diff --git a/docs/basic-usage/command-line.md b/docs/basic-usage/command-line.md
index 05a10fe..2cf8a42 100644
--- a/docs/basic-usage/command-line.md
+++ b/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
-Cortexβs CLI invokes the Cortex Engineβs API, which runs in the background on port `1337`.
+Cortexβs CLI invokes the Cortex Engineβs 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)
diff --git a/docs/basic-usage/cortexrc.mdx b/docs/basic-usage/cortexrc.mdx
new file mode 100644
index 0000000..504a8de
--- /dev/null
+++ b/docs/basic-usage/cortexrc.mdx
@@ -0,0 +1,12 @@
+---
+title: .cortexrc
+description: .cortexrc Overview.
+slug: "cortexrc"
+---
+
+import Tabs from "@theme/Tabs";
+import TabItem from "@theme/TabItem";
+
+:::warning
+π§ Cortex.cpp is currently under development. Our documentation outlines the intended behavior of Cortex, which may not yet be fully implemented in the codebase.
+:::
\ No newline at end of file
diff --git a/docs/basic-usage/overview.mdx b/docs/basic-usage/overview.mdx
new file mode 100644
index 0000000..24b3c97
--- /dev/null
+++ b/docs/basic-usage/overview.mdx
@@ -0,0 +1,140 @@
+---
+title: Overview
+description: Overview.
+slug: "basic-usage"
+---
+
+import Tabs from "@theme/Tabs";
+import TabItem from "@theme/TabItem";
+
+:::warning
+π§ 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
+
+
+ ```sh
+ # Stable
+ cortex start
+
+ # Beta
+ cortex-beta start
+
+ # Nightly
+ cortex-nightly start
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe start
+
+ # Beta
+ cortex-beta.exe start
+
+ # Nightly
+ cortex-nightly.exe start
+ ```
+
+
+### 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
+
+
+ ```sh
+ # Stable
+ cortex stop
+
+ # Beta
+ cortex-beta stop
+
+ # Nightly
+ cortex-nightly stop
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe stop
+
+ # Beta
+ cortex-beta.exe stop
+
+ # Nightly
+ cortex-nightly.exe stop
+ ```
+
+
\ No newline at end of file
diff --git a/docs/basic-usage/server.mdx b/docs/basic-usage/server.mdx
index 3a74bab..bbf78eb 100644
--- a/docs/basic-usage/server.mdx
+++ b/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
-p
diff --git a/docs/cli/chat.md b/docs/cli/chat.mdx
similarity index 73%
rename from docs/cli/chat.md
rename to docs/cli/chat.mdx
index 7fa2270..6615ac0 100644
--- a/docs/cli/chat.md
+++ b/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
π§ 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 +21,36 @@ 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
+:::info
+You can use the `--verbose` flag to display more detailed output of the internal processes. To apply this flag, use the following format: `cortex --verbose [subcommand]`.
+:::
+
+
+ ```sh
+ # Stable
+ cortex chat [options] -m
+
+ # Beta
+ cortex-beta chat [options] -m
+
+ # Nightly
+ cortex-nightly chat [options] -m
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe chat [options] -m
+
+ # Beta
+ cortex-beta.exe chat [options] -m
+
+ # Nightly
+ cortex-nightly.exe chat [options] -m
+ ```
+
+
-```bash
-cortex chat [options]
-```
:::info
This command uses a `model_id` from the model that you have downloaded or available in your file system.
:::
diff --git a/docs/cli/cortex.md b/docs/cli/cortex.md
deleted file mode 100644
index 7d897bb..0000000
--- a/docs/cli/cortex.md
+++ /dev/null
@@ -1,53 +0,0 @@
----
-title: Cortex
-description: Cortex CLI.
-slug: /cli
----
-
-:::warning
-π§ 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
-:::info
-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.
-
-## Usage
-
-```bash
-cortex [command] [options]
-```
-
-## Options
-
-| Option | Description | Required | Default value | Example |
-| ---------------------------- | ----------------------------------------- | -------- | ------------- | ----------------------------- |
-| `-v`, `--version` | Show version. | No | - | `-v` |
-| `-h`, `--help` | Display help information for the command. | No | - | `-h` |
-| `--verbose` | Show the detailed command logs | No | - | `--verbose` |
-
-
-
-
-## Command Chaining
-Cortex CLI's command chaining support allows multiple commands to be executed in sequence with a simplified syntax.
-
-For example:
-
-- [cortex run](/docs/cli/run)
-- [cortex chat](/docs/cli/chat)
-
-## Sub Commands
-
-- [cortex models](/docs/cli/models): Manage and configure models.
-- [cortex chat](/docs/cli/chat): Send a chat request to a model.
-- [cortex ps](/docs/cli/ps): Display active models and their operational status.
-- [cortex embeddings](/docs/cli/embeddings): Create an embedding vector representing the input text.
-- [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.
diff --git a/docs/cli/cortex.mdx b/docs/cli/cortex.mdx
new file mode 100644
index 0000000..517494c
--- /dev/null
+++ b/docs/cli/cortex.mdx
@@ -0,0 +1,68 @@
+---
+title: Cortex
+description: Cortex CLI.
+slug: /cli
+---
+
+import Tabs from "@theme/Tabs";
+import TabItem from "@theme/TabItem";
+
+:::warning
+π§ 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
+This command list all the available commands within the Cortex.cpp commands.
+
+## Usage
+:::info
+You can use the `--verbose` flag to display more detailed output of the internal processes. To apply this flag, use the following format: `cortex --verbose [subcommand]`.
+:::
+
+
+ ```sh
+ # Stable
+ cortex
+
+ # Beta
+ cortex-beta
+
+ # Nightly
+ cortex-nightly
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe
+
+ # Beta
+ cortex-beta.exe
+
+ # Nightly
+ cortex-nightly.exe
+ ```
+
+
+
+
+## Command Chaining
+Cortex CLI's command chaining support allows multiple commands to be executed in sequence with a simplified syntax.
+
+For example:
+
+- [cortex run](/docs/cli/run)
+- [cortex chat](/docs/cli/chat)
+
+## Sub Commands
+
+- [cortex models](/docs/cli/models): Manage and configure models.
+- [cortex chat](/docs/cli/chat): Send a chat request to a model.
+- [cortex ps](/docs/cli/ps): Display active models and their operational status.
+- [cortex embeddings](/docs/cli/embeddings): Create an embedding vector representing the input text.
+- [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/update): Update the Cortex.cpp version.
+- [cortex start](/docs/cli/start): Start the Cortex.cpp API server.
+- [cortex stop](/docs/cli/stop): Stop the Cortex.cpp API server.
diff --git a/docs/cli/embeddings.mdx b/docs/cli/embeddings.mdx
index 6713326..d43a26d 100644
--- a/docs/cli/embeddings.mdx
+++ b/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
π§ Cortex.cpp is currently under development. Our documentation outlines the intended behavior of Cortex, which may not yet be fully implemented in the codebase.
:::
@@ -18,15 +21,36 @@ This command creates the embedding vector representing the input text.
## Usage
+:::info
+You can use the `--verbose` flag to display more detailed output of the internal processes. To apply this flag, use the following format: `cortex --verbose [subcommand]`.
+:::
+
+
+ ```sh
+ # Stable
+ cortex embeddings [options] [model_id] [message]
+
+ # Beta
+ cortex-beta embeddings [options] [model_id] [message]
+
+ # Nightly
+ cortex-nightly embeddings [options] [model_id] [message]
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe embeddings [options] [model_id] [message]
+
+ # Beta
+ cortex-beta.exe embeddings [options] [model_id] [message]
-```bash
+ # Nightly
+ cortex-nightly.exe embeddings [options] [model_id] [message]
+ ```
+
+
-# 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.
:::
diff --git a/docs/cli/engines/index.mdx b/docs/cli/engines/index.mdx
index 53202f4..6b07fa8 100644
--- a/docs/cli/engines/index.mdx
+++ b/docs/cli/engines/index.mdx
@@ -2,6 +2,9 @@
title: Cortex Engines
---
+import Tabs from "@theme/Tabs";
+import TabItem from "@theme/TabItem";
+
:::warning
π§ Cortex.cpp is currently under development. Our documentation outlines the intended behavior of Cortex, which may not yet be fully implemented in the codebase.
:::
@@ -13,10 +16,36 @@ This command allows you to manage various engines available within Cortex.
**Usage**:
+:::info
+You can use the `--verbose` flag to display more detailed output of the internal processes. To apply this flag, use the following format: `cortex --verbose [subcommand]`.
+:::
+
+
+ ```sh
+ # Stable
+ cortex engines [options] [subcommand]
+
+ # Beta
+ cortex-beta engines [options] [subcommand]
+
+ # Nightly
+ cortex-nightly engines [options] [subcommand]
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe engines [options] [subcommand]
+
+ # Beta
+ cortex-beta.exe engines [options] [subcommand]
+
+ # Nightly
+ cortex-nightly.exe engines [options] [subcommand]
+ ```
+
+
-```bash
-cortex engines [options] [subcommand]
-```
**Options**:
@@ -35,10 +64,36 @@ This command returns an engine detail defined by an engine `engine_name`.
**Usage**:
+:::info
+You can use the `--verbose` flag to display more detailed output of the internal processes. To apply this flag, use the following format: `cortex --verbose [subcommand]`.
+:::
+
+
+ ```sh
+ # Stable
+ cortex engines get
+
+ # Beta
+ cortex-beta engines get
+
+ # Nightly
+ cortex-nightly engines get
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe engines get
+
+ # Beta
+ cortex-beta.exe engines get
+
+ # Nightly
+ cortex-nightly.exe engines get
+ ```
+
+
-```bash
-cortex engines get
-```
For example, it returns the following:
```bash
βββββββββββββββ¬βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
@@ -72,10 +127,36 @@ This command lists all the Cortex's engines.
