docs: Update modelyaml, llama.cpp parameters, log in the data folder

docs/basic-usage/command-line.md

@@ -11,13 +11,13 @@ slug: "command-line"
 Cortex has a [Docker](https://docs.docker.com/engine/reference/commandline/cli/) and [Ollama](https://ollama.com/)-inspired [CLI syntax](/docs/cli) for running model operations. 
 
 ## How It Works
-Cortex’s CLI invokes the Cortex Engine’s API, which runs in the background on port `1337`. 
+Cortex’s CLI invokes the Cortex Engine’s API, which runs in the background on port `3928`. 
 
 
 ## Basic Usage
 ### [Start Cortex Server](/docs/cli)
 ```bash
-# By default the server will be started on port `1337`
+# By default the server will be started on port `3928`
 cortex
 ```
 ### [Run Model](/docs/cli/run)

docs/basic-usage/cortexrc.mdx

@@ -0,0 +1,45 @@
+---
+title: .cortexrc
+description: .cortexrc Overview.
+slug: "cortexrc"
+---
+
+import Tabs from "@theme/Tabs";
+import TabItem from "@theme/TabItem";
+
+:::warning
+🚧 Cortex.cpp is currently under development. Our documentation outlines the intended behavior of Cortex, which may not yet be fully implemented in the codebase.
+:::
+
+Cortex.cpp supports reading its configuration from a file called `.cortexrc`. Using this file, you can also change the data folder, Cortex.cpp API server port, and host.
+
+## File Location
+The configuration file is stored in the following locations:
+
+- **Windows**:
+  - Stable: `C:\Users\<username>\.cortexrc`
+  - Beta: `C:\Users\<username>\.cortexrc-beta`
+  - Nighty: `C:\Users\<username>\.cortexrc-nightly`
+- **Linux**:
+  - Stable: `/home/<username>/.cortexrc`
+  - Beta: `/home/<username>/.cortexrc-beta`
+  - Nighty: `/home/<username>/.cortexrc-nightly`
+- **macOS**:
+  - Stable: `/Users/<username>/.cortexrc`
+  - Beta: `/Users/<username>/.cortexrc-beta`
+  - Nighty: `/Users/<username>/.cortexrc-nightly`
+
+## Configuration Parameters
+You can configure the following parameters in the `.cortexrc` file:
+| Parameter        | Description                                      | Default Value                  |
+|------------------|--------------------------------------------------|--------------------------------|
+| `dataFolderPath` | Path to the folder where `.cortexrc` located.  | User's home folder.  |
+| `apiServerHost`  | Host address for the Cortex.cpp API server.       | `127.0.0.1`                    |
+| `apiServerPort`  | Port number for the Cortex.cpp API server.        | `3928`                         |
+
+Example of the `.cortexrc` file:
+```
+dataFolderPath: /Users/<username>/cortexcpp
+apiServerHost: 127.0.0.1
+apiServerPort: 3928
+```

