@@ -35,7 +35,7 @@ Cortex is the open-source brain for robots: vision, speech, language, tabular, a
All other Linux distributions:
```bash
-curl -s https://raw.githubusercontent.com/janhq/cortex/main/engine/templates/linux/install.sh | sudo bash
+curl -s https://raw.githubusercontent.com/menloresearch/cortex/main/engine/templates/linux/install.sh | sudo bash
```
### Start the Server
@@ -144,7 +144,7 @@ cortex-nightly hardware activate
- Quick troubleshooting: `cortex --help`
- [Documentation](https://cortex.so/docs)
- [Community Discord](https://discord.gg/FTk2MvZwJH)
-- [Report Issues](https://github.com/janhq/cortex.cpp/issues)
+- [Report Issues](https://github.com/menloresearch/cortex.cpp/issues)
---
@@ -182,6 +182,6 @@ The script to uninstall Cortex comes with the binary and was added to the `/usr/
## Contact Support
-- For support, please file a [GitHub ticket](https://github.com/janhq/cortex.cpp/issues/new/choose).
+- For support, please file a [GitHub ticket](https://github.com/menloresearch/cortex.cpp/issues/new/choose).
- For questions, join our Discord [here](https://discord.gg/FTk2MvZwJH).
- For long-form inquiries, please email [hello@jan.ai](mailto:hello@jan.ai).
\ No newline at end of file
diff --git a/docker/README.md b/docker/README.md
index 89b5c3365..2f0022afb 100644
--- a/docker/README.md
+++ b/docker/README.md
@@ -25,7 +25,7 @@ docker pull menloltd/cortex:nightly-1.0.1-224
- Build and Run Cortex Docker Container from Dockerfile
```bash
-git clone https://github.com/janhq/cortex.cpp.git
+git clone https://github.com/menloresearch/cortex.cpp.git
cd cortex.cpp
git submodule update --init
diff --git a/docker/download-cortex.llamacpp.sh b/docker/download-cortex.llamacpp.sh
index 8e6a15df2..51471c342 100644
--- a/docker/download-cortex.llamacpp.sh
+++ b/docker/download-cortex.llamacpp.sh
@@ -4,7 +4,7 @@ VERSION=${1:-latest}
# Get the latest version of the cortex.llamacpp
if [ "$VERSION" = "latest" ]; then
- VERSION=$(curl -s https://api.github.com/repos/janhq/cortex.llamacpp/releases/latest | jq -r '.tag_name' | sed 's/^v//');
+ VERSION=$(curl -s https://api.github.com/repos/menloresearch/cortex.llamacpp/releases/latest | jq -r '.tag_name' | sed 's/^v//');
fi
# Create the directory to store the cortex.llamacpp
@@ -13,18 +13,18 @@ cd /opt/cortex.llamacpp
# Download the cortex.llamacpp engines
echo -e "Downloading Cortex Llama version $VERSION"
-wget https://github.com/janhq/cortex.llamacpp/releases/download/v$VERSION/cortex.llamacpp-$VERSION-linux-amd64-avx-cuda-11-7.tar.gz
-wget https://github.com/janhq/cortex.llamacpp/releases/download/v$VERSION/cortex.llamacpp-$VERSION-linux-amd64-avx-cuda-12-0.tar.gz
-wget https://github.com/janhq/cortex.llamacpp/releases/download/v$VERSION/cortex.llamacpp-$VERSION-linux-amd64-avx.tar.gz
-wget https://github.com/janhq/cortex.llamacpp/releases/download/v$VERSION/cortex.llamacpp-$VERSION-linux-amd64-avx2-cuda-11-7.tar.gz
-wget https://github.com/janhq/cortex.llamacpp/releases/download/v$VERSION/cortex.llamacpp-$VERSION-linux-amd64-avx2-cuda-12-0.tar.gz
-wget https://github.com/janhq/cortex.llamacpp/releases/download/v$VERSION/cortex.llamacpp-$VERSION-linux-amd64-avx2.tar.gz
-wget https://github.com/janhq/cortex.llamacpp/releases/download/v$VERSION/cortex.llamacpp-$VERSION-linux-amd64-avx512-cuda-11-7.tar.gz
-wget https://github.com/janhq/cortex.llamacpp/releases/download/v$VERSION/cortex.llamacpp-$VERSION-linux-amd64-avx512-cuda-12-0.tar.gz
-wget https://github.com/janhq/cortex.llamacpp/releases/download/v$VERSION/cortex.llamacpp-$VERSION-linux-amd64-avx512.tar.gz
-wget https://github.com/janhq/cortex.llamacpp/releases/download/v$VERSION/cortex.llamacpp-$VERSION-linux-amd64-noavx-cuda-11-7.tar.gz
-wget https://github.com/janhq/cortex.llamacpp/releases/download/v$VERSION/cortex.llamacpp-$VERSION-linux-amd64-noavx-cuda-12-0.tar.gz
-wget https://github.com/janhq/cortex.llamacpp/releases/download/v$VERSION/cortex.llamacpp-$VERSION-linux-amd64-noavx.tar.gz
-wget https://github.com/janhq/cortex.llamacpp/releases/download/v$VERSION/cortex.llamacpp-$VERSION-linux-amd64-vulkan.tar.gz
-wget https://github.com/janhq/cortex.llamacpp/releases/download/v$VERSION/cuda-11-7-linux-amd64.tar.gz
-wget https://github.com/janhq/cortex.llamacpp/releases/download/v$VERSION/cuda-12-0-linux-amd64.tar.gz
\ No newline at end of file
+wget https://github.com/menloresearch/cortex.llamacpp/releases/download/v$VERSION/cortex.llamacpp-$VERSION-linux-amd64-avx-cuda-11-7.tar.gz
+wget https://github.com/menloresearch/cortex.llamacpp/releases/download/v$VERSION/cortex.llamacpp-$VERSION-linux-amd64-avx-cuda-12-0.tar.gz
+wget https://github.com/menloresearch/cortex.llamacpp/releases/download/v$VERSION/cortex.llamacpp-$VERSION-linux-amd64-avx.tar.gz
+wget https://github.com/menloresearch/cortex.llamacpp/releases/download/v$VERSION/cortex.llamacpp-$VERSION-linux-amd64-avx2-cuda-11-7.tar.gz
+wget https://github.com/menloresearch/cortex.llamacpp/releases/download/v$VERSION/cortex.llamacpp-$VERSION-linux-amd64-avx2-cuda-12-0.tar.gz
+wget https://github.com/menloresearch/cortex.llamacpp/releases/download/v$VERSION/cortex.llamacpp-$VERSION-linux-amd64-avx2.tar.gz
+wget https://github.com/menloresearch/cortex.llamacpp/releases/download/v$VERSION/cortex.llamacpp-$VERSION-linux-amd64-avx512-cuda-11-7.tar.gz
+wget https://github.com/menloresearch/cortex.llamacpp/releases/download/v$VERSION/cortex.llamacpp-$VERSION-linux-amd64-avx512-cuda-12-0.tar.gz
+wget https://github.com/menloresearch/cortex.llamacpp/releases/download/v$VERSION/cortex.llamacpp-$VERSION-linux-amd64-avx512.tar.gz
+wget https://github.com/menloresearch/cortex.llamacpp/releases/download/v$VERSION/cortex.llamacpp-$VERSION-linux-amd64-noavx-cuda-11-7.tar.gz
+wget https://github.com/menloresearch/cortex.llamacpp/releases/download/v$VERSION/cortex.llamacpp-$VERSION-linux-amd64-noavx-cuda-12-0.tar.gz
+wget https://github.com/menloresearch/cortex.llamacpp/releases/download/v$VERSION/cortex.llamacpp-$VERSION-linux-amd64-noavx.tar.gz
+wget https://github.com/menloresearch/cortex.llamacpp/releases/download/v$VERSION/cortex.llamacpp-$VERSION-linux-amd64-vulkan.tar.gz
+wget https://github.com/menloresearch/cortex.llamacpp/releases/download/v$VERSION/cuda-11-7-linux-amd64.tar.gz
+wget https://github.com/menloresearch/cortex.llamacpp/releases/download/v$VERSION/cuda-12-0-linux-amd64.tar.gz
\ No newline at end of file
diff --git a/docs/docs/architecture/cortex-db.mdx b/docs/docs/architecture/cortex-db.mdx
index 6182c74f4..42583825d 100644
--- a/docs/docs/architecture/cortex-db.mdx
+++ b/docs/docs/architecture/cortex-db.mdx
@@ -23,7 +23,6 @@ The `schema_version` table is designed to hold schema version for cortex databas
|--------------------|-----------|---------------------------------------------------------|
| version | INTEGER | A unique schema version for database. |
-
### models Table
The `models` table is designed to hold metadata about various AI models. Below is the structure of the table:
diff --git a/docs/docs/basic-usage/cortex-js.md b/docs/docs/basic-usage/cortex-js.md
index 698e9e011..fbd687e6d 100644
--- a/docs/docs/basic-usage/cortex-js.md
+++ b/docs/docs/basic-usage/cortex-js.md
@@ -7,7 +7,7 @@ description: How to use the Cortex.js Library
🚧 Cortex.js is currently under development, and this page is a stub for future development.
:::
-[Cortex.js](https://github.com/janhq/cortex.js) is a Typescript client library that can be used to
+[Cortex.js](https://github.com/menloresearch/cortex.js) is a Typescript client library that can be used to
interact with the Cortex API. It is a fork of the OpenAI Typescript library with additional methods for Local AI.
