From 54fdaa0468d1079f70af667c1fc74112b2a19e6b Mon Sep 17 00:00:00 2001 From: Mike Bird Date: Wed, 20 Mar 2024 13:53:00 -0400 Subject: [PATCH] server setup --- docs/server/setup.mdx | 40 ++++++++++++++++++++++++++++++++++------ 1 file changed, 34 insertions(+), 6 deletions(-) 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.