restyle quicklinks

mkdocs/index.md

@@ -1,52 +1,29 @@
 # 👋 Hello, dear
 
+The Cheshire Cat is an open-source, hackable and production-ready framework that allows developing intelligent personal
+AI agents on top of [Large Language Models](framework/cat-components/llm.md) (LLM).
+
 ```
 "Every adventure requires a first step".
 (Alice's Adventures in Wonderland - Lewis Carroll)
 ```
 
 ## Quick links
 
-<div class="grid cards" markdown>
-
-- &#127939; __Onboarding__
-
-    ---
-
-    Take your first step with hands-on examples!
-
-    [Get started now](quickstart/introduction.md){ .md-button }
-
-- &#128268; __Plugins__
-
-    ---
-
-    Dive into advanced concepts to develop and publish your plugin!
-
-    [Plugin documentation](plugins/plugins.md){ .md-button }
-
-- &#129693; __Hooks__
+<div class="grid" markdown>
 
-    ---
-
-    Explore all the available hooks to customize the Cat!
+[&#127939; Get started now](quickstart/installation-configuration.md){ .md-button }
+ 
+[&#129693; Available Hooks](plugins/hooks.md#available-hooks){ .md-button }
 
-    [Available Hooks](plugins/hooks.md#available-hooks){ .md-button }
+[&#128268; Plugin documentation](plugins/plugins.md){ .md-button }
 
-- &#128640; __Deploy__
-
-    ---
-
-    Ready-to-use setup to deploy your assistant!
-
-    [Docker Compose examples](production/administrators/docker-compose.md){ .md-button }
+[&#128640; Docker Compose examples](production/administrators/docker-compose.md){ .md-button }
 
 </div>
 
 ## Cheshire Cat Features
 
-The Cheshire Cat is an open-source, hackable and production-ready framework that allows developing intelligent personal
-AI assistant agents on top of [Large Language Models](framework/cat-components/llm.md) (LLM).
 
 <div class="grid cards" markdown>
 
@@ -56,53 +33,55 @@ AI assistant agents on top of [Large Language Models](framework/cat-components/l
 
     Chat with the Cat and interact with its endpoints!
 
-    [:octicons-arrow-right-24: Python API](production/network/clients.md)
+    [Client libs](production/network/clients.md){ .md-button }
+    [Endpoints](production/network/http-endpoints.md){ .md-button }
 
 - &#128640; __Extendable via plugins in Python__
 
     ---
 
     Write your first plugin, your imagination is the limit!
 
-    [:octicons-arrow-right-24: Write your first plugin](quickstart/prepare-plugin.md)
+    [Write your first plugin](quickstart/prepare-plugin.md){ .md-button }
 
 - &#127757; __Language model agnostic__
 
     ---
 
     Easily choose from a plenty of models to use!
 
-    [:octicons-arrow-right-24: compatible-models](production/administrators/docker-compose.md#compatible-models)
+    [Compatible Models](production/administrators/docker-compose/#cat-ollama){ .md-button }
 
 - &#128220; __Can ingest documents__
 
     ---
 
     Ground the model based on your knowledge base!
 
-    [:octicons-arrow-right-24: Retrieval Augmented Generation](framework/llm-concepts/rag.md)
+    [Retrieval Augmented Generation](framework/llm-concepts/rag.md){ .md-button }
 
 - &#128024; __Local Long term memory__
 
     ---
 
     Make use of a persistent memory across restarts!
 
-    [:octicons-arrow-right-24: Cat's Long Term Memory](framework/cat-components/memory/long_term_memory.md)
+    [Cat's Long Term Memory](framework/cat-components/memory/long_term_memory.md){ .md-button }
 
 - &#128011; __100% dockerized__
 
     ---
 
     Setup the Cat in the blink of an eye with the pre-built docker image!
 