**Usage**:
+:::info
+You can use the `--verbose` flag to display more detailed output of the internal processes. To apply this flag, use the following format: `cortex --verbose [subcommand]`.
+:::
+
+
+ ```sh
+ # Stable
+ cortex engines list [options]
+
+ # Beta
+ cortex-beta engines list [options]
+
+ # Nightly
+ cortex-nightly engines list [options]
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe engines list [options]
+
+ # Beta
+ cortex-beta.exe engines list [options]
+
+ # Nightly
+ cortex-nightly.exe engines list [options]
+ ```
+
+
-```bash
-cortex engines list [options]
-```
For example, it returns the following:
```bash
+---------+---------------------+-------------------------------------------------------------------------------+---------+------------------------------+-----------------+
@@ -110,9 +191,36 @@ This command downloads the required dependencies and installs the engine within
- `Tensorrt-llm`
**Usage**:
-```bash
-cortex engines install [options]
-```
+:::info
+You can use the `--verbose` flag to display more detailed output of the internal processes. To apply this flag, use the following format: `cortex --verbose [subcommand]`.
+:::
+
+
+ ```sh
+ # Stable
+ cortex engines install [options]
+
+ # Beta
+ cortex-beta engines install [options]
+
+ # Nightly
+ cortex-nightly engines install [options]
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe engines install [options]
+
+ # Beta
+ cortex-beta.exe engines install [options]
+
+ # Nightly
+ cortex-nightly.exe engines install [options]
+ ```
+
+
+
For Example:
```bash
## Llama.cpp engine
@@ -138,9 +246,36 @@ cortex engines install tensorrt-llm
This command uninstalls the engine within Cortex.
**Usage**:
-```bash
-cortex engines uninstall [options]
-```
+:::info
+You can use the `--verbose` flag to display more detailed output of the internal processes. To apply this flag, use the following format: `cortex --verbose [subcommand]`.
+:::
+
+
+ ```sh
+ # Stable
+ cortex engines uninstall [options]
+
+ # Beta
+ cortex-beta engines uninstall [options]
+
+ # Nightly
+ cortex-nightly engines uninstall [options]
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe engines uninstall [options]
+
+ # Beta
+ cortex-beta.exe engines uninstall [options]
+
+ # Nightly
+ cortex-nightly.exe engines uninstall [options]
+ ```
+
+
+
For Example:
```bash
## Llama.cpp engine
diff --git a/docs/cli/models/index.md b/docs/cli/models/index.md
deleted file mode 100644
index f1f79e0..0000000
--- a/docs/cli/models/index.md
+++ /dev/null
@@ -1,248 +0,0 @@
----
-title: Cortex Models
----
-
-:::warning
-π§ 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 models`
-
-This command allows you to start, stop, and manage various local or remote model operations within Cortex.
-
-
-**Usage**:
-
-```bash
-cortex models [options]
-```
-
-**Options**:
-
-| Option | Description | Required | Default value | Example |
-|-------------------|-------------------------------------------------------|----------|---------------|-----------------|
-| `-h`, `--help` | Display help information for the command. | No | - | `-h` |
-
-
-
-## `cortex models get`
-:::info
-This CLI command calls the following API endpoint:
-- [Get Model](/api-reference#tag/models/get/v1/models/{id})
-:::
-This command returns a model detail defined by a `model_id`.
-
-
-
-**Usage**:
-
-```bash
-cortex models get
-```
-For example, it returns the following:
-
-```bash
-ModelConfig Details:
--------------------
-id: tinyllama
-name: tinyllama 1B
-model: tinyllama:1B
-version: 1
-stop: []
-top_p: 0.95
-temperature: 0.7
-frequency_penalty: 0
-presence_penalty: 0
-max_tokens: 4096
-stream: true
-ngl: 33
-ctx_len: 4096
-engine: llamacpp
-prompt_template:
-
-<|system|>
-{system_message}
-
-
-
-
-<|user|>
-{prompt}
-
-
-<|assistant|>
-
-
-system_template:
-
-<|system|>
-
-user_template:
-
-
-
-
-<|user|>
-
-ai_template:
-
-
-<|assistant|>
-
-
-tp: 0
-text_model: false
-files: [model_path]
-created: 1725342964
-```
-:::info
-This command uses a `model_id` from the model that you have downloaded or available in your file system.
-:::
-
-**Options**:
-
-| Option | Description | Required | Default value | Example |
-|-------------------|-------------------------------------------------------|----------|---------------|-----------------|
-| `model_id` | The identifier of the model you want to retrieve. | Yes | - | `mistral`|
-| `-h`, `--help` | Display help information for the command. | No | - | `-h` |
-
-## `cortex models list`
-:::info
-This CLI command calls the following API endpoint:
-- [List Model](/api-reference#tag/models/get/v1/models)
-:::
-This command lists all the downloaded local and remote models.
-
-
-
-**Usage**:
-
-```bash
-cortex models list [options]
-```
-For example, it returns the following:
-```bash
-+---------+----------------+-----------------+---------+
-| (Index) | ID | engine | version |
-+---------+----------------+-----------------+---------+
-| 1 | tinyllama-gguf | llamacpp | 1 |
-+---------+----------------+-----------------+---------+
-| 2 | tinyllama | llamacpp | 1 |
-+---------+----------------+-----------------+---------+
-
-```
-
-**Options**:
-
-| Option | Description | Required | Default value | Example |
-|---------------------------|----------------------------------------------------|----------|---------------|----------------------|
-| `-h`, `--help` | Display help for command. | No | - | `-h` |
-
-
-## `cortex models start`
-:::info
-This CLI command calls the following API endpoint:
-- [Start Model](/api-reference#tag/models/post/v1/models/{modelId}/start)
-:::
-This command starts a model defined by a `model_id`.
-
-
-
-**Usage**:
-
-```bash
-# Start a model
-cortex models start
-
-# Start a model with a preset
-cortex models start [options]
-
-# Start with a specified engine
-cortex models start [options] :[engine]
-```
-
-
-:::info
-This command uses a `model_id` from the model that you have downloaded or available in your file system.
-:::
-
-**Options**:
-
-| Option | Description | Required | Default value | Example |
-|---------------------------|---------------------------------------------------------------------------|----------|----------------------------------------------|------------------------|
-| `model_id` | The identifier of the model you want to start. | Yes | `Prompt to select from the available models` | `mistral` |
-| `-h`, `--help` | Display help information for the command. | No | - | `-h` |
-
-
-## `cortex models stop`
-:::info
-This CLI command calls the following API endpoint:
-- [Stop Model](/api-reference#tag/models/post/v1/models/{modelId}/stop)
-:::
-This command stops a model defined by a `model_id`.
-
-
-
-**Usage**:
-
-```bash
-cortex models stop
-```
-:::info
-This command uses a `model_id` from the model that you have started before.
-:::
-**Options**:
-
-| Option | Description | Required | Default value | Example |
-|---------------------------|-----------------------------------------------------------------------------|----------|----------------------|------------------------|
-| `model_id` | The identifier of the model you want to stop. | Yes | - | `mistral` |
-| `-h`, `--help` | Display help information for the command. | No | - | `-h` |
-
-## `cortex models update`
-:::info
-This CLI command calls the following API endpoint:
-- [Update Model](/api-reference#tag/models/patch/v1/models/{model})
-:::
-This command updates a model configuration defined by a `model_id`.
-
-
-
-**Usage**:
-
-```bash
-cortex models update [options]
-```
-:::info
-This command uses a `model_id` from the model that you have downloaded or available in your file system.
-:::
-**Options**:
-
-| Option | Description | Required | Default value | Example |
-|-----------------------------|-------------------------------------------------------------------------------------------------------|----------|----------------------|-----------------------------------------------------------|
-| `model_id` | The identifier of the model you want to update. | Yes | - | `mistral` |
-| `-c`, `--options ` | Specify the options to update the model. Syntax: `-c option1=value1 option2=value2`. | Yes | - | `-c max_tokens=100 temperature=0.5` |
-| `-h`, `--help` | Display help information for the command. | No | - | `-h` |
-
-## `cortex models delete`
-:::info
-This CLI command calls the following API endpoint:
-- [Delete Model](/api-reference#tag/models/delete/v1/models/{id})
-:::
-This command deletes a local model defined by a `model_id`.
-
-
-
-**Usage**:
-
-```bash
-cortex models delete
-```
-:::info
-This command uses a `model_id` from the model that you have downloaded or available in your file system.
-:::
-**Options**:
-| Option | Description | Required | Default value | Example |
-|---------------------------|-----------------------------------------------------------------------------|----------|----------------------|------------------------|
-| `model_id` | The identifier of the model you want to delete. | Yes | - | `mistral` |
-| `-h`, `--help` | Display help for command. | No | - | `-h` |
\ No newline at end of file
diff --git a/docs/cli/models/index.mdx b/docs/cli/models/index.mdx
new file mode 100644
index 0000000..9ac9b62
--- /dev/null
+++ b/docs/cli/models/index.mdx
@@ -0,0 +1,595 @@
+---
+title: Cortex Models
+---
+
+import Tabs from "@theme/Tabs";
+import TabItem from "@theme/TabItem";
+
+:::warning
+π§ 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 models`
+
+This command allows you to start, stop, and manage various local or remote model operations within Cortex.
+
+
+**Usage**:
+:::info
+You can use the `--verbose` flag to display more detailed output of the internal processes. To apply this flag, use the following format: `cortex --verbose [subcommand]`.