This is still a work in progress, and we will let the community know once a stable version is available.
@@ -20,7 +20,7 @@ Cortex.cpp can be used in a Typescript application with the `cortex.js` library.
## Installation
```ts
-npm install @janhq/cortexso-node
+npm install @menloresearch/cortexso-node
```
## Usage
@@ -29,7 +29,7 @@ npm install @janhq/cortexso-node
```diff
- import OpenAI from 'openai';
-+ import Cortex from '@janhq/cortexso-node';
++ import Cortex from '@menloresearch/cortexso-node';
```
2. Modify the initialization of the client to use Cortex.cpp:
@@ -46,7 +46,7 @@ npm install @janhq/cortexso-node
### Example Usage
```js
-import Cortex from "@janhq/cortexso-node";
+import Cortex from "@menloresearch/cortexso-node";
async function inference() {
const cortex = new Cortex({
diff --git a/docs/docs/basic-usage/cortex-py.md b/docs/docs/basic-usage/cortex-py.md
index cdc540d71..55a5b0340 100644
--- a/docs/docs/basic-usage/cortex-py.md
+++ b/docs/docs/basic-usage/cortex-py.md
@@ -17,7 +17,7 @@ Cortex.cpp can be used in a Python application with the `cortex.py` library. Cor
## Installation
```py
-pip install @janhq/cortex-python
+pip install @menloresearch/cortex-python
```
## Usage
@@ -26,7 +26,7 @@ pip install @janhq/cortex-python
```diff
- from openai import OpenAI
-+ from @janhq/cortex-python import Cortex
++ from @menloresearch/cortex-python import Cortex
```
2. Modify the initialization of the client to use Cortex.cpp:
@@ -40,7 +40,7 @@ pip install @janhq/cortex-python
### Example Usage
```py
-from @janhq/cortex-python import Cortex
+from @menloresearch/cortex-python import Cortex
client = OpenAI(base_url="http://localhost:3928", api_key="cortex")
diff --git a/docs/docs/cortex-llamacpp.mdx b/docs/docs/cortex-llamacpp.mdx
index db2085eb0..50c1bf880 100644
--- a/docs/docs/cortex-llamacpp.mdx
+++ b/docs/docs/cortex-llamacpp.mdx
@@ -77,7 +77,7 @@ The command will check, download, and install these dependencies:
:::info
-To include `llamacpp` in your own server implementation, follow the steps [here](https://github.com/janhq/llamacpp/tree/main/examples/server).
+To include `llamacpp` in your own server implementation, follow the steps [here](https://github.com/menloresearch/llamacpp/tree/main/examples/server).
:::
#### Get GGUF Models
@@ -184,5 +184,5 @@ The future plans for `llamacpp` are focused on enhancing performance and expandi
- **Multimodal Model Compatibility**: Expanding support to include a variety of multimodal models, enabling a broader range of applications and use cases.
:::info
-To follow the latest developments of `llamacpp`, please see the [GitHub Repository](https://github.com/janhq/llamacpp).
+To follow the latest developments of `llamacpp`, please see the [GitHub Repository](https://github.com/menloresearch/llamacpp).
:::
diff --git a/docs/docs/cortex-onnx.mdx b/docs/docs/cortex-onnx.mdx
index 1720c6e3a..b7e363b9a 100644
--- a/docs/docs/cortex-onnx.mdx
+++ b/docs/docs/cortex-onnx.mdx
@@ -40,7 +40,7 @@ The command will check, download, and install these dependencies for Windows:
- vcruntime140_1.dll
```
:::info
-To include `onnx` in your own server implementation, follow the steps [here](https://github.com/janhq/onnx/tree/main/examples/server).
+To include `onnx` in your own server implementation, follow the steps [here](https://github.com/menloresearch/onnx/tree/main/examples/server).
:::
#### Get ONNX Models
diff --git a/docs/docs/cortex-tensorrt-llm.mdx b/docs/docs/cortex-tensorrt-llm.mdx
index c6dc1859d..36269c9dc 100644
--- a/docs/docs/cortex-tensorrt-llm.mdx
+++ b/docs/docs/cortex-tensorrt-llm.mdx
@@ -13,7 +13,7 @@ import TabItem from "@theme/TabItem";
## Introduction
-[Cortex.tensorrt-llm](https://github.com/janhq/tensorrt-llm) is a C++ inference library for NVIDIA GPUs. It submodules NVIDIA’s [TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM) for GPU accelerated inference.
+[Cortex.tensorrt-llm](https://github.com/menloresearch/tensorrt-llm) is a C++ inference library for NVIDIA GPUs. It submodules NVIDIA’s [TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM) for GPU accelerated inference.
In addition to TensorRT-LLM, `tensorrt-llm` adds:
@@ -58,7 +58,7 @@ The command will check, download, and install these dependencies:
:::info
-To include `tensorrt-llm` in your own server implementation, follow the steps [here](https://github.com/janhq/tensorrt-llm/tree/rel).
+To include `tensorrt-llm` in your own server implementation, follow the steps [here](https://github.com/menloresearch/tensorrt-llm/tree/rel).
:::
#### Get TensorRT-LLM Models
diff --git a/docs/docs/engines/engine-extension.mdx b/docs/docs/engines/engine-extension.mdx
index 6bb966f60..d2edde830 100644
--- a/docs/docs/engines/engine-extension.mdx
+++ b/docs/docs/engines/engine-extension.mdx
@@ -163,7 +163,7 @@ Please ensure all dependencies are included with your dynamic library. This allo
#### 4.1 Publishing Your Engine (Optional)
-If you wish to make your engine publicly available, you can publish it through GitHub. For reference, examine the [cortex.llamacpp releases](https://github.com/janhq/cortex.llamacpp/releases) structure:
+If you wish to make your engine publicly available, you can publish it through GitHub. For reference, examine the [cortex.llamacpp releases](https://github.com/menloresearch/cortex.llamacpp/releases) structure:
- Each release tag should represent your version
- Include all variants within the same release
diff --git a/docs/docs/engines/python-engine.mdx b/docs/docs/engines/python-engine.mdx
index 64996406d..5839a346c 100644
--- a/docs/docs/engines/python-engine.mdx
+++ b/docs/docs/engines/python-engine.mdx
@@ -75,7 +75,7 @@ extra_params:
## Example: Ichigo Python Model
-[Ichigo python](https://github.com/janhq/ichigo) is a built-in Cortex model for chat with audio support.
+[Ichigo python](https://github.com/menloresearch/ichigo) is a built-in Cortex model for chat with audio support.
### Required Models
@@ -240,7 +240,7 @@ if __name__ == "__main__":
1. Create model files following the example above
2. Add required `requirements.txt` and `requirements.cuda.txt` files
-3. Trigger the [Python Script Package CI](https://github.com/janhq/cortex.cpp/actions/workflows/python-script-package.yml)
-4. Trigger the [Python Venv Package CI](https://github.com/janhq/cortex.cpp/actions/workflows/python-venv-package.yml)
+3. Trigger the [Python Script Package CI](https://github.com/menloresearch/cortex.cpp/actions/workflows/python-script-package.yml)
+4. Trigger the [Python Venv Package CI](https://github.com/menloresearch/cortex.cpp/actions/workflows/python-venv-package.yml)
The CIs will build and publish your model to Hugging Face where it can then be downloaded and used.
diff --git a/docs/docs/guides/function-calling.md b/docs/docs/guides/function-calling.md
index 387cf9b89..6b9157f18 100644
--- a/docs/docs/guides/function-calling.md
+++ b/docs/docs/guides/function-calling.md
@@ -318,5 +318,5 @@ Use enums to improve function accuracy:
- Function calling accuracy depends on model quality. Smaller models (8B-12B) work best with simple use cases.
- Cortex.cpp implements function calling through prompt engineering, injecting system prompts when tools are specified.
- Best compatibility with llama3.1 and derivatives (mistral-nemo, qwen)
-- System prompts can be customized for specific use cases (see [implementation details](https://github.com/janhq/cortex.cpp/pull/1472/files))
-- For complete implementation examples, refer to our [detailed guide](https://github.com/janhq/models/issues/16#issuecomment-2381129322)
+- System prompts can be customized for specific use cases (see [implementation details](https://github.com/menloresearch/cortex.cpp/pull/1472/files))
+- For complete implementation examples, refer to our [detailed guide](https://github.com/menloresearch/models/issues/16#issuecomment-2381129322)
diff --git a/docs/docs/installation.mdx b/docs/docs/installation.mdx
index acee4d5d0..fe1910d1b 100644
--- a/docs/docs/installation.mdx
+++ b/docs/docs/installation.mdx
@@ -32,7 +32,7 @@ For more information, please check out the [different channels](#different-chann
| **Local** | **Stable** | **MacOS** | [Download](https://app.cortexcpp.com/download/latest/mac-universal-local) |
:::info
-For other versions, please look at [cortex.cpp repo](https://github.com/janhq/cortex.cpp) or each installer page.
+For other versions, please look at [cortex.cpp repo](https://github.com/menloresearch/cortex.cpp) or each installer page.