docs/basic-usage/overview.mdx

@@ -0,0 +1,140 @@
+---
+title: API
+description: Cortex Server Overview.
+slug: "basic-usage"
+---
+
+import Tabs from "@theme/Tabs";
+import TabItem from "@theme/TabItem";
+
+:::warning
+🚧 Cortex.cpp is currently under development. Our documentation outlines the intended behavior of Cortex, which may not yet be fully implemented in the codebase.
+:::
+
+Cortex has an [API server](https://cortex.so/api-reference) that runs at `localhost:3928`.
+
+
+## Usage
+### Start Cortex.cpp Server
+<Tabs>
+  <TabItem value="MacOs/Linux" label="MacOs/Linux">
+  ```sh
+  # Stable
+  cortex
+
+  # Beta
+  cortex-beta
+
+  # Nightly
+  cortex-nightly
+  ```
+  </TabItem>
+  <TabItem value="Windows" label="Windows">
+  ```sh
+  # Stable
+  cortex.exe
+
+  # Beta
+  cortex-beta.exe
+
+  # Nightly
+  cortex-nightly.exe
+  ```
+  </TabItem>
+</Tabs>
+### Run Model
+```bash
+# Pull a model
+curl --request POST \
+  --url http://localhost:3928/v1/models/mistral/pull
+# Start the model
+curl --request POST \
+  --url http://localhost:3928/v1/models/mistral/start \
+  --header 'Content-Type: application/json' \
+  --data '{
+  "prompt_template": "system\n{system_message}\nuser\n{prompt}\nassistant",
+  "stop": [],
+  "ngl": 4096,
+  "ctx_len": 4096,
+  "cpu_threads": 10,
+  "n_batch": 2048,
+  "caching_enabled": true,
+  "grp_attn_n": 1,
+  "grp_attn_w": 512,
+  "mlock": false,
+  "flash_attn": true,
+  "cache_type": "f16",
+  "use_mmap": true,
+  "engine": "llamacpp"
+}'
+```
+### Show the Model State 
+```bash
+# Check the model status
+curl --request GET \
+  --url http://localhost:3928/v1/system/events/model
+```
+### Chat with Model
+```bash
+# Invoke the chat completions endpoint
+curl http://localhost:3928/v1/chat/completions \
+-H "Content-Type: application/json" \
+-d '{
+  "model": "",
+  "messages": [
+    {
+      "role": "user",
+      "content": "Hello"
+    },
+  ],
+  "model": "mistral",
+  "stream": true,
+  "max_tokens": 1,
+  "stop": [
+      null
+  ],
+  "frequency_penalty": 1,
+  "presence_penalty": 1,
+  "temperature": 1,
+  "top_p": 1
+}'
+```
+### Stop Model
+```bash
+# Stop a model
+curl --request POST \
+  --url http://localhost:3928/v1/models/mistral/stop
+```
+### Pull Model
+```bash
+# Pull a model
+curl --request POST \
+  --url http://localhost:3928/v1/models/mistral/pull
+```
+### Stop Cortex.cpp Server
+<Tabs>
+  <TabItem value="MacOs/Linux" label="MacOs/Linux">
+  ```sh
+  # Stable
+  cortex stop
+
+  # Beta
+  cortex-beta stop
+
+  # Nightly
+  cortex-nightly stop
+  ```
+  </TabItem>
+  <TabItem value="Windows" label="Windows">
+  ```sh
+  # Stable
+  cortex.exe stop
+
+  # Beta
+  cortex-beta.exe stop
+
+  # Nightly
+  cortex-nightly.exe stop
+  ```
+  </TabItem>
+</Tabs>