+:::
+
+
+ ```sh
+ # Stable
+ cortex models [options] [subcommand]
+
+ # Beta
+ cortex-beta models [options] [subcommand]
+
+ # Nightly
+ cortex-nightly models [options] [subcommand]
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe models [options]
+
+ # Beta
+ cortex-beta.exe models [options]
+
+ # Nightly
+ cortex-nightly.exe models [options]
+ ```
+
+
+
+**Options**:
+
+| Option | Description | Required | Default value | Example |
+|-------------------|-------------------------------------------------------|----------|---------------|-----------------|
+| `-h`, `--help` | Display help information for the command. | No | - | `-h` |
+
+
+
+## `cortex models get`
+:::info
+This CLI command calls the following API endpoint:
+- [Get Model](/api-reference#tag/models/get/v1/models/{id})
+:::
+This command returns a model detail defined by a `model_id`.
+
+
+
+**Usage**:
+:::info
+You can use the `--verbose` flag to display more detailed output of the internal processes. To apply this flag, use the following format: `cortex --verbose [subcommand]`.
+:::
+
+
+ ```sh
+ # Stable
+ cortex models get
+
+ # Beta
+ cortex-beta models get
+
+ # Nightly
+ cortex-nightly models get
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe models get
+
+ # Beta
+ cortex-beta.exe models get
+
+ # Nightly
+ cortex-nightly.exe models get
+ ```
+
+
+
+For example, it returns the following:
+
+```bash
+ModelConfig Details:
+-------------------
+id: tinyllama
+name: tinyllama 1B
+model: tinyllama:1B
+version: 1
+stop: []
+top_p: 0.95
+temperature: 0.7
+frequency_penalty: 0
+presence_penalty: 0
+max_tokens: 4096
+stream: true
+ngl: 33
+ctx_len: 4096
+engine: llamacpp
+prompt_template:
+
+<|system|>
+{system_message}
+
+
+
+
+<|user|>
+{prompt}
+
+
+<|assistant|>
+
+
+system_template:
+
+<|system|>
+
+user_template:
+
+
+
+
+<|user|>
+
+ai_template:
+
+
+<|assistant|>
+
+
+tp: 0
+text_model: false
+files: [model_path]
+created: 1725342964
+```
+:::info
+This command uses a `model_id` from the model that you have downloaded or available in your file system.
+:::
+
+**Options**:
+
+| Option | Description | Required | Default value | Example |
+|-------------------|-------------------------------------------------------|----------|---------------|-----------------|
+| `model_id` | The identifier of the model you want to retrieve. | Yes | - | `mistral`|
+| `-h`, `--help` | Display help information for the command. | No | - | `-h` |
+
+## `cortex models list`
+:::info
+This CLI command calls the following API endpoint:
+- [List Model](/api-reference#tag/models/get/v1/models)
+:::
+This command lists all the downloaded local and remote models.
+
+
+
+**Usage**:
+:::info
+You can use the `--verbose` flag to display more detailed output of the internal processes. To apply this flag, use the following format: `cortex --verbose [subcommand]`.
+:::
+
+
+ ```sh
+ # Stable
+ cortex models list [options]
+
+ # Beta
+ cortex-beta models list [options]
+
+ # Nightly
+ cortex-nightly models list [options]
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe models list [options]
+
+ # Beta
+ cortex-beta.exe models list [options]
+
+ # Nightly
+ cortex-nightly.exe models list [options]
+ ```
+
+
+
+For example, it returns the following:
+```bash
++---------+----------------+-----------------+---------+
+| (Index) | ID | engine | version |
++---------+----------------+-----------------+---------+
+| 1 | tinyllama-gguf | llamacpp | 1 |
++---------+----------------+-----------------+---------+
+| 2 | tinyllama | llamacpp | 1 |
++---------+----------------+-----------------+---------+
+
+```
+
+**Options**:
+
+| Option | Description | Required | Default value | Example |
+|---------------------------|----------------------------------------------------|----------|---------------|----------------------|
+| `-h`, `--help` | Display help for command. | No | - | `-h` |
+
+
+## `cortex models start`
+:::info
+This CLI command calls the following API endpoint:
+- [Start Model](/api-reference#tag/models/post/v1/models/{modelId}/start)
+:::
+This command starts a model defined by a `model_id`.
+
+
+
+**Usage**:
+:::info
+You can use the `--verbose` flag to display more detailed output of the internal processes. To apply this flag, use the following format: `cortex --verbose [subcommand]`.
+:::
+
+
+ ```sh
+ # Stable
+ cortex models start [options]
+
+ # Beta
+ cortex-beta models start [options]
+
+ # Nightly
+ cortex-nightly models start [options]
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe models start [options]
+
+ # Beta
+ cortex-beta.exe models start [options]
+
+ # Nightly
+ cortex-nightly.exe models start [options]
+ ```
+
+
+
+
+:::info
+This command uses a `model_id` from the model that you have downloaded or available in your file system.
+:::
+
+**Options**:
+
+| Option | Description | Required | Default value | Example |
+|---------------------------|---------------------------------------------------------------------------|----------|----------------------------------------------|------------------------|
+| `model_id` | The identifier of the model you want to start. | Yes | `Prompt to select from the available models` | `mistral` |
+| `-h`, `--help` | Display help information for the command. | No | - | `-h` |
+
+
+## `cortex models stop`
+:::info
+This CLI command calls the following API endpoint:
+- [Stop Model](/api-reference#tag/models/post/v1/models/{modelId}/stop)
+:::
+This command stops a model defined by a `model_id`.
+
+
+
+**Usage**:
+:::info
+You can use the `--verbose` flag to display more detailed output of the internal processes. To apply this flag, use the following format: `cortex --verbose [subcommand]`.
+:::
+
+
+ ```sh
+ # Stable
+ cortex models stop
+
+ # Beta
+ cortex-beta models stop
+
+ # Nightly
+ cortex-nightly models stop
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe models stop
+
+ # Beta
+ cortex-beta.exe models stop
+
+ # Nightly
+ cortex-nightly.exe models stop
+ ```
+
+
+
+:::info
+This command uses a `model_id` from the model that you have started before.
+:::
+**Options**:
+
+| Option | Description | Required | Default value | Example |
+|---------------------------|-----------------------------------------------------------------------------|----------|----------------------|------------------------|
+| `model_id` | The identifier of the model you want to stop. | Yes | - | `mistral` |
+| `-h`, `--help` | Display help information for the command. | No | - | `-h` |
+
+## `cortex models update`
+:::info
+This CLI command calls the following API endpoint:
+- [Update Model](/api-reference#tag/models/patch/v1/models/{model})
+:::
+This command updates a model configuration defined by a `model_id`.
+
+
+
+**Usage**:
+:::info
+You can use the `--verbose` flag to display more detailed output of the internal processes. To apply this flag, use the following format: `cortex --verbose [subcommand]`.
+:::
+
+
+ ```sh
+ # Stable
+ cortex models update [options]
+
+ # Beta
+ cortex-beta models update [options]
+
+ # Nightly
+ cortex-nightly models update [options]
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe models update [options]
+
+ # Beta
+ cortex-beta.exe models update [options]
+
+ # Nightly
+ cortex-nightly.exe models update [options]
+ ```
+
+
+
+:::info
+This command uses a `model_id` from the model that you have downloaded or available in your file system.
+:::
+**Options**:
+
+| Option | Description | Required | Default value | Example |
+|-----------------------------|-------------------------------------------------------------------------------------------------------|----------|----------------------|-----------------------------------------------------------|
+| `model_id` | The identifier of the model you want to update. | Yes | - | `mistral` |
+| `-c`, `--options ` | Specify the options to update the model. Syntax: `-c option1=value1 option2=value2`. | Yes | - | `-c max_tokens=100 temperature=0.5` |
+| `-h`, `--help` | Display help information for the command. | No | - | `-h` |
+
+## `cortex models delete`
+:::info
+This CLI command calls the following API endpoint:
+- [Delete Model](/api-reference#tag/models/delete/v1/models/{id})
+:::
+This command deletes a local model defined by a `model_id`.
+
+
+
+**Usage**:
+:::info
+You can use the `--verbose` flag to display more detailed output of the internal processes. To apply this flag, use the following format: `cortex --verbose [subcommand]`.
+:::
+
+
+ ```sh
+ # Stable
+ cortex models delete
+
+ # Beta
+ cortex-beta models delete
+
+ # Nightly
+ cortex-nightly models delete
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe models delete
+
+ # Beta
+ cortex-beta.exe models delete
+
+ # Nightly
+ cortex-nightly.exe models delete
+ ```
+
+
+
+:::info
+This command uses a `model_id` from the model that you have downloaded or available in your file system.
+:::
+
+**Options**:
+| Option | Description | Required | Default value | Example |
+|---------------------------|-----------------------------------------------------------------------------|----------|----------------------|------------------------|
+| `model_id` | The identifier of the model you want to delete. | Yes | - | `mistral` |
+| `-h`, `--help` | Display help for command. | No | - | `-h` |
+
+## `cortex models alias`
+This command adds an alias to a local model that function the same as `model_id`.
+
+
+**Usage**:
+:::info
+You can use the `--verbose` flag to display more detailed output of the internal processes. To apply this flag, use the following format: `cortex --verbose [subcommand]`.
+:::
+
+
+ ```sh
+ # Stable
+ cortex models alias --model_id --alias
+
+ # Beta
+ cortex-beta models alias --model_id --alias
+
+ # Nightly
+ cortex-nightly models alias --model_id --alias
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe models alias --model_id --alias
+
+ # Beta
+ cortex-beta.exe models alias --model_id --alias
+
+ # Nightly
+ cortex-nightly.exe models alias --model_id --alias
+ ```
+
+
+
+
+**Options**:
+| Option | Description | Required | Default value | Example |
+|---------------------------|-----------------------------------------------------------------------------|----------|----------------------|------------------------|
+| `--model_id` | The identifier of the model. | Yes | - | `mistral` |
+| `-alias` | The new identifier for the model. | Yes | - | `mistral_2` |
+
+## `cortex models update`
+This command updates the `model.yaml` file of a local model.
