From d06c5580532e9ce7fceec6d0e666735e8a58a369 Mon Sep 17 00:00:00 2001
From: Hause Lin <hauselin@gmail.com>
Date: Mon, 26 Aug 2024 12:33:02 -0400
Subject: [PATCH] Update site

---
 README.Rmd   |  6 ++++--
 README.md    | 14 +++++++++++---
 _pkgdown.yml | 10 +++++-----
 3 files changed, 20 insertions(+), 10 deletions(-)

diff --git a/README.Rmd b/README.Rmd
index 2f944ed..393b986 100644
--- a/README.Rmd
+++ b/README.Rmd
@@ -23,6 +23,8 @@ knitr::opts_chunk$set(
 
 The [Ollama R library](https://hauselin.github.io/ollama-r/) is the easiest way to integrate R with [Ollama](https://ollama.com/), which lets you run language models locally on your own machine. Main site: https://hauselin.github.io/ollama-r/
 
+The library also makes it easy to work with data structures (e.g., conversational/chat histories) that are standard for different LLMs (such as those provided by OpenAI and Anthropic). It also lets you specify different output formats (e.g., dataframes, text/vector, lists) that best suit your need, allowing easy integration with other libraries/tools and parallelization via the `httr2` library.
+
 To use this R library, ensure the [Ollama](https://ollama.com) app is installed. Ollama can use GPUs for accelerating LLM inference. See [Ollama GPU documentation](https://github.com/ollama/ollama/blob/main/docs/gpu.md) for more information.
 
 See [Ollama's Github page](https://github.com/ollama/ollama) for more information. This library uses the [Ollama REST API (see documentation for details)](https://github.com/ollama/ollama/blob/main/docs/api.md).
@@ -254,7 +256,7 @@ resp_process(resp, "text")  # text vector
 # or list_models("text")
 ```
 
-#### Utility/helper functions to format and prepare messages for the `chat()` function
+#### Format and prepare messages for the `chat()` function
 
 Internally, messages are represented as a `list` of many distinct `list` messages. Each list/message object has two elements: `role` (can be `"user"` or `"assistant"` or `"system"`) and `content` (the message text). The example below shows how the messages/lists are presented.
 
@@ -265,7 +267,7 @@ list(  # main list containing all the messages
 )
 ```
 
-To simplify the process of creating and managing messages, `ollamar` provides utility/helper functions to format and prepare messages for the `chat()` function.
+To simplify the process of creating and managing messages, `ollamar` provides functions to format and prepare messages for the `chat()` function. These functions also work with other APIs or LLM providers like OpenAI and Anthropic.
 
 - `create_messages()`: create messages to build a chat history
 - `create_message()` creates a chat history with a single message
diff --git a/README.md b/README.md
index 0b6530d..038add7 100644
--- a/README.md
+++ b/README.md
@@ -16,6 +16,13 @@ easiest way to integrate R with [Ollama](https://ollama.com/), which
 lets you run language models locally on your own machine. Main site:
 <https://hauselin.github.io/ollama-r/>
 
+The library also makes it easy to work with data structures (e.g.,
+conversational/chat histories) that are standard for different LLMs
+(such as those provided by OpenAI and Anthropic). It also lets you
+specify different output formats (e.g., dataframes, text/vector, lists)
+that best suit your need, allowing easy integration with other
+libraries/tools and parallelization via the `httr2` library.
+
 To use this R library, ensure the [Ollama](https://ollama.com) app is
 installed. Ollama can use GPUs for accelerating LLM inference. See
 [Ollama GPU
@@ -293,7 +300,7 @@ resp_process(resp, "text")  # text vector
 # or list_models("text")
 ```
 
-#### Utility/helper functions to format and prepare messages for the `chat()` function
+#### Format and prepare messages for the `chat()` function
 
 Internally, messages are represented as a `list` of many distinct `list`
 messages. Each list/message object has two elements: `role` (can be
@@ -308,8 +315,9 @@ list(  # main list containing all the messages
 ```
 
 To simplify the process of creating and managing messages, `ollamar`
-provides utility/helper functions to format and prepare messages for the
-`chat()` function.
+provides functions to format and prepare messages for the `chat()`
+function. These functions also work with other APIs or LLM providers
+like OpenAI and Anthropic.
 
 - `create_messages()`: create messages to build a chat history
 - `create_message()` creates a chat history with a single message
diff --git a/_pkgdown.yml b/_pkgdown.yml
index f722064..94818c6 100644
--- a/_pkgdown.yml
+++ b/_pkgdown.yml
@@ -18,7 +18,7 @@ reference:
   - title: Ollamar functions
 
   - subtitle: API endpoints
-    desc: Functions to make calls to the Ollama server/API.
+    desc: Make calls to the Ollama server/API.
     contents:
       - generate
       - chat
@@ -33,8 +33,8 @@ reference:
       - embeddings
       - ps
 
-  - subtitle: Utility functions
-    desc: Functions to work with the Ollama API.
+  - subtitle: API helpers
+    desc: ork with the Ollama API.
     contents:
       - resp_process
       - ohelp
@@ -43,8 +43,8 @@ reference:
       - test_connection
       - create_request
 
-  - subtitle: Manipulate chat/conversation history
-    desc: Functions to manipulate messages and chat history for `chat()` function.
+  - subtitle: Manipulate chat history
+    desc: Manipulate chat history for Ollama and other LLM providers.
     contents:
       - create_messages
       - create_message