:::
diff --git a/docs/docs/installation/docker.mdx b/docs/docs/installation/docker.mdx
index ffc485962..0a582f22f 100644
--- a/docs/docs/installation/docker.mdx
+++ b/docs/docs/installation/docker.mdx
@@ -59,7 +59,7 @@ docker pull menloltd/cortex:nightly-1.0.1-224
1. **Clone the repo:**
```bash
-git clone https://github.com/janhq/cortex.cpp.git
+git clone https://github.com/menloresearch/cortex.cpp.git
cd cortex.cpp
git submodule update --init
```
diff --git a/docs/docs/installation/linux.mdx b/docs/docs/installation/linux.mdx
index a45c9cefe..debcbce1b 100644
--- a/docs/docs/installation/linux.mdx
+++ b/docs/docs/installation/linux.mdx
@@ -27,12 +27,12 @@ This instruction is for stable releases. For beta and nightly releases, please r
- Network installer for all linux distros
```bash
- curl -s https://raw.githubusercontent.com/janhq/cortex/main/engine/templates/linux/install.sh | sudo bash -s
+ curl -s https://raw.githubusercontent.com/menloresearch/cortex/main/engine/templates/linux/install.sh | sudo bash -s
```
- Local installer for Debian-based distros
```bash
- curl -s https://raw.githubusercontent.com/janhq/cortex/main/engine/templates/linux/install.sh | sudo bash -s -- --deb_local
+ curl -s https://raw.githubusercontent.com/menloresearch/cortex/main/engine/templates/linux/install.sh | sudo bash -s -- --deb_local
```
- Parameters
@@ -83,7 +83,7 @@ sudo /usr/bin/cortex-uninstall.sh
1. **Clone the Cortex Repository**
```bash
- git clone https://github.com/janhq/cortex.cpp.git
+ git clone https://github.com/menloresearch/cortex.cpp.git
cd cortex.cpp
git submodule update --init
```
diff --git a/docs/docs/installation/mac.mdx b/docs/docs/installation/mac.mdx
index b1e8b5e2b..646a30571 100644
--- a/docs/docs/installation/mac.mdx
+++ b/docs/docs/installation/mac.mdx
@@ -13,7 +13,7 @@ The instructions below are for stable releases only. For beta and nightly releas
:::
1. Download the Linux installer:
-- From release: https://github.com/janhq/cortex.cpp/releases
+- From release: https://github.com/menloresearch/cortex.cpp/releases
- From quick download links:
- Local installer `.deb`:
- Stable: https://app.cortexcpp.com/download/latest/mac-universal-local
@@ -80,7 +80,7 @@ The script requires sudo permission.
1. **Clone the Cortex Repository**
```bash
- git clone https://github.com/janhq/cortex.cpp.git
+ git clone https://github.com/menloresearch/cortex.cpp.git
cd cortex.cpp
git submodule update --init
```
diff --git a/docs/docs/installation/windows.mdx b/docs/docs/installation/windows.mdx
index f49fe2c78..eeb3c3be1 100644
--- a/docs/docs/installation/windows.mdx
+++ b/docs/docs/installation/windows.mdx
@@ -21,7 +21,7 @@ and `cortex-nightly`, respectively.
:::
Download the windows installer:
-- From release: https://github.com/janhq/cortex.cpp/releases
+- From release: https://github.com/menloresearch/cortex.cpp/releases
- From quick download links:
- Local installer `.deb`:
- Stable: https://app.cortexcpp.com/download/latest/windows-amd64-local
@@ -77,7 +77,7 @@ Follow the [linux installation steps](linux) to install Cortex.cpp on the WSL.
1. **Clone the Cortex Repository**
```cmd
- git clone https://github.com/janhq/cortex.cpp.git
+ git clone https://github.com/menloresearch/cortex.cpp.git
cd cortex.cpp
git submodule update --init
```
diff --git a/docs/docs/overview.mdx b/docs/docs/overview.mdx
index 4a00b55ba..4d983d937 100644
--- a/docs/docs/overview.mdx
+++ b/docs/docs/overview.mdx
@@ -17,7 +17,7 @@ Key Features:
- Full C++ implementation, packageable into Desktop and Mobile apps
- Pull from Huggingface, or Cortex Built-in Model Library
- Models stored in universal file formats (vs blobs)
-- Swappable Inference Backends (default: [`llamacpp`](https://github.com/janhq/cortex.llamacpp) and [`ONNXRuntime`](https://github.com/janhq/cortex.onnx))
+- Swappable Inference Backends (default: [`llamacpp`](https://github.com/menloresearch/cortex.llamacpp) and [`ONNXRuntime`](https://github.com/menloresearch/cortex.onnx))
- Cortex can be deployed as a standalone API server, or integrated into apps like [Jan.ai](https://jan.ai/)
- Automatic API docs for your server
diff --git a/docs/docusaurus.config.ts b/docs/docusaurus.config.ts
index 659e155d7..6e7820088 100644
--- a/docs/docusaurus.config.ts
+++ b/docs/docusaurus.config.ts
@@ -214,7 +214,7 @@ const config: Config = {
async contentLoaded({ content, actions }) {
const { setGlobalData } = actions;
const fetchRepoInfo = await fetch(
- "https://api.github.com/repos/janhq/cortex.cpp"
+ "https://api.github.com/repos/menloresearch/cortex.cpp"
);
const repoInfo = await fetchRepoInfo.json();
setGlobalData(repoInfo);
@@ -227,7 +227,7 @@ const config: Config = {
async contentLoaded({ content, actions }) {
const { setGlobalData } = actions;
const fetchLatestRelease = await fetch(
- "https://api.github.com/repos/janhq/cortex.cpp/releases/latest"
+ "https://api.github.com/repos/menloresearch/cortex.cpp/releases/latest"
);
const latestRelease = await fetchLatestRelease.json();
setGlobalData(latestRelease);
@@ -310,7 +310,7 @@ const config: Config = {
// GitHub pages deployment config.
// If you aren't using GitHub pages, you don't need these.
- organizationName: "janhq", // Usually your GitHub org/user name.
+ organizationName: "menloresearch", // Usually your GitHub org/user name.
projectName: "cortex", // Usually your repo name.
onBrokenLinks: "throw",
@@ -342,7 +342,7 @@ const config: Config = {
sidebarPath: "./sidebars.ts",
// Please change this to your repo.
// Remove this to remove the "edit this page" links.
- editUrl: "https://github.com/janhq/cortex.cpp/blob/dev/docs/",
+ editUrl: "https://github.com/menloresearch/cortex.cpp/blob/dev/docs/",
},
sitemap: {
changefreq: "daily",
@@ -451,7 +451,7 @@ const config: Config = {
items: [
{
label: "Github",
- href: "https://github.com/janhq/cortex.cpp",
+ href: "https://github.com/menloresearch/cortex.cpp",
},
{
label: "Discord",
diff --git a/docs/src/components/Announcement/index.tsx b/docs/src/components/Announcement/index.tsx
index 31761a152..35e8d525f 100644
--- a/docs/src/components/Announcement/index.tsx
+++ b/docs/src/components/Announcement/index.tsx
@@ -7,7 +7,7 @@ const Announcement = () => {
🎉
-
+
{" "}
Cortex.cpp v1.0 is now live on GitHub. Check it out!
diff --git a/docs/src/components/SocialNavbar/index.tsx b/docs/src/components/SocialNavbar/index.tsx
index efb9ed738..64ae08dc1 100644
--- a/docs/src/components/SocialNavbar/index.tsx
+++ b/docs/src/components/SocialNavbar/index.tsx
@@ -14,7 +14,7 @@ const SocialNavbar = () => {
diff --git a/docs/src/containers/Homepage/Download/CardDownload.tsx b/docs/src/containers/Homepage/Download/CardDownload.tsx
index b02a481fd..2f1512382 100644
--- a/docs/src/containers/Homepage/Download/CardDownload.tsx
+++ b/docs/src/containers/Homepage/Download/CardDownload.tsx
@@ -85,7 +85,7 @@ export default function CardDownload({ lastRelease }: Props) {
.replace("{tag}", tag);
return {
...system,
- href: `https://github.com/janhq/cortex/releases/download/${lastRelease.tag_name}/${downloadUrl}`,
+ href: `https://github.com/menloresearch/cortex/releases/download/${lastRelease.tag_name}/${downloadUrl}`,
};
});
diff --git a/docs/static/huggingface/hub.json b/docs/static/huggingface/hub.json
index 20eea4a0a..d7718974b 100644
--- a/docs/static/huggingface/hub.json
+++ b/docs/static/huggingface/hub.json
@@ -11,7 +11,7 @@
{
"url": "https://huggingface.co/bartowski/Mistral-7B-Instruct-v0.3-GGUF/blob/main/Mistral-7B-Instruct-v0.3-Q4_K_M.gguf",
"author": "Mistral AI",
- "logo": "https://raw.githubusercontent.com/janhq/cortex-web/main/static/img/logos/mistral.svg",
+ "logo": "https://raw.githubusercontent.com/menloresearch/cortex-web/main/static/img/logos/mistral.svg",
"model_name": "Mistral 7B Instruct v0.3 Q4_K_M GGUF",
"note": "Small + Chat"
},
diff --git a/docs/static/openapi/cortex.json b/docs/static/openapi/cortex.json
index 8f378a83f..23970ef51 100644
--- a/docs/static/openapi/cortex.json
+++ b/docs/static/openapi/cortex.json
@@ -77,7 +77,9 @@
"oneOf": [
{
"type": "string",
- "enum": ["auto"]
+ "enum": [
+ "auto"
+ ]
},
{
"type": "object"
@@ -85,7 +87,9 @@
]
}
},
- "required": ["model"]
+ "required": [
+ "model"
+ ]
}
}
}
@@ -104,7 +108,9 @@
},
"object": {
"type": "string",
- "enum": ["assistant"],
+ "enum": [
+ "assistant"
+ ],
"description": "The object type, which is always 'assistant'."