+
+
+**Usage**:
+:::info
+You can use the `--verbose` flag to display more detailed output of the internal processes. To apply this flag, use the following format: `cortex --verbose [subcommand]`.
+:::
+
+
+ ```sh
+ # Stable
+ cortex models update [options]
+
+ # Beta
+ cortex-beta models update [options]
+
+ # Nightly
+ cortex-nightly models update [options]
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe models update [options]
+
+ # Beta
+ cortex-beta.exe models update [options]
+
+ # Nightly
+ cortex-nightly.exe models update [options]
+ ```
+
+
+
+
+**Options**:
+| Option | Description | Required | Default value | Example |
+|---------------------------|-----------------------------------------------------------------------------|----------|----------------------|------------------------|
+| `-h`, `--help` | Display help for command. | No | - | `-h` |
+| `--model_id REQUIRED` | Unique identifier for the model. | Yes | - | `--model_id my_model` |
+| `--name` | Name of the model. | No | - | `--name "GPT Model"` |
+| `--model` | Model type or architecture. | No | - | `--model GPT-4` |
+| `--version` | Version of the model to use. | No | - | `--version 1.2.0` |
+| `--stop` | Stop token to terminate generation. | No | - | `--stop ""` |
+| `--top_p` | Sampling parameter for nucleus sampling. | No | - | `--top_p 0.9` |
+| `--temperature` | Controls randomness in generation. | No | - | `--temperature 0.8` |
+| `--frequency_penalty` | Penalizes repeated tokens based on frequency. | No | - | `--frequency_penalty 0.5` |
+| `--presence_penalty` | Penalizes repeated tokens based on presence. | No | `0.0` | `--presence_penalty 0.6` |
+| `--max_tokens` | Maximum number of tokens to generate. | No | - | `--max_tokens 1500` |
+| `--stream` | Stream output tokens as they are generated. | No | `false` | `--stream true` |
+| `--ngl` | Number of generations in parallel. | No | - | `--ngl 4` |
+| `--ctx_len` | Maximum context length in tokens. | No | - | `--ctx_len 1024` |
+| `--engine` | Compute engine for running the model. | No | - | `--engine CUDA` |
+| `--prompt_template` | Template for the prompt structure. | No | - | `--prompt_template "###"` |
+| `--system_template` | Template for system-level instructions. | No | - | `--system_template "SYSTEM"` |
+| `--user_template` | Template for user inputs. | No | - | `--user_template "USER"` |
+| `--ai_template` | Template for AI responses. | No | - | `--ai_template "ASSISTANT"` |
+| `--os` | Operating system environment. | No | - | `--os Ubuntu` |
+| `--gpu_arch` | GPU architecture specification. | No | - | `--gpu_arch A100` |
+| `--quantization_method` | Quantization method for model weights. | No | - | `--quantization_method int8` |
+| `--precision` | Floating point precision for computations. | No | `float32` | `--precision float16` |
+| `--tp` | Tensor parallelism. | No | - | `--tp 4` |
+| `--trtllm_version` | Version of the TRTLLM library. | No | - | `--trtllm_version 2.0` |
+| `--text_model` | The model used for text generation. | No | - | `--text_model llama2` |
+| `--files` | File path or resources associated with the model. | No | - | `--files config.json` |
+| `--created` | Creation date of the model. | No | - | `--created 2024-01-01` |
+| `--object` | The object type (e.g., model or file). | No | - | `--object model` |
+| `--owned_by` | The owner or creator of the model. | No | - | `--owned_by "Company"` |
+| `--seed` | Seed for random number generation. | No | - | `--seed 42` |
+| `--dynatemp_range` | Range for dynamic temperature scaling. | No | - | `--dynatemp_range 0.7-1.0` |
+| `--dynatemp_exponent` | Exponent for dynamic temperature scaling. | No | - | `--dynatemp_exponent 1.2` |
+| `--top_k` | Top K sampling to limit token selection. | No | - | `--top_k 50` |
+| `--min_p` | Minimum probability threshold for tokens. | No | - | `--min_p 0.1` |
+| `--tfs_z` | Token frequency selection scaling factor. | No | - | `--tfs_z 0.5` |
+| `--typ_p` | Typicality-based token selection probability. | No | - | `--typ_p 0.9` |
+| `--repeat_last_n` | Number of last tokens to consider for repetition penalty. | No | - | `--repeat_last_n 64` |
+| `--repeat_penalty` | Penalty for repeating tokens. | No | - | `--repeat_penalty 1.2` |
+| `--mirostat` | Mirostat sampling method for stable generation. | No | - | `--mirostat 1` |
+| `--mirostat_tau` | Target entropy for Mirostat. | No | - | `--mirostat_tau 5.0` |
+| `--mirostat_eta` | Learning rate for Mirostat. | No | - | `--mirostat_eta 0.1` |
+| `--penalize_nl` | Penalize new lines in generation. | No | `false` | `--penalize_nl true` |
+| `--ignore_eos` | Ignore the end of sequence token. | No | `false` | `--ignore_eos true` |
+| `--n_probs` | Number of probability outputs to return. | No | - | `--n_probs 5` |
+
+## `cortex models import`
+This command imports the local model using the model's `gguf` file.
+
+
+**Usage**:
+:::info
+You can use the `--verbose` flag to display more detailed output of the internal processes. To apply this flag, use the following format: `cortex --verbose [subcommand]`.
+:::
+
+
+ ```sh
+ # Stable
+ cortex models import --model_id --model_path
+
+ # Beta
+ cortex-beta models import --model_id --model_path
+
+ # Nightly
+ cortex-nightly models import --model_id --model_path
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe models import --model_id --model_path
+
+ # Beta
+ cortex-beta.exe models import --model_id --model_path
+
+ # Nightly
+ cortex-nightly.exe models import --model_id --model_path
+ ```
+
+
+
+
+**Options**:
+| Option | Description | Required | Default value | Example |
+|---------------------------|-----------------------------------------------------------------------------|----------|----------------------|------------------------|
+| `-h`, `--help` | Display help for command. | No | - | `-h` |
+| `--model_id` | The identifier of the model. | Yes | - | `mistral` |
+| `--model_path` | The path of the model source file. | Yes | - | `/path/to/your/model.gguf` |
\ No newline at end of file
diff --git a/docs/cli/ps.md b/docs/cli/ps.mdx
similarity index 81%
rename from docs/cli/ps.md
rename to docs/cli/ps.mdx
index cdf22e5..cbe09fa 100644
--- a/docs/cli/ps.md
+++ b/docs/cli/ps.mdx
@@ -4,6 +4,9 @@ description: Cortex ps command.
slug: "ps"
---
+import Tabs from "@theme/Tabs";
+import TabItem from "@theme/TabItem";
+
:::warning
π§ Cortex.cpp is currently under development. Our documentation outlines the intended behavior of Cortex, which may not yet be fully implemented in the codebase.
:::
@@ -19,10 +22,36 @@ This command shows the running model and its status.
## Usage
+:::info
+You can use the `--verbose` flag to display more detailed output of the internal processes. To apply this flag, use the following format: `cortex --verbose [subcommand]`.
+:::
+
+
+ ```sh
+ # Stable
+ cortex ps [options]
+
+ # Beta
+ cortex-beta ps [options]
+
+ # Nightly
+ cortex-nightly ps [options]
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe ps [options]
+
+ # Beta
+ cortex-beta.exe ps [options]
+
+ # Nightly
+ cortex-nightly.exe ps [options]
+ ```
+
+
-```bash
-cortex ps [options]
-```
For example, it returns the following table:
diff --git a/docs/cli/pull.md b/docs/cli/pull.mdx
similarity index 58%
rename from docs/cli/pull.md
rename to docs/cli/pull.mdx
index 5dbc478..df1f391 100644
--- a/docs/cli/pull.md
+++ b/docs/cli/pull.mdx
@@ -4,6 +4,9 @@ description: Cortex CLI.
slug: "pull"
---
+import Tabs from "@theme/Tabs";
+import TabItem from "@theme/TabItem";
+
:::warning
π§ Cortex.cpp is currently under development. Our documentation outlines the intended behavior of Cortex, which may not yet be fully implemented in the codebase.
:::
@@ -19,10 +22,36 @@ The downloaded model will be stored in the Cortex folder in your home data direc
## Usage
+:::info
+You can use the `--verbose` flag to display more detailed output of the internal processes. To apply this flag, use the following format: `cortex --verbose [subcommand]`.
+:::
+
+
+ ```sh
+ # Stable
+ cortex pull [options]
+
+ # Beta
+ cortex-beta pull [options]
+
+ # Nightly
+ cortex-nightly pull [options]
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe pull [options]
+
+ # Beta
+ cortex-beta.exe pull [options]
+
+ # Nightly
+ cortex-nightly.exe pull [options]
+ ```
+
+
-```bash
-cortex pull [options]
-```
## Options
diff --git a/docs/cli/run.md b/docs/cli/run.mdx
similarity index 81%
rename from docs/cli/run.md
rename to docs/cli/run.mdx
index 964ee0b..88911ba 100644
--- a/docs/cli/run.md
+++ b/docs/cli/run.mdx
@@ -4,6 +4,9 @@ description: Cortex run command
slug: "run"
---
+import Tabs from "@theme/Tabs";
+import TabItem from "@theme/TabItem";
+
:::warning
π§ Cortex.cpp is currently under development. Our documentation outlines the intended behavior of Cortex, which may not yet be fully implemented in the codebase.
