From f66b720bac696c8901ffe1dc3bf8ead74a24490f Mon Sep 17 00:00:00 2001
From: Cleo Schneider <cleoschneider@google.com>
Date: Wed, 8 May 2024 16:29:03 +0000
Subject: [PATCH 1/2] Rename toc titles to be more consistent with behaviors

---
 docs/_guides.yaml |  8 ++++----
 docs/models.md    | 16 ++++++++++------
 2 files changed, 14 insertions(+), 10 deletions(-)

diff --git a/docs/_guides.yaml b/docs/_guides.yaml
index c6ca663c9..6708e4b30 100644
--- a/docs/_guides.yaml
+++ b/docs/_guides.yaml
@@ -23,14 +23,14 @@ toc:
     path: /docs/genkit/devtools
   
   - heading: Building AI workflows
-  - title: Models
+  - title: Generating content
     path: /docs/genkit/models
+  - title: Creating flows
+    path: /docs/genkit/flows
   - title: Prompting models
     path: /docs/genkit/prompts
-  - title: Prompt management
+  - title: Managing prompts
     path: /docs/genkit/dotprompt
-  - title: Flows
-    path: /docs/genkit/flows
   - title: Retrieval-augmented generation (RAG)
     path: /docs/genkit/rag
   - title: Evaluation
diff --git a/docs/models.md b/docs/models.md
index e8cb3b108..fcc479c2b 100644
--- a/docs/models.md
+++ b/docs/models.md
@@ -1,4 +1,8 @@
-# Models
+# Generating Content
+
+Firebase Genkit provides an easy interface for generating content with LLMs.
+
+## Models
 
 Models in Firebase Genkit are libraries and abstractions that provide access to
 various Google and non-Google LLMs.
@@ -22,7 +26,7 @@ configureGenkit({
 });
 ```
 
-Also note that different plugins and models use different methods of
+NOTE: Different plugins and models use different methods of
 authentication. For example, Vertex API uses the Google Auth Library so it can
 pull required credentials using Application Default Credentials.
 
@@ -51,7 +55,7 @@ are officially supported:
 
 See the docs for each plugin for setup and usage information.
 
-## Working with models
+## How to generate content
 
 `generate` is a helper function for working with models.
 
@@ -169,7 +173,7 @@ await generate({
 });
 ```
 
-## Retriever context
+### Adding retriever context
 
 Documents from a retriever can be passed directly to `generate` to provide
 grounding context:
@@ -187,7 +191,7 @@ await generate({
 The document context is automatically appended to the content of the prompt
 sent to the model.
 
-## Message history
+### Recording message history
 
 Genkit models support maintaining a history of the messages sent to the model
 and its responses, which you can use to build interactive experiences, such as
@@ -231,7 +235,7 @@ let response = await generate({
 history = response.toHistory();
 ```
 
-## Streaming
+### Streaming responses
 
 Genkit supports chunked streaming of model responses via the `generateStream()` method:
 

From 877e7b7bd34c3239e100bdebeaaaf6b085206a34 Mon Sep 17 00:00:00 2001
From: Cleo Schneider <cleoschneider@google.com>
Date: Wed, 8 May 2024 13:07:14 -0400
Subject: [PATCH 2/2] Apply suggestions from code review

Co-authored-by: Kevin Cheung <kevinthecheung@users.noreply.github.com>
---
 docs/models.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/docs/models.md b/docs/models.md
index fcc479c2b..5b9af68bf 100644
--- a/docs/models.md
+++ b/docs/models.md
@@ -1,4 +1,4 @@
-# Generating Content
+# Generating content
 
 Firebase Genkit provides an easy interface for generating content with LLMs.
 
@@ -26,7 +26,7 @@ configureGenkit({
 });
 ```
 
-NOTE: Different plugins and models use different methods of
+Note: Different plugins and models use different methods of
 authentication. For example, Vertex API uses the Google Auth Library so it can
 pull required credentials using Application Default Credentials.