},
"created_at": {
@@ -175,7 +181,9 @@
"oneOf": [
{
"type": "string",
- "enum": ["auto"]
+ "enum": [
+ "auto"
+ ]
},
{
"type": "object"
@@ -195,7 +203,9 @@
}
}
},
- "tags": ["Assistants"]
+ "tags": [
+ "Assistants"
+ ]
},
"patch": {
"operationId": "AssistantsController_update",
@@ -218,7 +228,9 @@
"description": "Beta feature header.",
"schema": {
"type": "string",
- "enum": ["assistants=v2"]
+ "enum": [
+ "assistants=v2"
+ ]
}
}
],
@@ -293,7 +305,9 @@
"oneOf": [
{
"type": "string",
- "enum": ["auto"]
+ "enum": [
+ "auto"
+ ]
},
{
"type": "object"
@@ -320,7 +334,9 @@
},
"object": {
"type": "string",
- "enum": ["assistant"],
+ "enum": [
+ "assistant"
+ ],
"description": "The object type, which is always 'assistant'."
},
"created_at": {
@@ -391,7 +407,9 @@
"oneOf": [
{
"type": "string",
- "enum": ["auto"]
+ "enum": [
+ "auto"
+ ]
},
{
"type": "object"
@@ -411,7 +429,9 @@
}
}
},
- "tags": ["Assistants"]
+ "tags": [
+ "Assistants"
+ ]
},
"get": {
"operationId": "AssistantsController_list",
@@ -427,7 +447,9 @@
"properties": {
"object": {
"type": "string",
- "enum": ["list"],
+ "enum": [
+ "list"
+ ],
"description": "The object type, which is always 'list' for a list response."
},
"data": {
@@ -441,7 +463,9 @@
},
"object": {
"type": "string",
- "enum": ["assistant"],
+ "enum": [
+ "assistant"
+ ],
"description": "The object type, which is always 'assistant'."
},
"created_at": {
@@ -468,13 +492,18 @@
}
}
},
- "required": ["object", "data"]
+ "required": [
+ "object",
+ "data"
+ ]
}
}
}
}
},
- "tags": ["Assistants"]
+ "tags": [
+ "Assistants"
+ ]
}
},
"/v1/assistants/{id}": {
@@ -499,7 +528,9 @@
"description": "Beta feature header.",
"schema": {
"type": "string",
- "enum": ["assistants=v2"]
+ "enum": [
+ "assistants=v2"
+ ]
}
}
],
@@ -517,7 +548,9 @@
},
"object": {
"type": "string",
- "enum": ["assistant"],
+ "enum": [
+ "assistant"
+ ],
"description": "The object type, which is always 'assistant'."
},
"created_at": {
@@ -546,7 +579,9 @@
}
}
},
- "tags": ["Assistants"]
+ "tags": [
+ "Assistants"
+ ]
},
"delete": {
"operationId": "AssistantsController_remove",
@@ -577,22 +612,32 @@
},
"object": {
"type": "string",
- "enum": ["assistant.deleted"],
+ "enum": [
+ "assistant.deleted"
+ ],
"description": "The object type for a deleted assistant."
},
"deleted": {
"type": "boolean",
- "enum": [true],
+ "enum": [
+ true
+ ],
"description": "Indicates the assistant was successfully deleted."
}
},
- "required": ["id", "object", "deleted"]
+ "required": [
+ "id",
+ "object",
+ "deleted"
+ ]
}
}
}
}
},
- "tags": ["Assistants"]
+ "tags": [
+ "Assistants"
+ ]
}
},
"/healthz": {
@@ -609,7 +654,9 @@
}
}
},
- "tags": ["Server"]
+ "tags": [
+ "Server"
+ ]
}
},
"/processManager/destroy": {
@@ -626,7 +673,9 @@
}
}
},
- "tags": ["Server"]
+ "tags": [
+ "Server"
+ ]
}
},
"/v1/embeddings": {
@@ -681,11 +730,17 @@
"encoding_format": {
"type": "string",
"description": "The format to return the embeddings in.",
- "enum": ["float", "base64"],
+ "enum": [
+ "float",
+ "base64"
+ ],
"default": "float"
}
},
- "required": ["input", "model"]
+ "required": [
+ "input",
+ "model"
+ ]
}
}
}
@@ -728,7 +783,9 @@
}
}
},
- "tags": ["Embeddings"]
+ "tags": [
+ "Embeddings"
+ ]
}
},
"/v1/chat/completions": {
@@ -768,7 +825,9 @@
}
}
},
- "tags": ["Chat"]
+ "tags": [
+ "Chat"
+ ]
}
},
"/v1/models/pull": {
@@ -867,10 +926,14 @@
}
}
},
- "tags": ["Pulling Models"]
+ "tags": [
+ "Pulling Models"
+ ]
},
"delete": {
- "tags": ["Pulling Models"],
+ "tags": [
+ "Pulling Models"
+ ],
"summary": "Stop model download",
"description": "Stops the download of a model with the corresponding taskId provided in the request body",
"operationId": "ModelsController_stopModelDownload",
@@ -886,7 +949,9 @@
"description": "The unique identifier of the download task to be stopped"
}
},
- "required": ["taskId"]
+ "required": [
+ "taskId"
+ ]
}
}
}
@@ -1027,7 +1092,9 @@
}
}
},
- "tags": ["Pulling Models"]
+ "tags": [
+ "Pulling Models"
+ ]
}
},
"/v1/models": {
@@ -1048,7 +1115,9 @@
}
}
},
- "tags": ["Running Models"]
+ "tags": [
+ "Running Models"
+ ]
}
},
"/v1/models/start": {
@@ -1081,7 +1150,9 @@
}
}
},
- "tags": ["Running Models"]
+ "tags": [
+ "Running Models"
+ ]
}
},
"/v1/models/stop": {
@@ -1114,7 +1185,9 @@
}
}
},
- "tags": ["Running Models"]
+ "tags": [
+ "Running Models"
+ ]
}
},
"/v1/models/{id}": {
@@ -1145,7 +1218,9 @@
}
}
},
- "tags": ["Running Models"]
+ "tags": [
+ "Running Models"
+ ]
},
"delete": {
"operationId": "ModelsController_remove",
@@ -1174,7 +1249,9 @@
}
}
},
- "tags": ["Running Models"]
+ "tags": [
+ "Running Models"
+ ]
}
},
"/v1/models/{model}": {
@@ -1214,7 +1291,9 @@
}
}
},
- "tags": ["Running Models"]
+ "tags": [
+ "Running Models"
+ ]
}
},
"/v1/models/import": {
@@ -1255,7 +1334,9 @@
}
}
},
- "tags": ["Pulling Models"]
+ "tags": [
+ "Pulling Models"
+ ]
}
},
"/v1/models/sources": {
@@ -1297,7 +1378,9 @@
}
}
},
- "tags": ["Pulling Models"]
+ "tags": [
+ "Pulling Models"
+ ]
},
"delete": {
"summary": "Remove a model source",
@@ -1354,7 +1437,9 @@
}
}
},
- "tags": ["Pulling Models"]
+ "tags": [
+ "Pulling Models"
+ ]
}
},
"/v1/threads": {
@@ -1419,7 +1504,11 @@
"description": "Type of object, always 'thread'"
}
},
- "required": ["created_at", "id", "object"]
+ "required": [
+ "created_at",
+ "id",
+ "object"
+ ]
},
"example": {
"created_at": 1734020845,
@@ -1433,7 +1522,9 @@
}
}
},
- "tags": ["Threads"]
+ "tags": [
+ "Threads"
+ ]
},
"get": {
"summary": "List Threads",
@@ -1483,11 +1574,18 @@
"description": "Type of object, always 'thread'"
}
},
- "required": ["created_at", "id", "object"]
+ "required": [
+ "created_at",
+ "id",
+ "object"
+ ]
}
}
},
- "required": ["object", "data"]
+ "required": [
+ "object",
+ "data"
+ ]
},
"example": {
"data": [
@@ -1514,7 +1612,9 @@
}
}
},
- "tags": ["Threads"]
+ "tags": [
+ "Threads"
+ ]
}
},
"/v1/threads/{id}": {
@@ -1567,7 +1667,11 @@
"description": "Type of object, always 'thread'"
}
},
- "required": ["created_at", "id", "object"]
+ "required": [
+ "created_at",
+ "id",
+ "object"
+ ]
},
"example": {
"created_at": 1732370026,
@@ -1582,7 +1686,9 @@
}
}
},
- "tags": ["Threads"]
+ "tags": [
+ "Threads"
+ ]
},
"patch": {
"summary": "Modify Thread",
@@ -1656,7 +1762,11 @@
"description": "Type of object, always 'thread'"
