Enable RAG by default (#240)

* Update the RAG learning docs to reflect the changes
  * RAG is enabled by default
  * You don't need to enable AILogs in RunMe
* You don't need to configure the location of the RunMe logs Related to
#224

Render the navigation sidebar in compact mode.

app/pkg/config/config.go

@@ -38,6 +38,8 @@ const (
 	// https://github.com/stateful/vscode-runme/blob/f1cc965ab0c4cdffa9adb70922e2da792d7e23de/package.json#L849
 	// The value isn't 8080 because 8080 is over used and likely to conflict with other locally running services.
 	defaultHTTPPort = 8877
+
+	defaultRagEnabled = true
 )
 
 // Config represents the persistent configuration data for Foyle.
@@ -463,6 +465,8 @@ func setServerDefaults() {
 
 func setAgentDefaults() {
 	viper.SetDefault("agent.model", DefaultModel)
+	viper.SetDefault("agent.rag.enabled", defaultRagEnabled)
+	viper.SetDefault("agent.rag.maxResults", defaultMaxResults)
 }
 
 func DefaultConfigFile() string {

docs/content/en/docs/learning/_index.md

@@ -3,84 +3,3 @@ title: "Learning"
 description: "How to use Foyle to learn from human feedback"
 weight: 2
 ---
-
-## What You'll Learn
-
-How to configure Foyle to continually learn from human feedback
-
-## Configure Foyle to use RAG
-
-To configure Foyle to use RAG
-
-```
-foyle config set agent.rag.enabled=true
-foyle config set agent.rag.maxResults=3
-```
-
-## Enabling Logging In RunMe
-
-If you are using [RunMe.dev](https://runme.dev/) as the frontend for Foyle
-then you need to configure RunMe to enable the AI logging experiment
-
-1. Inside vscode open the settings panel
-2. Enable the option `Runme › Experiments: Ai Logs`
-
-Now that logging is enabled. You can verify that the logs are being written and identify the location
-of the logs.
-
-Inside VSCode open an output window and select the **RunMe** output channel. 
-Scroll to the top of the messages and look for a `Logger initialized` message like the one below
-
-```
-[2024-05-28T22:12:20.681Z] INFO Runme(RunmeServer): {"level":"info","ts":1716934340.6789708,"caller":"cmd/common.go:190","msg":"Logger initialized","devMode":false,"aiLogs":true,"aiLogFile":"/Users/jlewi/Library/Application Support/runme/logs/logs.2024-05-28T15:12:20.json"}
-```
-
-The field `aiLogs` will contain the file that the current instance of RunMe is using for the JSON logs.
-
-By default, on MacOs RunMe will use the directory
-
-```bash
-/Users/${USER}/Library/Application Support/runme/logs/
-```
-
-## Configuring Learning
-
-If you are using [RunMe.dev](https://runme.dev/) as the frontend for Foyle
-then you need to configure Foyle with the location of the **directory** of RunMe's logs.
-Refer to the previous section for instructions on how to locate the file
-where `RunMe` is writing the logs. Then remove the filename to get the directory
-where the logs are being written.
-
-Once you know the directory run the following command to configure Foyle to use that
-directory
-
-```bash
-foyle config set learner.logDirs=${RUNME_LOGS_DIR}
-```
-
-## Sharing Learned Examples
-
-In a team setting, you should build a shared AI that learns from the feedback of all team members and assists
-all members. To do this you can configure Foyle to write and read examples from a shared location like GCS.
-If you'd like S3 support please vote up [issue #153](https://github.com/jlewi/foyle/issues/153).
-
-To configure Foyle to use a shared location for learned examples 
-
-1. Create a GCS bucket to store the learned examples
-
-   ```bash
-    gsutil mb gs://my-foyle-examples
-   ```
-
-1. Configure Foyle to use the GCS bucket
-
-   ```bash
-   foyle config set learner.exampleDirs=gs://${YOUR_BUCKET}
-   ```
-
-Optionally you can configure Foyle to use a local location as well if you want to be able to use the AI without
-an internet connection.
-
-```bash
-foyle config set learner.exampleDirs=gs://${YOUR_BUCKET},/local/training/examples
-```

docs/content/en/docs/learning/configuring.md

@@ -0,0 +1,66 @@
+---
+title: "Configuring"
+description: "Configuring Learning In Foyle"
+weight: 1
+---
+
+## What You'll Learn
+
+How to configure Learning in Foyle to continually learn from human feedback
+
+## How It Works
+
+* As you use Foyle, the AI builds a dataset of examples (input, output)
+* The input is a notebook at some point in time , `t`
+* The output is one more or cells that were then added to the notebook at time `t+1`
+* Foyle uses these examples to get better at suggesting cells to insert into the notebook
+
+## Configuring RAG
+
+Foyle uses RAG to improve its predictions using its existing dataset of examples. You can control
+the number of RAG results used by Foyle by setting `agent.rag.maxResults`.
+
+```
+foyle config set agent.rag.maxResults=3
+```
+
+## Disabling RAG
+
+RAG is enabled by default. To disable it run
+
+```
+foyle config set agent.rag.enabled=false
+```
+
+To check the status of RAG get the current configuration
+
+```
+foyle config get
+```
+
+## Sharing Learned Examples
+
+In a team setting, you should build a shared AI that learns from the feedback of all team members and assists
+all members. To do this you can configure Foyle to write and read examples from a shared location like GCS.
+If you'd like S3 support please vote up [issue #153](https://github.com/jlewi/foyle/issues/153).
+
+To configure Foyle to use a shared location for learned examples
+
+1. Create a GCS bucket to store the learned examples
+
+   ```bash
+    gsutil mb gs://my-foyle-examples
+   ```
+
+1. Configure Foyle to use the GCS bucket
+
+   ```bash
+   foyle config set learner.exampleDirs=gs://${YOUR_BUCKET}
+   ```
+
+Optionally you can configure Foyle to use a local location as well if you want to be able to use the AI without
+an internet connection.
+
+```bash
+foyle config set learner.exampleDirs=gs://${YOUR_BUCKET},/local/training/examples
+```

docs/content/en/docs/learning/troubleshoot_learning.md

@@ -1,7 +1,7 @@
 ---
 title: "Troubleshoot Learning"
 description: "How to troubleshoot and monitor learning"
-weight: 1
+weight: 2
 ---
 
 ## What You'll Learn

docs/hugo.toml

@@ -146,7 +146,7 @@ navbar_logo = true
 # Set to true if you don't want the top navbar to be translucent when over a `block/cover`, like on the homepage.
 navbar_translucent_over_cover_disable = false
 # Enable to show the side bar menu in its compact state.
-sidebar_menu_compact = false
+sidebar_menu_compact = true
 # Set to true to hide the sidebar search box (the top nav search box will still be displayed if search is enabled)
 sidebar_search_disable = false