:::
@@ -20,12 +23,36 @@ This CLI command calls the following API endpoint:
This command facilitates the initiation of an interactive chat shell with a specified machine-learning model.
## Usage
+:::info
+You can use the `--verbose` flag to display more detailed output of the internal processes. To apply this flag, use the following format: `cortex --verbose [subcommand]`.
+:::
+
+
+ ```sh
+ # Stable
+ cortex [options] :[engine]
+
+ # Beta
+ cortex-beta [options] :[engine]
+
+ # Nightly
+ cortex-nightly [options] :[engine]
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe [options] :[engine]
+
+ # Beta
+ cortex-beta.exe [options] :[engine]
+
+ # Nightly
+ cortex-nightly.exe [options] :[engine]
+ ```
+
+
-```bash
-cortex run [options]
-# With a specified engine
-cortex run [options] :[engine]
-```
### `model_id`
You can use the [Built-in models](/docs/hub/cortex-hub) or Supported [HuggingFace models](/docs/hub/hugging-face).
diff --git a/docs/cli/serve.md b/docs/cli/serve.md
index 99a8c83..d7193e3 100644
--- a/docs/cli/serve.md
+++ b/docs/cli/serve.md
@@ -28,7 +28,7 @@ cortex serve [options] stop
| Option | Description | Required | Default Value | Example |
|----------------------------|-------------------------------------------|----------|---------------|------------------------|
| `-a`, `--address ` | Specify the address to use. | No | `localhost` | `-a 192.168.1.1`|
-| `-p`, `--port ` | Define the port to serve the application. | No | `1337` | `-p 8080` |
+| `-p`, `--port ` | Define the port to serve the application. | No | `3928` | `-p 8080` |
| `-d`, `--detach` | Run the server in detached mode. | No | `false` | `-d` |
| `-h`, `--help` | Display help information for the command. | No | - | `-h` |
diff --git a/docs/cli/start.mdx b/docs/cli/start.mdx
new file mode 100644
index 0000000..87075d1
--- /dev/null
+++ b/docs/cli/start.mdx
@@ -0,0 +1,60 @@
+---
+title: Cortex Start
+description: Cortex CLI.
+---
+
+import Tabs from "@theme/Tabs";
+import TabItem from "@theme/TabItem";
+
+:::warning
+π§ Cortex.cpp is currently under development. Our documentation outlines the intended behavior of Cortex, which may not yet be fully implemented in the codebase.
+:::
+
+# Start
+:::info
+This is the initial command you need to run to start using Cortex.cpp.
+:::
+
+This command start the Cortex.cpp's API server processes.
+
+## Usage
+:::info
+You can use the `--verbose` flag to display more detailed output of the internal processes. To apply this flag, use the following format: `cortex --verbose [subcommand]`.
+:::
+
+
+ ```sh
+ # Stable
+ cortex start [options]
+
+ # Beta
+ cortex-beta start [options]
+
+ # Nightly
+ cortex-nightly start [options]
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe start [options]
+
+ # Beta
+ cortex-beta.exe start [options]
+
+ # Nightly
+ cortex-nightly.exe start [options]
+ ```
+
+
+
+
+## Options
+
+| Option | Description | Required | Default value | Example |
+| ---------------------------- | ----------------------------------------- | -------- | ------------- | ----------------------------- |
+| `-h`, `--help` | Display help information for the command. | No | - | `-h` |
+| `-p`, `--port ` | Port to serve the application. | No | - | `-p 3928` |
+
+
+
diff --git a/docs/cli/stop.md b/docs/cli/stop.mdx
similarity index 54%
rename from docs/cli/stop.md
rename to docs/cli/stop.mdx
index 3f4aee8..48c4eec 100644
--- a/docs/cli/stop.md
+++ b/docs/cli/stop.mdx
@@ -4,6 +4,9 @@ description: Cortex stop command.
slug: "stop"
---
+import Tabs from "@theme/Tabs";
+import TabItem from "@theme/TabItem";
+
:::warning
π§ 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 +21,36 @@ This command stops the API server.
## Usage
+:::info
+You can use the `--verbose` flag to display more detailed output of the internal processes. To apply this flag, use the following format: `cortex --verbose [subcommand]`.
+:::
+
+
+ ```sh
+ # Stable
+ cortex stop [options]
+
+ # Beta
+ cortex-beta stop [options]
+
+ # Nightly
+ cortex-nightly stop [options]
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe stop [options]
+
+ # Beta
+ cortex-beta.exe stop [options]
+
+ # Nightly
+ cortex-nightly.exe stop [options]
+ ```
+
+
-```bash
-cortex stop [options]
-```
## Options
diff --git a/docs/cli/update.mdx b/docs/cli/update.mdx
index 9355d96..f54d554 100644
--- a/docs/cli/update.mdx
+++ b/docs/cli/update.mdx
@@ -4,6 +4,9 @@ description: Cortex update command.
slug: "update"
---
+import Tabs from "@theme/Tabs";
+import TabItem from "@theme/TabItem";
+
:::warning
π§ Cortex.cpp is currently under development. Our documentation outlines the intended behavior of Cortex, which may not yet be fully implemented in the codebase.
:::
@@ -15,10 +18,36 @@ This command updates Cortex.cpp to the provided version or the latest version.
## Usage
+:::info
+You can use the `--verbose` flag to display more detailed output of the internal processes. To apply this flag, use the following format: `cortex --verbose [subcommand]`.
+:::
+
+
+ ```sh
+ # Stable
+ cortex update [options]
+
+ # Beta
+ cortex-beta update [options]
+
+ # Nightly
+ cortex-nightly update [options]
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe update [options]
+
+ # Beta
+ cortex-beta.exe update [options]
+
+ # Nightly
+ cortex-nightly.exe update [options]
+ ```
+
+
-```bash
-cortex update [options]
-```
:::info
By default, if no version is specified, Cortex.cpp will be updated to the latest version.
:::
diff --git a/docs/data-structures.mdx b/docs/data-folder.mdx
similarity index 96%
rename from docs/data-structures.mdx
rename to docs/data-folder.mdx
index 86a1aa7..c2d502f 100644
--- a/docs/data-structures.mdx
+++ b/docs/data-folder.mdx
@@ -1,7 +1,7 @@
---
-title: Data Structures
-description: Cortex.cpp's data structures.
-slug: "data-structures"
+title: Data Folder
+description: Cortex.cpp's data folder.
+slug: "data-folder"
---
:::warning
diff --git a/docs/hub/cortex-hub.mdx b/docs/hub/cortex-hub.mdx
index 10e4752..6c9ac50 100644
--- a/docs/hub/cortex-hub.mdx
+++ b/docs/hub/cortex-hub.mdx
@@ -3,6 +3,9 @@ title: Cortex Model Repos
description: Cortex's built-in models are hosted on Huggingface, supporting multi-engine repositories.
---
+import Tabs from "@theme/Tabs";
+import TabItem from "@theme/TabItem";
+
:::warning
π§ Cortex.cpp is currently under development. Our documentation outlines the intended behavior of Cortex, which may not yet be fully implemented in the codebase.
:::
@@ -23,16 +26,89 @@ Cortex Model Repos are hosted on Huggingface for several reasons:
## Usage
Download a built-in model from the [Cortex Model Repos](https://huggingface.co/cortexso) using a `model_id`. You can obtain the `model_id` from the Cortex model repository or the model's specific branch.
