --tts-service openai +# Set a local TTS service +01 --tts-service piper ``` -## Piper (Local) - -Local, nice! - ## OpenAI (Hosted) -Still cool! +```bash +# Set TTS service +01 --tts-service openai +``` ## Other Models