}
},
- "required": ["created_at", "id", "object"]
+ "required": [
+ "created_at",
+ "id",
+ "object"
+ ]
},
"example": {
"created_at": 1733301054,
@@ -1670,7 +1780,9 @@
}
}
},
- "tags": ["Threads"]
+ "tags": [
+ "Threads"
+ ]
},
"delete": {
"summary": "Delete Thread",
@@ -1707,7 +1819,11 @@
"description": "Type of object, always 'thread.deleted'"
}
},
- "required": ["deleted", "id", "object"]
+ "required": [
+ "deleted",
+ "id",
+ "object"
+ ]
},
"example": {
"deleted": true,
@@ -1718,7 +1834,9 @@
}
}
},
- "tags": ["Threads"]
+ "tags": [
+ "Threads"
+ ]
}
},
"/v1/threads/{thread_id}/messages": {
@@ -1746,14 +1864,20 @@
"role": {
"type": "string",
"description": "Role of the message sender",
- "enum": ["user", "assistant"]
+ "enum": [
+ "user",
+ "assistant"
+ ]
},
"content": {
"type": "string",
"description": "The content of the message"
}
},
- "required": ["role", "content"]
+ "required": [
+ "role",
+ "content"
+ ]
},
"example": {
"role": "user",
@@ -1793,12 +1917,17 @@
"role": {
"type": "string",
"description": "Role of the message sender",
- "enum": ["user", "assistant"]
+ "enum": [
+ "user",
+ "assistant"
+ ]
},
"status": {
"type": "string",
"description": "Status of the message",
- "enum": ["completed"]
+ "enum": [
+ "completed"
+ ]
},
"content": {
"type": "array",
@@ -1808,7 +1937,9 @@
"type": {
"type": "string",
"description": "Type of content",
- "enum": ["text"]
+ "enum": [
+ "text"
+ ]
},
"text": {
"type": "object",
@@ -1865,7 +1996,9 @@
}
}
},
- "tags": ["Messages"]
+ "tags": [
+ "Messages"
+ ]
},
"get": {
"summary": "List Messages",
@@ -1896,7 +2029,10 @@
"description": "Sort order of messages",
"schema": {
"type": "string",
- "enum": ["asc", "desc"]
+ "enum": [
+ "asc",
+ "desc"
+ ]
}
},
{
@@ -1964,12 +2100,17 @@
"role": {
"type": "string",
"description": "Role of the message sender",
- "enum": ["assistant", "user"]
+ "enum": [
+ "assistant",
+ "user"
+ ]
},
"status": {
"type": "string",
"description": "Status of the message",
- "enum": ["completed"]
+ "enum": [
+ "completed"
+ ]
},
"content": {
"type": "array",
@@ -1979,7 +2120,9 @@
"type": {
"type": "string",
"description": "Type of content",
- "enum": ["text"]
+ "enum": [
+ "text"
+ ]
},
"text": {
"type": "object",
@@ -2037,7 +2180,10 @@
}
}
},
- "required": ["object", "data"]
+ "required": [
+ "object",
+ "data"
+ ]
},
"example": {
"data": [
@@ -2066,7 +2212,9 @@
}
}
},
- "tags": ["Messages"]
+ "tags": [
+ "Messages"
+ ]
}
},
"/v1/threads/{thread_id}/messages/{message_id}": {
@@ -2120,12 +2268,17 @@
"role": {
"type": "string",
"description": "Role of the message sender",
- "enum": ["assistant", "user"]
+ "enum": [
+ "assistant",
+ "user"
+ ]
},
"status": {
"type": "string",
"description": "Status of the message",
- "enum": ["completed"]
+ "enum": [
+ "completed"
+ ]
},
"content": {
"type": "array",
@@ -2135,7 +2288,9 @@
"type": {
"type": "string",
"description": "Type of content",
- "enum": ["text"]
+ "enum": [
+ "text"
+ ]
},
"text": {
"type": "object",
@@ -2223,7 +2378,9 @@
}
}
},
- "tags": ["Messages"]
+ "tags": [
+ "Messages"
+ ]
},
"patch": {
"summary": "Modify Message",
@@ -2306,12 +2463,17 @@
"role": {
"type": "string",
"description": "Role of the message sender",
- "enum": ["user", "assistant"]
+ "enum": [
+ "user",
+ "assistant"
+ ]
},
"status": {
"type": "string",
"description": "Status of the message",
- "enum": ["completed"]
+ "enum": [
+ "completed"
+ ]
},
"content": {
"type": "array",
@@ -2321,7 +2483,9 @@
"type": {
"type": "string",
"description": "Type of content",
- "enum": ["text"]
+ "enum": [
+ "text"
+ ]
},
"text": {
"type": "object",
@@ -2381,7 +2545,9 @@
}
}
},
- "tags": ["Messages"]
+ "tags": [
+ "Messages"
+ ]
},
"delete": {
"summary": "Delete Message",
@@ -2427,7 +2593,11 @@
"description": "Type of object, always 'thread.message.deleted'"
}
},
- "required": ["deleted", "id", "object"]
+ "required": [
+ "deleted",
+ "id",
+ "object"
+ ]
},
"example": {
"deleted": true,
@@ -2438,7 +2608,9 @@
}
}
},
- "tags": ["Messages"]
+ "tags": [
+ "Messages"
+ ]
}
},
"/v1/system": {
@@ -2452,7 +2624,9 @@
"description": ""
}
},
- "tags": ["System"]
+ "tags": [
+ "System"
+ ]
},
"get": {
"operationId": "SystemController_get",
@@ -2464,7 +2638,9 @@
"description": "Ok"
}
},
- "tags": ["System"]
+ "tags": [
+ "System"
+ ]
}
},
"/v1/system/events/download": {
@@ -2485,7 +2661,9 @@
}
}
},
- "tags": ["System"]
+ "tags": [
+ "System"
+ ]
}
},
"/v1/system/events/model": {
@@ -2506,7 +2684,9 @@
}
}
},
- "tags": ["System"]
+ "tags": [
+ "System"
+ ]
}
},
"/v1/system/events/resources": {
@@ -2527,7 +2707,9 @@
}
}
},
- "tags": ["System"]
+ "tags": [
+ "System"
+ ]
}
},
"/v1/engines/{name}": {
@@ -2542,7 +2724,11 @@
"required": true,
"schema": {
"type": "string",
- "enum": ["llama-cpp", "onnxruntime", "tensorrt-llm"],
+ "enum": [
+ "llama-cpp",
+ "onnxruntime",
+ "tensorrt-llm"
+ ],
"default": "llama-cpp"
},
"description": "The type of engine"
@@ -2589,7 +2775,9 @@
}
}
},
- "tags": ["Engines"]
+ "tags": [
+ "Engines"
+ ]
}
},
"/v1/engines/{name}/releases": {
@@ -2603,7 +2791,11 @@
"required": true,
"schema": {
"type": "string",
- "enum": ["llama-cpp", "onnxruntime", "tensorrt-llm"],
+ "enum": [
+ "llama-cpp",
+ "onnxruntime",
+ "tensorrt-llm"
+ ],
"default": "llama-cpp"
},
"description": "The type of engine"
@@ -2638,7 +2830,7 @@
},
"url": {
"type": "string",
- "example": "https://api.github.com/repos/janhq/cortex.llamacpp/releases/186479804"
+ "example": "https://api.github.com/repos/menloresearch/cortex.llamacpp/releases/186479804"
}
}
}
@@ -2647,7 +2839,9 @@
}
}
},
- "tags": ["Engines"]
+ "tags": [
+ "Engines"
+ ]
}
},
"/v1/engines/{name}/releases/{version}": {
@@ -2661,7 +2855,11 @@
"required": true,
"schema": {
"type": "string",
- "enum": ["llama-cpp", "onnxruntime", "tensorrt-llm"],
+ "enum": [
+ "llama-cpp",
+ "onnxruntime",
+ "tensorrt-llm"
+ ],
"default": "llama-cpp"
},
"description": "The type of engine"
@@ -2681,7 +2879,10 @@
"required": false,
"schema": {
"type": "string",
- "enum": ["all", "compatible"],
+ "enum": [
+ "all",
+ "compatible"
+ ],
"default": "all"
},
"description": "Filter the variants list. Use 'compatible' to show only variants compatible with the current system, or 'all' to show all available variants."