-```bash
-# Download the default mistral model from: https://huggingface.co/cortexso/mistral/tree/main
-cortex pull mistral
+
+
+ ```sh
+ # Stable
+ ## Download the default mistral model from: https://huggingface.co/cortexso/mistral/tree/main
+ cortex pull mistral
+
+ ## Download an ONNX version of the mistral model from: https://huggingface.co/cortexso/mistral/tree/onnx
+ cortex pull mistral:onnx
+
+ ## Download a TensorRT-LLM version of the mistral model from: https://huggingface.co/cortexso/mistral/tree/tensorrt-llm-linux-ada
+ cortex pull mistral:tensorrt-llm-linux-ada
+
+ ## Download a 7B version of the mistral model from: https://huggingface.co/cortexso/mistral/tree/7b-gguf
+ cortex pull mistral:7b-gguf
+
+ # Beta
+ ## Download the default mistral model from: https://huggingface.co/cortexso/mistral/tree/main
+ cortex-beta pull mistral
+
+ ## Download an ONNX version of the mistral model from: https://huggingface.co/cortexso/mistral/tree/onnx
+ cortex-beta pull mistral:onnx
+
+ ## Download a TensorRT-LLM version of the mistral model from: https://huggingface.co/cortexso/mistral/tree/tensorrt-llm-linux-ada
+ cortex-beta pull mistral:tensorrt-llm-linux-ada
+
+ ## Download a 7B version of the mistral model from: https://huggingface.co/cortexso/mistral/tree/7b-gguf
+ cortex-beta pull mistral:7b-gguf
+
+ # Nightly
+ ## Download the default mistral model from: https://huggingface.co/cortexso/mistral/tree/main
+ cortex-nightly pull mistral
+
+ ## Download an ONNX version of the mistral model from: https://huggingface.co/cortexso/mistral/tree/onnx
+ cortex-nightly pull mistral:onnx
+
+ ## Download a TensorRT-LLM version of the mistral model from: https://huggingface.co/cortexso/mistral/tree/tensorrt-llm-linux-ada
+ cortex-nightly pull mistral:tensorrt-llm-linux-ada
+
+ ## Download a 7B version of the mistral model from: https://huggingface.co/cortexso/mistral/tree/7b-gguf
+ cortex-nightly pull mistral:7b-gguf
+ ```
+
+
+ ```sh
+ # Stable
+ ## Download the default mistral model from: https://huggingface.co/cortexso/mistral/tree/main
+ cortex.exe pull mistral
+
+ ## Download an ONNX version of the mistral model from: https://huggingface.co/cortexso/mistral/tree/onnx
+ cortex.exe pull mistral:onnx
+
+ ## Download a TensorRT-LLM version of the mistral model from: https://huggingface.co/cortexso/mistral/tree/tensorrt-llm-linux-ada
+ cortex.exe pull mistral:tensorrt-llm-linux-ada
+
+ ## Download a 7B version of the mistral model from: https://huggingface.co/cortexso/mistral/tree/7b-gguf
+ cortex.exe pull mistral:7b-gguf
+
+ # Beta
+ ## Download the default mistral model from: https://huggingface.co/cortexso/mistral/tree/main
+ cortex-beta.exe pull mistral
+
+ ## Download an ONNX version of the mistral model from: https://huggingface.co/cortexso/mistral/tree/onnx
+ cortex-beta.exe pull mistral:onnx
+
+ ## Download a TensorRT-LLM version of the mistral model from: https://huggingface.co/cortexso/mistral/tree/tensorrt-llm-linux-ada
+ cortex-beta.exe pull mistral:tensorrt-llm-linux-ada
+
+ ## Download a 7B version of the mistral model from: https://huggingface.co/cortexso/mistral/tree/7b-gguf
+ cortex-beta.exe pull mistral:7b-gguf
+
+ # Nightly
+ ## Download the default mistral model from: https://huggingface.co/cortexso/mistral/tree/main
+ cortex-nightly.exe pull mistral
-# Download an ONNX version of the mistral model from: https://huggingface.co/cortexso/mistral/tree/onnx
-cortex pull mistral:onnx
+ ## Download an ONNX version of the mistral model from: https://huggingface.co/cortexso/mistral/tree/onnx
+ cortex-nightly.exe pull mistral:onnx
-# Download a TensorRT-LLM version of the mistral model from: https://huggingface.co/cortexso/mistral/tree/tensorrt-llm-linux-ada
-cortex pull mistral:tensorrt-llm-linux-ada
+ ## Download a TensorRT-LLM version of the mistral model from: https://huggingface.co/cortexso/mistral/tree/tensorrt-llm-linux-ada
+ cortex-nightly.exe pull mistral:tensorrt-llm-linux-ada
-# Download a 7B version of the mistral model from: https://huggingface.co/cortexso/mistral/tree/7b-gguf
-cortex pull mistral:7b-gguf
-```
\ No newline at end of file
+ ## Download a 7B version of the mistral model from: https://huggingface.co/cortexso/mistral/tree/7b-gguf
+ cortex-nightly.exe pull mistral:7b-gguf
+ ```
+
+
\ No newline at end of file
diff --git a/docs/hub/hugging-face.mdx b/docs/hub/hugging-face.mdx
index 8def7fb..a440999 100644
--- a/docs/hub/hugging-face.mdx
+++ b/docs/hub/hugging-face.mdx
@@ -3,6 +3,9 @@ title: Hugging Face
description: Cortex supports all `GGUF` and `ONNX` models available in Huggingface repositories, providing access to a wide range of models.
---
+import Tabs from "@theme/Tabs";
+import TabItem from "@theme/TabItem";
+
:::warning
π§ Cortex.cpp is currently under development. Our documentation outlines the intended behavior of Cortex, which may not yet be fully implemented in the codebase.
:::
@@ -16,27 +19,110 @@ To pull a supported model from HuggingFace, use the format `ORG_ID/MODEL_ID`.
## GGUF

To view all available `GGUF` models on HuggingFace, select the `GGUF` tag in the Libraries section.
-```bash
-# Pull the Codestral-22B-v0.1-GGUF model from the bartowski organization
-cortex pull bartowski/Codestral-22B-v0.1-GGUF
+
+
+ ```sh
+ # Stable
+ ## Pull the Codestral-22B-v0.1-GGUF model from the bartowski organization
+ cortex pull bartowski/Codestral-22B-v0.1-GGUF
+
+ # Pull the gemma-7b model from the google organization
+ cortex pull google/gemma-7b
+
+ # Beta
+ ## Pull the Codestral-22B-v0.1-GGUF model from the bartowski organization
+ cortex-beta pull bartowski/Codestral-22B-v0.1-GGUF
+
+ # Pull the gemma-7b model from the google organization
+ cortex-beta pull google/gemma-7b
+
+ # Nightly
+ ## Pull the Codestral-22B-v0.1-GGUF model from the bartowski organization
+ cortex-nightly pull bartowski/Codestral-22B-v0.1-GGUF
+
+ # Pull the gemma-7b model from the google organization
+ cortex-nightly pull google/gemma-7b
+ ```
+
+
+ ```sh
+ # Stable
+ ## Pull the Codestral-22B-v0.1-GGUF model from the bartowski organization
+ cortex.exe pull bartowski/Codestral-22B-v0.1-GGUF
+
+ # Pull the gemma-7b model from the google organization
+ cortex.exe pull google/gemma-7b
+
+ # Beta
+ ## Pull the Codestral-22B-v0.1-GGUF model from the bartowski organization
+ cortex-beta.exe pull bartowski/Codestral-22B-v0.1-GGUF
-# Pull the gemma-7b model from the google organization
-cortex pull google/gemma-7b
+ # Pull the gemma-7b model from the google organization
+ cortex-beta.exe pull google/gemma-7b
-```
+ # Nightly
+ ## Pull the Codestral-22B-v0.1-GGUF model from the bartowski organization
+ cortex-nightly.exe pull bartowski/Codestral-22B-v0.1-GGUF
+
+ # Pull the gemma-7b model from the google organization
+ cortex-nightly.exe pull google/gemma-7b
+ ```
+
+
## ONNX

To view all available `ONNX` models on HuggingFace, select the `ONNX` tag in the Libraries section.
-```bash
-# Pull the XLM-Roberta-Large-Vit-B-16Plus model from the immich-app organization
-cortex pull immich-app/XLM-Roberta-Large-Vit-B-16Plus
+
+
+ ```sh
+ # Stable
+ ## Pull the XLM-Roberta-Large-Vit-B-16Plus model from the immich-app organization
+ cortex pull immich-app/XLM-Roberta-Large-Vit-B-16Plus
+
+ # Pull the mt0-base model from the bigscience organization
+ cortex pull bigscience/mt0-base
+
+ # Beta
+ ## Pull the XLM-Roberta-Large-Vit-B-16Plus model from the immich-app organization
+ cortex-beta pull immich-app/XLM-Roberta-Large-Vit-B-16Plus
+
+ # Pull the mt0-base model from the bigscience organization
+ cortex-beta pull bigscience/mt0-base
+
+ # Nightly
+ ## Pull the XLM-Roberta-Large-Vit-B-16Plus model from the immich-app organization
+ cortex-nightly pull immich-app/XLM-Roberta-Large-Vit-B-16Plus
+
+ # Pull the mt0-base model from the bigscience organization
+ cortex-nightly pull bigscience/mt0-base
+ ```
+
+
+ ```sh
+ # Stable
+ ## Pull the XLM-Roberta-Large-Vit-B-16Plus model from the immich-app organization
+ cortex.exe pull immich-app/XLM-Roberta-Large-Vit-B-16Plus
+
+ # Pull the mt0-base model from the bigscience organization
+ cortex.exe pull bigscience/mt0-base
+
+ # Beta
+ ## Pull the XLM-Roberta-Large-Vit-B-16Plus model from the immich-app organization
+ cortex-beta.exe pull immich-app/XLM-Roberta-Large-Vit-B-16Plus
-# Pull the mt0-base model from the bigscience organization
-cortex pull bigscience/mt0-base
+ # Pull the mt0-base model from the bigscience organization
+ cortex-beta.exe pull bigscience/mt0-base
+ # Nightly
+ ## Pull the XLM-Roberta-Large-Vit-B-16Plus model from the immich-app organization
+ cortex-nightly.exe pull immich-app/XLM-Roberta-Large-Vit-B-16Plus
-```
+ # Pull the mt0-base model from the bigscience organization
+ cortex-nightly.exe pull bigscience/mt0-base
+ ```
+
+
## TensorRT-LLM
We are still working to support all available `TensorRT-LLM` models on HuggingFace. For now, Cortex.cpp only supports built-in `TensorRT-LLM` models, which can be downloaded from the [Cortex Model Repos](/docs/hub/cortex-hub).
diff --git a/docs/installation/linux.mdx b/docs/installation/linux.mdx
index 186d0df..08cc975 100644
--- a/docs/installation/linux.mdx
+++ b/docs/installation/linux.mdx
@@ -13,19 +13,34 @@ import Admonition from '@theme/Admonition';
:::
## Cortex.cpp Installation
-Before installation, make sure that you have met the required [dependencies](#dependencies) and [hardware](#hardware) to run Cortex.
-### .deb
-- Stable: https://github.com/janhq/cortex.cpp/releases
-- Beta: https://github.com/janhq/cortex.cpp/releases
-- Nightly: https://github.com/janhq/cortex.cpp/releases
-
-### .appImage
-- Stable: https://github.com/janhq/cortex.cpp/releases
-- Beta: https://github.com/janhq/cortex.cpp/releases
-- Nightly: https://github.com/janhq/cortex.cpp/releases
+Cortex.cpp offers two installer types:
+- Network Installers download a minimal system and require an internet connection to fetch packages during installation.
+- Local Installers include all necessary packages, enabling offline installation without internet access.