docs/basic-usage/server.mdx

@@ -17,7 +17,7 @@ Cortex has an [API server](https://cortex.so/api-reference) that runs at `localh
 ## Usage
 ### Start Cortex Server
 ```bash
-# By default the server will be started on port `1337`
+# By default the server will be started on port `3928`
 cortex
 # Start a server with different port number
 cortex -a <address> -p <port_number>

docs/cli/chat.md → docs/cli/chat.mdx

@@ -4,6 +4,9 @@ description: Cortex chat command.
 slug: "chat"
 ---
 
+import Tabs from "@theme/Tabs";
+import TabItem from "@theme/TabItem";
+
 :::warning
 🚧 Cortex.cpp is currently under development. Our documentation outlines the intended behavior of Cortex, which may not yet be fully implemented in the codebase.
 :::
@@ -18,10 +21,33 @@ This CLI command calls the following API endpoint:
 This command starts a chat session with a specified model, allowing you to interact directly with it through an interactive chat interface.
 
 ## Usage
+<Tabs>
+  <TabItem value="MacOs/Linux" label="MacOs/Linux">
+  ```sh
+  # Stable
+  cortex chat [options] <model_id> <message>
+
+  # Beta
+  cortex-beta chat [options] <model_id> <message>
+
+  # Nightly
+  cortex-nightly chat [options] <model_id> <message>
+  ```
+  </TabItem>
+  <TabItem value="Windows" label="Windows">
+  ```sh
+  # Stable
+  cortex.exe chat [options] <model_id> <message>
+
+  # Beta
+  cortex-beta.exe chat [options] <model_id> <message>
+
+  # Nightly
+  cortex-nightly.exe chat [options] <model_id> <message>
+  ```
+  </TabItem>
+</Tabs>
 
-```bash
-cortex chat [options] <model_id> <message>
-```
 :::info
 This command uses a `model_id` from the model that you have downloaded or available in your file system.
 :::

docs/cli/cortex.md → docs/cli/cortex.mdx

@@ -4,6 +4,9 @@ description: Cortex CLI.
 slug: /cli
 ---
 
+import Tabs from "@theme/Tabs";
+import TabItem from "@theme/TabItem";
+
 :::warning
 🚧 Cortex.cpp is currently under development. Our documentation outlines the intended behavior of Cortex, which may not yet be fully implemented in the codebase.
 :::
@@ -13,13 +16,36 @@ slug: /cli
 This is the initial command you need to run to start using Cortex.cpp.
 :::
 
-This command starts the Cortex.cpp process and the API server, which runs on port `1337` by default.
+This command starts the Cortex.cpp API server, which runs on port `3928` by default.
 
 ## Usage
+<Tabs>
+  <TabItem value="MacOs/Linux" label="MacOs/Linux">
+  ```sh
+  # Stable
+  cortex [command] [options]
+
+  # Beta
+  cortex-beta [command] [options]
+
+  # Nightly
+  cortex-nightly [command] [options]
+  ```
+  </TabItem>
+  <TabItem value="Windows" label="Windows">
+  ```sh
+  # Stable
+  cortex.exe [command] [options]
+
+  # Beta
+  cortex-beta.exe [command] [options]
+
+  # Nightly
+  cortex-nightly.exe [command] [options]
+  ```
+  </TabItem>
+</Tabs>
 
-```bash
-cortex [command] [options]
-```
 
 ## Options
 
@@ -50,4 +76,5 @@ For example:
 - [cortex engines](/docs/cli/engines): Manage Cortex.cpp engines.
 - [cortex pull|download](/docs/cli/pull): Download a model.
 - [cortex run](/docs/cli/run): Shortcut to start a model and chat.
-- [cortex update](/docs/cli/stop): Update the Cortex.cpp version.
+- [cortex update](/docs/cli/update): Update the Cortex.cpp version.
+- [cortex stop](/docs/cli/stop): Stop the Cortex.cpp API server.

docs/cli/embeddings.mdx

@@ -4,6 +4,9 @@ description: Cortex embeddings command.
 slug: "embeddings"
 ---
 
+import Tabs from "@theme/Tabs";
+import TabItem from "@theme/TabItem";
+
 :::warning
 🚧 Cortex.cpp is currently under development. Our documentation outlines the intended behavior of Cortex, which may not yet be fully implemented in the codebase.
 :::
@@ -19,14 +22,33 @@ This command creates the embedding vector representing the input text.
 
 ## Usage
 
-```bash 
+<Tabs>
+  <TabItem value="MacOs/Linux" label="MacOs/Linux">
+  ```sh
+  # Stable
+  cortex embeddings [options] [model_id] [message]
+
+  # Beta
+  cortex-beta embeddings [options] [model_id] [message]
+
+  # Nightly
+  cortex-nightly embeddings [options] [model_id] [message]
+  ```
+  </TabItem>
+  <TabItem value="Windows" label="Windows">
+  ```sh
+  # Stable
+  cortex.exe embeddings [options] [model_id] [message]
+
+  # Beta
+  cortex-beta.exe embeddings [options] [model_id] [message]
+
+  # Nightly
+  cortex-nightly.exe embeddings [options] [model_id] [message]
+  ```
+  </TabItem>
+</Tabs>
 
-# With a model started
-cortex models start [model_id]
-cortex embeddings [options] [message]
-# Without any started models
-cortex embeddings [options] [model_id] [message]
-```
 :::info
 This command uses a `model_id` from the model that you have downloaded or available in your file system.
 :::