@@ -2725,7 +2926,9 @@
}
}
},
- "tags": ["Engines"]
+ "tags": [
+ "Engines"
+ ]
}
},
"/v1/engines/{name}/releases/latest": {
@@ -2739,7 +2942,11 @@
"required": true,
"schema": {
"type": "string",
- "enum": ["llama-cpp", "onnxruntime", "tensorrt-llm"],
+ "enum": [
+ "llama-cpp",
+ "onnxruntime",
+ "tensorrt-llm"
+ ],
"default": "llama-cpp"
},
"description": "The type of engine"
@@ -2779,7 +2986,9 @@
}
}
},
- "tags": ["Engines"]
+ "tags": [
+ "Engines"
+ ]
}
},
"/v1/engines/{name}/install": {
@@ -2870,7 +3079,9 @@
}
}
},
- "tags": ["Engines"]
+ "tags": [
+ "Engines"
+ ]
},
"delete": {
"summary": "Uninstall an engine",
@@ -2951,7 +3162,9 @@
}
}
},
- "tags": ["Engines"]
+ "tags": [
+ "Engines"
+ ]
}
},
"/v1/engines/{name}/update": {
@@ -2965,7 +3178,11 @@
"required": true,
"schema": {
"type": "string",
- "enum": ["llama-cpp", "onnxruntime", "tensorrt-llm"],
+ "enum": [
+ "llama-cpp",
+ "onnxruntime",
+ "tensorrt-llm"
+ ],
"default": "llama-cpp"
},
"description": "The name of the engine to update"
@@ -2989,7 +3206,9 @@
}
}
},
- "tags": ["Engines"]
+ "tags": [
+ "Engines"
+ ]
}
},
"/v1/engines/{name}/default": {
@@ -3003,7 +3222,11 @@
"required": true,
"schema": {
"type": "string",
- "enum": ["llama-cpp", "onnxruntime", "tensorrt-llm"],
+ "enum": [
+ "llama-cpp",
+ "onnxruntime",
+ "tensorrt-llm"
+ ],
"default": "llama-cpp"
},
"description": "The type of engine"
@@ -3035,7 +3258,9 @@
}
}
},
- "tags": ["Engines"]
+ "tags": [
+ "Engines"
+ ]
},
"post": {
"summary": "Set default engine variant",
@@ -3047,7 +3272,11 @@
"required": true,
"schema": {
"type": "string",
- "enum": ["llama-cpp", "onnxruntime", "tensorrt-llm"],
+ "enum": [
+ "llama-cpp",
+ "onnxruntime",
+ "tensorrt-llm"
+ ],
"default": "llama-cpp"
},
"description": "The type of engine"
@@ -3059,7 +3288,10 @@
"application/json": {
"schema": {
"type": "object",
- "required": ["version", "variant"],
+ "required": [
+ "version",
+ "variant"
+ ],
"properties": {
"version": {
"type": "string",
@@ -3094,7 +3326,9 @@
}
}
},
- "tags": ["Engines"]
+ "tags": [
+ "Engines"
+ ]
}
},
"/v1/engines/{name}/load": {
@@ -3138,7 +3372,9 @@
}
}
},
- "tags": ["Engines"]
+ "tags": [
+ "Engines"
+ ]
},
"delete": {
"summary": "Unload engine",
@@ -3150,7 +3386,11 @@
"required": true,
"schema": {
"type": "string",
- "enum": ["llama-cpp", "onnxruntime", "tensorrt-llm"],
+ "enum": [
+ "llama-cpp",
+ "onnxruntime",
+ "tensorrt-llm"
+ ],
"default": "llama-cpp"
},
"description": "The name of the engine to update"
@@ -3174,7 +3414,9 @@
}
}
},
- "tags": ["Engines"]
+ "tags": [
+ "Engines"
+ ]
}
},
"/v1/hardware": {
@@ -3216,7 +3458,9 @@
}
}
},
- "tags": ["Hardware"]
+ "tags": [
+ "Hardware"
+ ]
}
},
"/v1/hardware/activate": {
@@ -3235,11 +3479,17 @@
"items": {
"type": "integer"
},
- "example": [0, 1, 2],
+ "example": [
+ 0,
+ 1,
+ 2
+ ],
"description": "An array of GPU indices to activate."
}
},
- "required": ["gpus"]
+ "required": [
+ "gpus"
+ ]
}
}
}
@@ -3262,7 +3512,11 @@
"items": {
"type": "integer"
},
- "example": [0, 1, 2],
+ "example": [
+ 0,
+ 1,
+ 2
+ ],
"description": "List of GPU indices that were activated."
}
}
@@ -3288,7 +3542,9 @@
}
}
},
- "tags": ["Hardware"]
+ "tags": [
+ "Hardware"
+ ]
}
},
"/v1/files": {
@@ -3308,11 +3564,16 @@
},
"purpose": {
"type": "string",
- "enum": ["assistants"],
+ "enum": [
+ "assistants"
+ ],
"description": "The intended purpose of the uploaded file"
}
},
- "required": ["file", "purpose"]
+ "required": [
+ "file",
+ "purpose"
+ ]
}
}
}
@@ -3355,7 +3616,9 @@
}
}
},
- "tags": ["Files"]
+ "tags": [
+ "Files"
+ ]
},
"get": {
"summary": "List files",
@@ -3410,7 +3673,9 @@
}
}
},
- "tags": ["Files"]
+ "tags": [
+ "Files"
+ ]
}
},
"/v1/files/{id}": {
@@ -3475,7 +3740,9 @@
}
}
},
- "tags": ["Files"]
+ "tags": [
+ "Files"
+ ]
},
"delete": {
"summary": "Delete File",
@@ -3512,7 +3779,11 @@
"description": "Type of object, always 'file'"
}
},
- "required": ["deleted", "id", "object"]
+ "required": [
+ "deleted",
+ "id",
+ "object"
+ ]
},
"example": {
"deleted": true,
@@ -3534,7 +3805,9 @@
"description": "Error message describing the issue"
}
},
- "required": ["message"]
+ "required": [
+ "message"
+ ]
},
"example": {
"message": "File not found: file-0001KNP26FC62D620DGYNG2R8H"
@@ -3543,7 +3816,9 @@
}
}
},
- "tags": ["Files"]
+ "tags": [
+ "Files"
+ ]
}
},
"/v1/files/{id}/content": {
@@ -3595,13 +3870,17 @@
"description": "Error message describing the issue"
}
},
- "required": ["message"]
+ "required": [
+ "message"
+ ]
}
}
}
}
},
- "tags": ["Files"]
+ "tags": [
+ "Files"
+ ]
}
},
"/v1/configs": {
@@ -3621,7 +3900,10 @@
"items": {
"type": "string"
},
- "example": ["http://127.0.0.1:39281", "https://cortex.so"]
+ "example": [
+ "http://127.0.0.1:39281",
+ "https://cortex.so"
+ ]
},
"cors": {
"type": "boolean",
@@ -3663,6 +3945,16 @@
"huggingface_token": {
"type": "string",
"example": "your_token"
+ },
+ "api_keys": {
+ "type": "array",
+ "items": {
+ "type": "string"
+ },
+ "example": [
+ "api_key1",
+ "api_key2"
+ ]
}
}
},
@@ -3680,16 +3972,24 @@
"verify_peer_ssl": false,
"verify_host_ssl": false,
"no_proxy": "localhost",
- "huggingface_token": "your_token"
+ "huggingface_token": "your_token",
+ "api_keys": [
+ "api_key1",
+ "api_key2"
+ ]
}
}
}
}
},
- "tags": ["Configurations"]
+ "tags": [
+ "Configurations"
+ ]
},
"patch": {
- "tags": ["Configurations"],
+ "tags": [
+ "Configurations"
+ ],
"summary": "Update configuration settings",
"requestBody": {
"required": true,
@@ -3709,7 +4009,10 @@
"type": "string"
},
"description": "List of allowed origins.",
- "example": ["http://127.0.0.1:39281", "https://cortex.so"]
+ "example": [
+ "http://127.0.0.1:39281",
+ "https://cortex.so"
+ ]
},
"proxy_username": {
"type": "string",
@@ -3755,6 +4058,17 @@
"type": "string",
"description": "HuggingFace token to pull models.",
"example": "your_token"
+ },
+ "api_keys": {
+ "type": "array",
+ "items": {
+ "type": "string"
+ },
+ "description": "List of allowed origins.",
+ "example": [
+ "api_key1",
+ "api_key2"
+ ]
}
}
}
@@ -3821,6 +4135,16 @@
"huggingface_token": {
"type": "string",
"example": "your_token"
+ },
+ "api_keys": {
+ "type": "array",
+ "items": {
+ "type": "string"
+ },
+ "example": [
+ "api_key1",
+ "api_key2"
+ ]
}
}
},
@@ -3973,13 +4297,18 @@
"properties": {
"type": {
"type": "string",
- "enum": ["function"]
+ "enum": [
+ "function"
+ ]
},
"function": {
"$ref": "#/components/schemas/Function"
}
},
- "required": ["type", "function"]
+ "required": [
+ "type",
+ "function"
+ ]
}
},
"metadata": {
@@ -4100,7 +4429,11 @@
"description": "Indicates whether the assistant was successfully deleted."
}
},
- "required": ["id", "object", "deleted"]
+ "required": [
+ "id",
+ "object",
+ "deleted"
+ ]
},
"Message": {
"type": "object",
@@ -4117,14 +4450,21 @@
"properties": {
"role": {
"type": "string",
- "enum": ["system", "user", "assistant", "tool"]
+ "enum": [
+ "system",
+ "user",
+ "assistant",
+ "tool"
+ ]
},
"name": {
"type": "string",
"description": "An optional name for the participant. Provides the model information to differentiate between participants of the same role."
}
},
- "required": ["role"]
+ "required": [
+ "role"
+ ]
},
"SystemMessage": {
"allOf": [
@@ -4153,7 +4493,10 @@
"description": "An optional name for the participant. Provides the model information to differentiate between participants of the same role."
}
},
- "required": ["content", "role"]
+ "required": [
+ "content",
+ "role"
+ ]
}
]
},
@@ -4204,7 +4547,10 @@
"description": "An optional name for the participant. Provides the model information to differentiate between participants of the same role."
}
},
- "required": ["content", "role"]
+ "required": [
+ "content",
+ "role"
+ ]
}
]
},
@@ -4316,7 +4662,10 @@
"type": "string"
}
},
- "required": ["content", "tool_call_id"]
+ "required": [
+ "content",
+ "tool_call_id"
+ ]
}
]
},
@@ -4333,26 +4682,36 @@
"properties": {
"type": {
"type": "string",
- "enum": ["text"]
+ "enum": [
+ "text"
+ ]
},
"text": {
"type": "string"
}
},
- "required": ["type", "text"]
+ "required": [
+ "type",
+ "text"
+ ]
},
"ImageContentPart": {
"type": "object",
"properties": {
"type": {
"type": "string",
- "enum": ["image_url"]
+ "enum": [
+ "image_url"
+ ]
},
"image_url": {
"$ref": "#/components/schemas/ImageUrl"
}
},
- "required": ["type", "image_url"]
+ "required": [
+ "type",
+ "image_url"
+ ]
},
"AudioContentPart": {
"type": "object",
@@ -4365,7 +4724,10 @@
"$ref": "#/components/schemas/InputAudio"
}
},
- "required": ["type", "input_audio"]
+ "required": [
+ "type",
+ "input_audio"
+ ]
},
"RefusalContentPart": {
"type": "object",
@@ -4377,7 +4739,10 @@
"type": "string"
}
},
- "required": ["type", "refusal"]
+ "required": [
+ "type",
+ "refusal"
+ ]
},
"ImageUrl": {
"type": "object",
@@ -4392,7 +4757,9 @@
"description": "Specifies the detail level of the image. Defaults to `auto`."