:::info
-You can also install Cortex.cpp using the Cortex Installer available on [GitHub Releases](https://github.com/janhq/cortex/releases).
+Before installation, make sure that you have met the required [dependencies](#dependencies) and [hardware](#hardware) to run Cortex.
:::
+1. Download the Linux installer:
+ - `.deb`:
+ - Stable: https://github.com/janhq/cortex.cpp/releases
+ - Beta: https://github.com/janhq/cortex.cpp/releases
+ - Nightly: https://github.com/janhq/cortex.cpp/releases
+ - `.appImage`:
+ - Stable: https://github.com/janhq/cortex.cpp/releases
+ - Beta: https://github.com/janhq/cortex.cpp/releases
+ - Nightly: https://github.com/janhq/cortex.cpp/releases
+
+2. Ensure that Cortex.cpp is sucessfulyy installed:
+```bash
+# Stable
+cortex
+
+# Beta
+cortex-beta
+
+# Nightly
+cortex-nightly
+```
+
### Data Folder
By default, Cortex.cpp is installed in the following directory:
```
@@ -36,20 +51,17 @@ By default, Cortex.cpp is installed in the following directory:
/home//.cortexcpp
```
## Uninstall Cortex.cpp
-```sh
-# Uninstall Jan
-sudo apt-get remove cortexcpp
-
-# Remove all user data
-rm -rf ~/.cortexcpp
+Run the uninstaller script:
+```bash
+# Stable version
+sudo apt remove cortexcpp
-# Delete the application data
-rm -rf ~/.cortexrc
+# Beta version
+sudo apt remove cortexcpp-beta
+# Nightly version
+sudo apt remove cortexcpp-nightly
```
-:::info
-Delete the Cortex.cpp data folder located in your home folder.
-:::
## Build from Source
1. Clone the Cortex.cpp repository [here](https://github.com/janhq/cortex.cpp).
diff --git a/docs/installation/mac.mdx b/docs/installation/mac.mdx
index 44a22be..a198c2f 100644
--- a/docs/installation/mac.mdx
+++ b/docs/installation/mac.mdx
@@ -12,13 +12,28 @@ import TabItem from '@theme/TabItem';
:::
## Cortex.cpp Installation
-Before installation, make sure that you have met the required [dependencies](#dependencies) and [hardware](#hardware) to run Cortex.
-- Stable: https://github.com/janhq/cortex.cpp/releases
-- Beta: https://github.com/janhq/cortex.cpp/releases
-- Nightly: https://github.com/janhq/cortex.cpp/releases
+Cortex.cpp offers two installer types:
+- Network Installers download a minimal system and require an internet connection to fetch packages during installation.
+- Local Installers include all necessary packages, enabling offline installation without internet access.
:::info
-You can also install Cortex.cpp using the Cortex.cpp Installer available on [GitHub Releases](https://github.com/janhq/cortex/releases).
+Before installation, make sure that you have met the required [dependencies](#dependencies) and [hardware](#hardware) to run Cortex.
:::
+1. Download the MacOs installer:
+ - Stable: https://github.com/janhq/cortex.cpp/releases
+ - Beta: https://github.com/janhq/cortex.cpp/releases
+ - Nightly: https://github.com/janhq/cortex.cpp/releases
+2. Ensure that Cortex.cpp is sucessfulyy installed:
+```bash
+# Stable
+cortex
+
+# Beta
+cortex-beta
+
+# Nightly
+cortex-nightly
+```
+
### Data Folder
By default, Cortex.cpp is installed in the following directory:
```
@@ -29,23 +44,19 @@ By default, Cortex.cpp is installed in the following directory:
/Users//.cortexcpp
```
## Uninstall Cortex.cpp
-1. Open the Finder menu.
-2. Click the Applications option from the sidebar.
-3. Find the Jan app or type in the search bar.
-4. Use any of these ways to move the Jan app to the Trash:
- - Drag the app to the Trash.
- - Select the app and choose the Move to Trash option.
- - Select the app and press Command-Delete on your keyboard.
-5. Use the following command to delete Jan's user data and app cache:
+Run the uninstaller script:
```bash
-# Remove all user data
-rm -rf ~/.cortexcpp
+# Stable version
+sudo sh cortex-uninstall.sh
+
+# Beta version
+sudo sh cortex-beta-uninstall.sh
-# Delete the application data
-rm -rf ~/.cortexrc
+# Stable version
+sudo sh cortex-nightly-uninstall.sh
```
:::info
-Delete the Cortex.cpp data folder located in your home folder.
+The script requires sudo permission.
:::
## Build from Source
1. Clone the Cortex.cpp repository [here](https://github.com/janhq/cortex.cpp).
diff --git a/docs/installation/windows.mdx b/docs/installation/windows.mdx
index cdb76bb..11dce33 100644
--- a/docs/installation/windows.mdx
+++ b/docs/installation/windows.mdx
@@ -19,10 +19,15 @@ For Windows, Cortex.cpp can be installed in two ways:
## Windows
### Install Cortex.cpp
-Before installation, make sure that you have met the required [dependencies](#windows) and [hardware](#hardware) to run Cortex.
-- Stable:
-- Beta:
-- Nightly:
+Cortex.cpp offers two installer types:
+- Network Installers download a minimal system and require an internet connection to fetch packages during installation.
+- Local Installers include all necessary packages, enabling offline installation without internet access.
+:::info
+Before installation, make sure that you have met the required [dependencies](#dependencies) and [hardware](#hardware) to run Cortex.
+:::
+- Stable: https://github.com/janhq/cortex.cpp/releases
+- Beta: https://github.com/janhq/cortex.cpp/releases
+- Nightly: https://github.com/janhq/cortex.cpp/releases
#### Data Folder
By default, Cortex.cpp is installed in the following directory:
```
@@ -33,20 +38,35 @@ C:\Users\\AppData\Local\cortexcpp
C:\Users\\.cortexcpp
```
### Uninstall Cortex.cpp
-To uninstall Cortex.cpp, simply run the `uninstaller.exe` located in the binary data folder after installation.
-:::info
-Delete the Cortex.cpp data folder located in your home folder.
-:::
+To uninstall Cortex.cpp:
+1. Navigate to **Add or Remove program**.
+2. Search for Cortex.cpp and click **Uninstall**.
## Windows Subsystem Linux
:::info
Windows Subsystem Linux allows running Linux tools and workflows seamlessly alongside Windows applications. For more information, please see this [article](https://learn.microsoft.com/en-us/windows/wsl/faq).
:::
### Install Cortex.cpp
-Before installation, make sure that you have met the required [dependencies](#windows-subsystem-for-linux) and [hardware](#hardware) to run Cortex.
+Cortex.cpp offers two installer types:
+- Network Installers download a minimal system and require an internet connection to fetch packages during installation.
+- Local Installers include all necessary packages, enabling offline installation without internet access.
+:::info
+Before installation, make sure that you have met the required [dependencies](#dependencies) and [hardware](#hardware) to run Cortex.
+:::
+1. Download the Windows installer:
+ - Stable: https://github.com/janhq/cortex.cpp/releases
+ - Beta: https://github.com/janhq/cortex.cpp/releases
+ - Nightly: https://github.com/janhq/cortex.cpp/releases
+2. Ensure that Cortex.cpp is sucessfulyy installed:
+```bash
+# Stable
+cortex.exe
-- Stable: https://github.com/janhq/cortex.cpp/releases
-- Beta: https://github.com/janhq/cortex.cpp/releases
-- Nightly: https://github.com/janhq/cortex.cpp/releases
+# Beta
+cortex-beta.exe
+
+# Nightly
+cortex-nightly.exe
+```
#### Data Folder
By default, Cortex.cpp is installed in the following directory:
@@ -58,11 +78,17 @@ C:\Users\\AppData\Local\cortexcpp\cortex.exe
C:\Users\\.cortexcpp
```
### Uninstall Cortex.cpp
-To uninstall Cortex.cpp, simply run the `uninstaller.exe` located in the binary data folder after installation.
-:::info
-Delete the Cortex.cpp data folder located in your home folder.
-:::
+Run the uninstaller script:
+```bash
+# Stable version
+sudo apt remove cortexcpp
+# Beta version
+sudo apt remove cortexcpp-beta
+
+# Nightly version
+sudo apt remove cortexcpp-nightly
+```
## Build from Source
1. Clone the Cortex.cpp repository [here](https://github.com/janhq/cortex.cpp).
diff --git a/docs/overview.mdx b/docs/overview.mdx
index 36f36bb..25be18b 100644
--- a/docs/overview.mdx
+++ b/docs/overview.mdx
@@ -90,3 +90,13 @@ Cortex.cpp supports the following list of [Built-in Models](/models):
:::info
Cortex.cpp supports pulling `GGUF` and `ONNX` models from the [Hugging Face Hub](https://huggingface.co). Read how to [Pull models from Hugging Face](/docs/hub/hugging-face/)
:::
+
+## Cortex.cpp Versions
+Cortex.cpp offers three different versions of the app, each serving a unique purpose:
+- **Stable**: The official release version of Cortex.cpp, designed for general use with proven stability.
+- **Beta**: This version includes upcoming features still in testing, allowing users to try new functionality before the next official release.
+- **Nightly**: Automatically built every night, this version includes the latest updates and changes from the engineering team but may be unstable.
+
+:::info
+Each of these versions has a different CLI prefix command.
+:::
\ No newline at end of file
diff --git a/docs/quickstart.mdx b/docs/quickstart.mdx
index 5c59052..ee3b35d 100644
--- a/docs/quickstart.mdx
+++ b/docs/quickstart.mdx
@@ -21,23 +21,64 @@ To install Cortex, download the installer for your operating system from the fol
- [Linux (Fedora)](https://github.com/janhq/cortex.cpp/releases)
## Start Cortex.cpp Processes and API Server
This command starts the Cortex.cpp API server at `localhost:3928`.
