updated running locally

Author: MikeBirdTech

docs/guides/profiles.mdx

@@ -4,11 +4,11 @@ title: Profiles
 
 Profiles are a powerful way to customize your instance of Open Interpreter.
 
-Everything from the model to the context window to the message templates can be configured in a profile. This allows you to save multiple variations of Open Interpreter to optimize your specific use-cases.
+Profiles are Python files that configure Open Interpreter. A wide range of fields from the [model](/settings/all-settings#model-selection) to the [context window](/settings/all-settings#context-window) to the [message templates](/settings/all-settings#user-message-template) can be configured in a Profile. This allows you to save multiple variations of Open Interpreter to optimize for your specific use-cases.
 
-You can access Profiles with `interpreter --profiles`. This will open up the directory where all of your profiles are stored.
+You can access your Profiles by running `interpreter --profiles`. This will open the directory where all of your Profiles are stored.
 
-To apply a Profile to a session of Open Interpreter, you can run `interpreter --profile <name>`
+To apply a Profile to an Open Interpreter session, you can run `interpreter --profile <name>`
 
 # Example Profile
 
@@ -17,7 +17,6 @@ from interpreter import interpreter
 
 interpreter.os = True
 interpreter.llm.supports_vision = True
-# interpreter.shrink_images = True # Faster but less accurate
 
 interpreter.llm.model = "gpt-4-vision-preview"
 

docs/guides/running-locally.mdx

@@ -2,40 +2,27 @@
 title: Running Locally
 ---
 
-In this video, Mike Bird goes over three different methods for running Open Interpreter with a local language model:
+Open Interpreter can be run fully locally.
 
-<iframe width="560" height="315" src="https://www.youtube.com/embed/CEs51hGWuGU?si=cN7f6QhfT4edfG5H" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" allowfullscreen></iframe>
+Users need to install software to run local LLMs. Open Interpreter supports multiple local model providers such as [Ollama](https://www.ollama.com/), [Llamafile](https://github.com/Mozilla-Ocho/llamafile), [LM Studio](https://lmstudio.ai/), and [Jan](https://jan.ai/).
 
-## How to Use Open Interpreter Locally
+## Local Setup Menu
 
-### Ollama
+A Local Setup Menu was created to simplify the process of using OI locally. To access this menu, run the command `interpreter --local`.
 
-1. Download Ollama from https://ollama.ai/download
-2. Run the command:  
-`ollama run dolphin-mixtral:8x7b-v2.6`
-3. Execute the Open Interpreter:  
-`interpreter --model ollama/dolphin-mixtral:8x7b-v2.6`
+### Provider
 
-### Jan.ai
+Select your chosen local model provider from the list of options.
 
-1. Download Jan from http://jan.ai
-2. Download the model from the Hub
-3. Enable API server:
-   1. Go to Settings
-   2. Navigate to Advanced
-   3. Enable API server
-4. Select the model to use
-5. Run the Open Interpreter with the specified API base:  
-`interpreter --api_base http://localhost:1337/v1 --model mixtral-8x7b-instruct`
+It is possible to use a provider other than the ones listed. Instead of running `--local` you will set the `--api_base` flag to set a [custom endpoint](/language-models/local-models/custom-endpoint).
 
-### Llamafile
+### Model
 
-⚠ Ensure that Xcode is installed for Apple Silicon
+Most providers will require the user to state the model they are using. There are Provider specific instructions shown to the user.
 
-1. Download or create a llamafile from https://github.com/Mozilla-Ocho/llamafile
-2. Make the llamafile executable:  
-`chmod +x mixtral-8x7b-instruct-v0.1.Q5_K_M.llamafile`
-3. Execute the llamafile:  
-`./mixtral-8x7b-instruct-v0.1.Q5_K_M.llamafile`
-4. Run the interpreter with the specified API base:  
-`interpreter --api_base https://localhost:8080/v1`
+It is possible to set the model without going through the Local Setup Menu by setting the `--model` flag to select a [model](/settings/all-settings#model-selection).
+
+<Tip>
+  Local models perform better with extra guidance and direction. You can improve
+  performance for your use-case by creating a new [Profile](/guides/profiles).
+</Tip>