}
},
- "required": ["url"]
+ "required": [
+ "url"
+ ]
},
"InputAudio": {
"type": "object",
@@ -4403,11 +4770,17 @@
},
"format": {
"type": "string",
- "enum": ["wav", "mp3"],
+ "enum": [
+ "wav",
+ "mp3"
+ ],
"description": "The format of the encoded audio data. Currently supports `wav` and `mp3`."
}
},
- "required": ["data", "format"]
+ "required": [
+ "data",
+ "format"
+ ]
},
"Audio": {
"type": "object",
@@ -4418,7 +4791,9 @@
"description": "Unique identifier for a previous audio response from the model."
}
},
- "required": ["id"]
+ "required": [
+ "id"
+ ]
},
"ToolCall": {
"type": "object",
@@ -4433,7 +4808,11 @@
"$ref": "#/components/schemas/FunctionCall"
}
},
- "required": ["id", "type", "function"]
+ "required": [
+ "id",
+ "type",
+ "function"
+ ]
},
"FunctionCall": {
"type": "object",
@@ -4445,7 +4824,10 @@
"type": "string"
}
},
- "required": ["name", "arguments"]
+ "required": [
+ "name",
+ "arguments"
+ ]
},
"CreateChatCompletionDto": {
"type": "object",
@@ -4499,7 +4881,9 @@
},
"stop": {
"description": "Defines specific tokens or phrases that signal the model to stop producing further output.",
- "example": ["End"],
+ "example": [
+ "End"
+ ],
"type": "array",
"items": {
"type": "string"
@@ -4529,13 +4913,18 @@
"type": "array",
"items": {
"type": "string",
- "enum": ["text", "audio"]
+ "enum": [
+ "text",
+ "audio"
+ ]
},
- "description": "Specifies the modalities (types of input) supported by the model. Currently, cortex only support text modalities. We are actively working on this feature to bring cortex as fully OpenAI compatible platform. Planning and roadmap for this feature can be found [**here**](https://github.com/janhq/cortex.cpp/issues/1582).",
- "example": ["text"]
+ "description": "Specifies the modalities (types of input) supported by the model. Currently, cortex only support text modalities. We are actively working on this feature to bring cortex as fully OpenAI compatible platform. Planning and roadmap for this feature can be found [**here**](https://github.com/menloresearch/cortex.cpp/issues/1582).",
+ "example": [
+ "text"
+ ]
},
"audio": {
- "description": "Parameters for audio output. Required when audio output is requested with `modalities: ['audio']`. We are actively working on this feature to bring cortex as fully OpenAI compatible platform. Planning and roadmap for this feature can be found [**here**](https://github.com/janhq/cortex.cpp/issues/1582).",
+ "description": "Parameters for audio output. Required when audio output is requested with `modalities: ['audio']`. We are actively working on this feature to bring cortex as fully OpenAI compatible platform. Planning and roadmap for this feature can be found [**here**](https://github.com/menloresearch/cortex.cpp/issues/1582).",
"type": "object",
"properties": {
"voice": {
@@ -4545,20 +4934,29 @@
"format": {
"type": "string",
"description": "Specifies the output audio format. Must be one of `wav`, `mp3`, `flac`, `opus`, or `pcm16`.",
- "enum": ["mp3", "wav", "flac", "opus", "pcm16"]
+ "enum": [
+ "mp3",
+ "wav",
+ "flac",
+ "opus",
+ "pcm16"
+ ]
}
},
- "required": ["voice", "format"]
+ "required": [
+ "voice",
+ "format"
+ ]
},
"store": {
"type": "boolean",
- "description": "Whether or not to store the output of this chat completion request for use in our model distillation or evals products. We are actively working on this feature to bring cortex as fully OpenAI compatible platform. Planning and roadmap for this feature can be found [**here**](https://github.com/janhq/cortex.cpp/issues/1582).",
+ "description": "Whether or not to store the output of this chat completion request for use in our model distillation or evals products. We are actively working on this feature to bring cortex as fully OpenAI compatible platform. Planning and roadmap for this feature can be found [**here**](https://github.com/menloresearch/cortex.cpp/issues/1582).",
"default": false,
"example": false
},
"metadata": {
"type": "object",
- "description": "Developer-defined tags and values used for filtering completions in the dashboard. We are actively working on this feature to bring cortex as fully OpenAI compatible platform. Planning and roadmap for this feature can be found [**here**](https://github.com/janhq/cortex.cpp/issues/1582).",
+ "description": "Developer-defined tags and values used for filtering completions in the dashboard. We are actively working on this feature to bring cortex as fully OpenAI compatible platform. Planning and roadmap for this feature can be found [**here**](https://github.com/menloresearch/cortex.cpp/issues/1582).",
"example": {
"type": "conversation"
}
@@ -4590,15 +4988,21 @@
},
"response_format": {
"type": "object",
- "description": "An object specifying the format that the model must output. Setting to { \"type\": \"json_object\" } enables JSON mode, which guarantees the message the model generates is valid JSON. We are actively working on this feature to bring cortex as fully OpenAI compatible platform. Planning and roadmap for this feature can be found [**here**](https://github.com/janhq/cortex.cpp/issues/1582).",
+ "description": "An object specifying the format that the model must output. Setting to { \"type\": \"json_object\" } enables JSON mode, which guarantees the message the model generates is valid JSON. We are actively working on this feature to bring cortex as fully OpenAI compatible platform. Planning and roadmap for this feature can be found [**here**](https://github.com/menloresearch/cortex.cpp/issues/1582).",
"properties": {
"type": {
"type": "string",
"description": "The format of the generated output. Must be one of `text`, `json_schema` or `json_object`.",
- "enum": ["text", "json_object", "json_schema"]
+ "enum": [
+ "text",
+ "json_object",
+ "json_schema"
+ ]
}
},
- "required": ["type"]
+ "required": [
+ "type"
+ ]
},
"seed": {
"type": "number",
@@ -4608,7 +5012,7 @@
},
"service_tier": {
"type": "string",
- "description": "Specifies the latency tier to use for processing the request. This parameter is relevant for customers subscribed to the scale tier service:\n\n - If set to 'auto', and the Project is Scale tier enabled, the system will utilize scale tier credits until they are exhausted.\n- If set to 'auto', and the Project is not Scale tier enabled, the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee.\n- If set to 'default', the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee.\nWhen not set, the default behavior is 'auto'.\nWhen this parameter is set, the response body will include the service_tier utilized.\n\n We are actively working on this feature to bring cortex as fully OpenAI compatible platform. Planning and roadmap for this feature can be found [**here**](https://github.com/janhq/cortex.cpp/issues/1582)."
+ "description": "Specifies the latency tier to use for processing the request. This parameter is relevant for customers subscribed to the scale tier service:\n\n - If set to 'auto', and the Project is Scale tier enabled, the system will utilize scale tier credits until they are exhausted.\n- If set to 'auto', and the Project is not Scale tier enabled, the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee.\n- If set to 'default', the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee.\nWhen not set, the default behavior is 'auto'.\nWhen this parameter is set, the response body will include the service_tier utilized.\n\n We are actively working on this feature to bring cortex as fully OpenAI compatible platform. Planning and roadmap for this feature can be found [**here**](https://github.com/menloresearch/cortex.cpp/issues/1582)."
},
"stream_options": {
"type": "object",
@@ -4630,27 +5034,38 @@
"properties": {
"type": {
"type": "string",
- "enum": ["function"]
+ "enum": [
+ "function"
+ ]
},
"function": {
"$ref": "#/components/schemas/Function"
}
},
- "required": ["type", "function"]
+ "required": [
+ "type",
+ "function"
+ ]
}
},
"tool_choice": {
"anyOf": [
{
"type": "string",
- "enum": ["none", "auto", "required"]
+ "enum": [
+ "none",
+ "auto",
+ "required"
+ ]
},
{
"type": "object",
"properties": {
"type": {
"type": "string",
- "enum": ["function"]
+ "enum": [
+ "function"
+ ]
},
"function": {
"type": "object",
@@ -4659,10 +5074,15 @@
"type": "string"
}
},
- "required": ["name"]
+ "required": [
+ "name"
+ ]
}
},
- "required": ["type", "function"]
+ "required": [
+ "type",
+ "function"
+ ]
}
]
},
@@ -4674,7 +5094,7 @@
},
"user": {
"type": "string",
- "description": "A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. We are actively working on this feature to bring cortex as fully OpenAI compatible platform. Planning and roadmap for this feature can be found [**here**](https://github.com/janhq/cortex.cpp/issues/1582)."
+ "description": "A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. We are actively working on this feature to bring cortex as fully OpenAI compatible platform. Planning and roadmap for this feature can be found [**here**](https://github.com/menloresearch/cortex.cpp/issues/1582)."
},
"dynatemp_range": {
"type": "number",
@@ -4737,7 +5157,10 @@
"description": "Minimum number of tokens to keep. This parameter only supported by `llama-cpp` engine."