-```sh
-cortex
-```
+
+
+ ```sh
+ # Stable
+ cortex start
+
+ # Beta
+ cortex-beta start
+
+ # Nightly
+ cortex-nightly start
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe start
+
+ # Beta
+ cortex-beta.exe start
+
+ # Nightly
+ cortex-nightly.exe start
+ ```
+
+
## Run a Model
-This command downloads the default `gguf` model format from the [Cortex Hub](https://huggingface.co/cortexso) and starts the model.
-```sh
-cortex run mistral
-```
+This command downloads the default `gguf` model format from the [Cortex Hub](https://huggingface.co/cortexso), starts the model, and chat with the model.
+
+
+ ```sh
+ # Stable
+ cortex run mistral
+
+ # Beta
+ cortex-beta run mistral
+
+ # Nightly
+ cortex-nightly run mistral
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe run mistral
+
+ # Beta
+ cortex-beta.exe run mistral
+
+ # Nightly
+ cortex-nightly.exe run mistral
+ ```
+
+
:::info
All model files are stored in the `~users/cortex/models` folder.
:::
## Using the Model
-### CLI
-```sh
-# CLI
-cortex chat mistral
-```
### API
```curl
curl http://localhost:3928/v1/chat/completions \
@@ -86,25 +127,137 @@ completion = client.chat.completions.create(
```
## Stop a Model
This command stops the running model.
- ```bash
-cortex models stop
-```
+
+
+ ```sh
+ # Stable
+ cortex models stop mistral
+
+ # Beta
+ cortex-beta models stop mistral
+
+ # Nightly
+ cortex-nightly models stop mistral
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe models stop mistral
+
+ # Beta
+ cortex-beta.exe models stop mistral
+
+ # Nightly
+ cortex-nightly.exe models stop mistral
+ ```
+
+
## Show the System State
This command displays the running model and the hardware system status.
- ```bash
-cortex ps
-```
+
+
+ ```sh
+ # Stable
+ cortex ps
+
+ # Beta
+ cortex-beta ps
+
+ # Nightly
+ cortex-nightly ps
+ ```
+
+
+ ```sh
+ # Stable
+ cortex.exe ps
+
+ # Beta
+ cortex-beta.exe ps
+
+ # Nightly
+ cortex-nightly.exe ps
+ ```
+
+
## Run Different Model Variants
-```bash
-# Run HuggingFace model with HuggingFace Repo
-cortex run TheBloke/Mistral-7B-Instruct-v0.2-GGUF
+
+
+ ```sh
+ # Stable
+ ## Run HuggingFace model with HuggingFace Repo
+ cortex run TheBloke/Mistral-7B-Instruct-v0.2-GGUF
-# Run Mistral in ONNX format
-cortex run mistral:onnx
+ # Run Mistral in ONNX format
+ cortex run mistral:onnx
-# Run Mistral in TensorRT-LLM format
-cortex run mistral:tensorrt-llm
-```
+ # Run Mistral in TensorRT-LLM format
+ cortex run mistral:tensorrt-llm
+
+ # Beta
+ ## Run HuggingFace model with HuggingFace Repo
+ cortex-beta run TheBloke/Mistral-7B-Instruct-v0.2-GGUF
+
+ # Run Mistral in ONNX format
+ cortex-beta run mistral:onnx
+
+ # Run Mistral in TensorRT-LLM format
+ cortex-beta run mistral:tensorrt-llm
+
+ # Nightly
+ ## Run HuggingFace model with HuggingFace Repo
+ cortex-nightly run TheBloke/Mistral-7B-Instruct-v0.2-GGUF
+
+ # Run Mistral in ONNX format
+ cortex-nightly run mistral:onnx
+
+ # Run Mistral in TensorRT-LLM format
+ cortex-nightly run mistral:tensorrt-llm
+ ```
+
+
+ ```sh
+ # Stable
+ ## Run HuggingFace model with HuggingFace Repo
+ cortex.exe run TheBloke/Mistral-7B-Instruct-v0.2-GGUF
+
+ # Run Mistral in ONNX format
+ cortex.exe run mistral:onnx
+
+ # Run Mistral in TensorRT-LLM format
+ cortex.exe run mistral:tensorrt-llm
+
+ # Beta
+ ## Run HuggingFace model with HuggingFace Repo
+ cortex-beta.exe run TheBloke/Mistral-7B-Instruct-v0.2-GGUF
+
+ # Run Mistral in ONNX format
+ cortex-beta.exe run mistral:onnx
+
+ # Run Mistral in TensorRT-LLM format
+ cortex-beta.exe run mistral:tensorrt-llm
+
+ # Nightly
+ ## Run HuggingFace model with HuggingFace Repo
+ cortex-nightly.exe run TheBloke/Mistral-7B-Instruct-v0.2-GGUF
+
+ # Run Mistral in ONNX format
+ cortex-nightly.exe run mistral:onnx
+
+ # Run Mistral in TensorRT-LLM format
+ cortex-nightly.exe run mistral:tensorrt-llm
+ ```
+
+
+
+## What's Next?
+Now that Cortex.cpp is set up, here are the next steps to explore:
+
+1. Adjust the folder path and configuration using the [`.cortexrc`](/docs/basic-usage/cortexrc) file.
+2. Explore the Cortex.cpp [data folder](/docs/data-folder) to understand how it stores data.
+3. Learn about the structure of the [`model.yaml`](/docs/model-yaml) file in Cortex.cpp.
+4. Integrate Cortex.cpp [libraries](/docs/category/libraries) seamlessly into your Python or JavaScript applications.
:::info
diff --git a/docs/troubleshooting.mdx b/docs/troubleshooting.mdx
index a437ad4..1b38a85 100644
--- a/docs/troubleshooting.mdx
+++ b/docs/troubleshooting.mdx
@@ -129,7 +129,7 @@ To resolve this issue:
## 426 Error Code
-This issue occurs when a new Cortex process is started without fully stopping the previous Cortex processes. This causes a heavy load on port `1337` and requires a protocol upgrade.
+This issue occurs when a new Cortex process is started without fully stopping the previous Cortex processes. This causes a heavy load on port `3928` and requires a protocol upgrade.
To resolve this issue:
diff --git a/sidebars.ts b/sidebars.ts
index 04490e6..43c91dc 100644
--- a/sidebars.ts
+++ b/sidebars.ts
@@ -50,9 +50,19 @@ const sidebars: SidebarsConfig = {
},
],
},
+ {
+ type: "html",
+ value: "BASIC USAGE",
+
+ className: "sidebar-divider",
+ },
+ { type: "doc", id: "basic-usage/overview", label: "Overview" },
+ { type: "doc", id: "basic-usage/cortexrc", label: ".cortexrc" },
+ { type: "doc", id: "model-yaml", label: "model.yaml" },
+ { type: "doc", id: "data-folder", label: "Data Folder" },
{
type: "category",
- label: "Integration",
+ label: "Libraries",
link: {
type: "generated-index",
},
@@ -70,7 +80,21 @@ const sidebars: SidebarsConfig = {
},
],
},
- { type: "doc", id: "data-structures", label: "Data Structures" },
+ {
+ type: "category",
+ label: "Model Sources",
+ link: { type: "doc", id: "hub/index" },
+ collapsed: true,
+ items: [
+ { type: "doc", id: "hub/cortex-hub", label: "Cortex Model Repos" },
+ { type: "doc", id: "hub/hugging-face", label: "HuggingFace Repos" },
+ {
+ type: "doc",
+ id: "hub/nvidia-ngc",
+ label: "Nvidia Catalog (Coming Soon)",
+ },
+ ],
+ },
// {
// type: "category",
// label: "Basic Usage",
@@ -105,13 +129,13 @@ const sidebars: SidebarsConfig = {
// },
// { type: "doc", id: "telemetry", label: "Telemetry" },
// MODELs
- {
- type: "html",
- value: "MODELS",
- className: "sidebar-divider",
- },
- { type: "doc", id: "model-overview", label: "Overview" },
- { type: "doc", id: "model-yaml", label: "model.yaml" },
+ // {
+ // type: "html",
+ // value: "MODELS",
+ // className: "sidebar-divider",
+ // },
+ // { type: "doc", id: "model-overview", label: "Overview" },
+ // { type: "doc", id: "model-yaml", label: "model.yaml" },
// { type: "doc", id: "built-in-models", label: "Built-in Models" },
// {
// type: "category",
@@ -135,21 +159,6 @@ const sidebars: SidebarsConfig = {
// { type: "doc", id: "formats/onnx", label: "ONNX" },
// ],
// },
- {
- type: "category",
- label: "Model Sources",
- link: { type: "doc", id: "hub/index" },
- collapsed: true,
- items: [
- { type: "doc", id: "hub/cortex-hub", label: "Cortex Model Repos" },
- { type: "doc", id: "hub/hugging-face", label: "HuggingFace Repos" },
- {
- type: "doc",
- id: "hub/nvidia-ngc",
- label: "Nvidia Catalog (Coming Soon)",
- },
- ],
- },
// BASIC USAGE
// {
// type: "html",
@@ -175,6 +184,7 @@ const sidebars: SidebarsConfig = {
className: "sidebar-divider",
},
{ type: "doc", id: "cli/cortex", label: "cortex" },
+ { type: "doc", id: "cli/start", label: "cortex start" },
{ type: "doc", id: "cli/chat", label: "cortex chat" },
{ type: "doc", id: "cli/embeddings", label: "cortex embeddings" },
// { type: "doc", id: "cli/presets", label: "cortex presets" },