-    [:octicons-arrow-right-24: Installation](quickstart/installation-configuration.md)
+    [Installation](quickstart/installation-configuration.md){ .md-button }
 
 </div>
 
 ## Get in touch with us
 
-[:fontawesome-brands-discord: Discord](https://discord.gg/bHX5sNFCYU){ .md-button .md-button--primary } &#128072;
+[:fontawesome-brands-discord: Discord](https://discord.gg/bHX5sNFCYU){ .md-button }
+
 Join our Discord community where you can
 connect with other developers and ask for support to the contributors or directly to the Cat &#128570;
 mentioning `@Cheshire Cat AI`.

mkdocs/production/administrators/docker-compose.md

@@ -1,4 +1,4 @@
-To facilitate, speed up, and standardize the Cat's user experience, the Cat lives inside a Docker container.
+To facilitate, speed up, and standardize the Cat's user experience, the Cat lives inside a Docker container. This allows for maximum power, flexibility and portability, but requires a little understanding from you on [how docker works](https://docs.docker.com/get-started/).
 
 
 ## Cat standalone
@@ -19,20 +19,26 @@ services:
 
 ## Cat + Ollama
 
-The cat is agnostic, meaning You can attach your preferred llm and embedder model/provider. The Cat supports the most used ones, but you can increase the number of models/providers by [plugins](../../plugins/hooks.md/#__tabbed_1_5), here is a list of the main ones:
+The Cat is model agnostic, meaning you can attach your preferred LLM and embedder model/provider. The Cat supports the most used ones, but you can increase the number of models/providers by [plugins](../../plugins/hooks.md/#__tabbed_1_5), here is a list of the main ones:
 
 1. OpenAI and Azure OpenAI
 2. Cohere
-3. Ollama (LLM model only)
+3. Ollama
 4. HuggingFace TextInference API (LLM model only)
 5. Google Gemini
 6. Qdrant FastEmbed (Embedder model only)
 7. (custom via plugin)
 
-If you want a setup Cat + Ollama, here an example `compose.yml`:
+Let's see a full local setup for Cat + Ollama.  
+To make this work properly, be sure your docker engine can see the GPU via [NVIDIA docker](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html).
+
+As an alternative you can install Ollama directly on your machine and making the Cat aware of it in the Ollama LLM settings, inserting your local network IP or using `host.docker.internal`.
+
+Example `compose.yml`:
 
 ```yaml
 services:
+
   cheshire-cat-core:
     image: ghcr.io/cheshire-cat-ai/core:latest
     container_name: cheshire_cat_core
@@ -64,10 +70,14 @@ services:
               capabilities: [gpu]
 ```
 
+For a solid local embedder, choose one from the FastEmbed list.  
+The Cat will download the embedder in `cat/data` and will use it to embed text.  
+Congratulations, you are now free from commercial LLM providers.
+
 ## Cat + Qdrant
 
 By default the Core uses an embedded version of [Qdrant](https://qdrant.tech/), based on SQLite.  
-It is highly recommended to connect the Cat to a full Qdrant instance to increase performance and capacity!
+It is highly recommended to connect the Cat to a full Qdrant instance to increase performance and scalability!
 
 ```yaml
 services:

mkdocs/quickstart/installation-configuration.md

@@ -27,7 +27,7 @@ services:
     image: ghcr.io/cheshire-cat-ai/core:latest
     container_name: cheshire_cat_core
     ports:
-      - ${CORE_PORT:-1865}:80
+      - 1865:80
     volumes:
       - ./static:/app/cat/static
       - ./plugins:/app/cat/plugins

mkdocs/quickstart/introduction.md

@@ -1,5 +1,7 @@
 # Introduction
 
+There are a few things you need to know about the Cheshire Cat. If you are eager to launch and start hacking, jump to the [installation page](installation-configuration.md), but please be sure to return here.
+
 The Cheshire Cat is a ready-to-use AI micro-framework.
 Once installed and connected to a Language Model (LLM), it can be queried through APIs.
 These APIs return the responses provided by the LLM.

mkdocs/quickstart/prepare-plugin.md

@@ -1,4 +1,4 @@
-# 🔌 Preparing a Plugin
+# 🔌 Your first Plugin
 
 Plugins are packages of `Tools` and `Hooks`.
 You don't distribute a `Tool` or a `Hook` directly, you will distribute a Plugin containing them.

mkdocs/stylesheets/extra.css

@@ -26,6 +26,11 @@ body[data-md-color-scheme="slate"] .md-header__button.md-logo img {
   color: black;
 }
 
+/* Buttons */
+[data-md-color-scheme="custom"] .md-button {
+  color: #666;
+}
+
 [data-md-color-scheme="custom"] .md-typeset a {
   font-weight: 700;
 }