}
},
- "required": ["messages", "model"]
+ "required": [
+ "messages",
+ "model"
+ ]
},
"Function": {
"type": "object",
@@ -4757,7 +5180,9 @@
"default": false
}
},
- "required": ["name"]
+ "required": [
+ "name"
+ ]
},
"MessageDto": {
"type": "object",
@@ -4771,7 +5196,10 @@
"description": "The role of the participant in the chat, such as 'user' or 'system', indicating who is the sender of the message."
}
},
- "required": ["content", "role"]
+ "required": [
+ "content",
+ "role"
+ ]
},
"ChoiceDto": {
"type": "object",
@@ -4793,7 +5221,11 @@
]
}
},
- "required": ["finish_reason", "index", "message"]
+ "required": [
+ "finish_reason",
+ "index",
+ "message"
+ ]
},
"UsageDto": {
"type": "object",
@@ -4811,7 +5243,11 @@
"description": "The total number of tokens used in both the prompt and the completion, summarizing the entire token count of the chat operation."
}
},
- "required": ["completion_tokens", "prompt_tokens", "total_tokens"]
+ "required": [
+ "completion_tokens",
+ "prompt_tokens",
+ "total_tokens"
+ ]
},
"ChatCompletionResponseDto": {
"type": "object",
@@ -4838,11 +5274,17 @@
"type": "object",
"properties": {
"content": {
- "type": ["string", "null"],
+ "type": [
+ "string",
+ "null"
+ ],
"description": "The contents of the message."
},
"refusal": {
- "type": ["string", "null"],
+ "type": [
+ "string",
+ "null"
+ ],
"description": "The refusal message generated by the model."
},
"tool_calls": {
@@ -4871,10 +5313,17 @@
"description": "The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function."
}
},
- "required": ["name", "arguments"]
+ "required": [
+ "name",
+ "arguments"
+ ]
}
},
- "required": ["id", "type", "function"]
+ "required": [
+ "id",
+ "type",
+ "function"
+ ]
}
},
"role": {
@@ -4895,7 +5344,10 @@
"description": "The name of the function to call."
}
},
- "required": ["arguments", "name"]
+ "required": [
+ "arguments",
+ "name"
+ ]
},
"audio": {
"type": "object",
@@ -4918,17 +5370,27 @@
"description": "Transcript of the audio generated by the model."
}
},
- "required": ["id", "expires_at", "data", "transcript"]
+ "required": [
+ "id",
+ "expires_at",
+ "data",
+ "transcript"
+ ]
}
},
- "required": ["role"]
+ "required": [
+ "role"
+ ]
},
"logprobs": {
"type": "object",
"description": "Log probability information for the choice.",
"properties": {
"content": {
- "type": ["array", "null"],
+ "type": [
+ "array",
+ "null"
+ ],
"description": "A list of message content tokens with log probability information.",
"items": {
"type": "object",
@@ -4942,11 +5404,17 @@
"description": "The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely."
},
"bytes": {
- "type": ["array", "null"],
+ "type": [
+ "array",
+ "null"
+ ],
"description": "A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token."
}
},
- "required": ["token", "logprob"]
+ "required": [
+ "token",
+ "logprob"
+ ]
}
},
"top_logprobs": {
@@ -4964,15 +5432,24 @@
"description": "The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely."
},
"bytes": {
- "type": ["array", "null"],
+ "type": [
+ "array",
+ "null"
+ ],
"description": "A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token."
}
},
- "required": ["token", "logprob"]
+ "required": [
+ "token",
+ "logprob"
+ ]
}
},
"refusal": {
- "type": ["array", "null"],
+ "type": [
+ "array",
+ "null"
+ ],
"description": "A list of message refusal tokens with log probability information.",
"items": {
"type": "object",
@@ -4986,17 +5463,27 @@
"description": "The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely."
},
"bytes": {
- "type": ["array", "null"],
+ "type": [
+ "array",
+ "null"
+ ],
"description": "A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token."
}
},
- "required": ["token", "logprob"]
+ "required": [
+ "token",
+ "logprob"
+ ]
}
}
}
}
},
- "required": ["finish_reason", "index", "message"]
+ "required": [
+ "finish_reason",
+ "index",
+ "message"
+ ]
}
},
"created": {
@@ -5008,7 +5495,10 @@
"description": "The model used for the chat completion."
},
"service_tier": {
- "type": ["string", "null"],
+ "type": [
+ "string",
+ "null"
+ ],
"description": "The service tier used for processing the request. This field is only included if the service_tier parameter is specified in the request."
},
"system_fingerprint": {
@@ -5048,7 +5538,10 @@
"description": "Tokens generated by the model for reasoning."
}
},
- "required": ["audio_tokens", "reasoning_tokens"]
+ "required": [
+ "audio_tokens",
+ "reasoning_tokens"
+ ]
},
"prompt_tokens_details": {
"type": "object",
@@ -5063,7 +5556,10 @@
"description": "Cached tokens present in the prompt."
}
},
- "required": ["audio_tokens", "cached_tokens"]
+ "required": [
+ "audio_tokens",
+ "cached_tokens"
+ ]
}
},
"required": [
@@ -5103,7 +5599,10 @@
"description": "A chat completion delta generated by streamed model responses.",
"properties": {
"content": {
- "type": ["string", "null"],
+ "type": [
+ "string",
+ "null"
+ ],
"description": "The contents of the chunk message."
},
"function_call": {
@@ -5141,10 +5640,18 @@
"description": "The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function."
}
},
- "required": ["name", "arguments"]
+ "required": [
+ "name",
+ "arguments"
+ ]
}
},
- "required": ["index", "id", "type", "function"]
+ "required": [
+ "index",
+ "id",
+ "type",
+ "function"
+ ]
}
},
"role": {
@@ -5152,7 +5659,10 @@
"description": "The role of the author of this message."
},
"refusal": {
- "type": ["string", "null"],
+ "type": [
+ "string",
+ "null"
+ ],
"description": "The refusal message generated by the model."
}
}
@@ -5162,7 +5672,10 @@
"description": "Log probability information for the choice.",
"properties": {
"content": {
- "type": ["array", "null"],
+ "type": [
+ "array",
+ "null"
+ ],
"description": "A list of message content tokens with log probability information.",
"items": {
"type": "object",
@@ -5176,11 +5689,17 @@
"description": "The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely."
},
"bytes": {
- "type": ["array", "null"],
+ "type": [
+ "array",
+ "null"
+ ],
"description": "A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token."
}
},
- "required": ["token", "logprob"]
+ "required": [
+ "token",
+ "logprob"
+ ]
}
},
"top_logprobs": {
@@ -5198,15 +5717,24 @@
"description": "The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely."
},
"bytes": {
- "type": ["array", "null"],
+ "type": [
+ "array",
+ "null"
+ ],
"description": "A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token."
}
},
- "required": ["token", "logprob"]
+ "required": [
+ "token",
+ "logprob"
+ ]
}
},
"refusal": {
- "type": ["array", "null"],
+ "type": [
+ "array",
+ "null"
+ ],
"description": "A list of message refusal tokens with log probability information.",
"items": {
"type": "object",
@@ -5220,17 +5748,26 @@
"description": "The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely."
},
"bytes": {
- "type": ["array", "null"],
+ "type": [
+ "array",
+ "null"
+ ],
"description": "A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token."
}
},
- "required": ["token", "logprob"]
+ "required": [
+ "token",
+ "logprob"
+ ]
}
}
}
},
"finish_reason": {
- "type": ["string", "null"],
+ "type": [
+ "string",
+ "null"
+ ],
"description": "The reason the model stopped generating tokens. This will be stop if the model hit a natural stop point or a provided stop sequence, length if the maximum number of tokens specified in the request was reached, content_filter if content was omitted due to a flag from our content filters, tool_calls if the model called a tool, or function_call (deprecated) if the model called a function."
},
"index": {
@@ -5238,7 +5775,10 @@
"description": "The index of the choice in the list of choices."
}
},
- "required": ["delta", "index"]
+ "required": [
+ "delta",
+ "index"
+ ]
}
},
"created": {
@@ -5250,7 +5790,10 @@
"description": "The model used to generate the completion."
},
"service_tier": {
- "type": ["string", "null"],
+ "type": [
+ "string",
+ "null"
+ ],
"description": "The service tier used for processing the request. This field is only included if the service_tier parameter is specified in the request."
},
"system_fingerprint": {
@@ -5278,7 +5821,11 @@
"description": "Total number of tokens used in the request (prompt + completion)."
}
},
- "required": ["completion_tokens", "prompt_tokens", "total_tokens"]
+ "required": [
+ "completion_tokens",
+ "prompt_tokens",
+ "total_tokens"
+ ]
}
},
"required": [
@@ -5299,7 +5846,9 @@
"description": "The name of the embedding model to be used."
},
"input": {
- "example": ["Hello World"],
+ "example": [
+ "Hello World"
+ ],
"description": "The text or token array(s) to be embedded. This can be a single string, an array of strings, or an array of token arrays to embed multiple inputs in one request.",
"type": "array",
"items": {
@@ -5317,7 +5866,10 @@
"description": "Defines the number of dimensions for the output embeddings. This feature is supported by certain models only. This field is optional."
}
},
- "required": ["model", "input"]
+ "required": [
+ "model",
+ "input"
+ ]
},
"EmbeddingsResponseDto": {
"type": "object",
@@ -5346,11 +5898,18 @@
]
}
},
- "required": ["object", "model", "embedding", "usage"]
+ "required": [
+ "object",
+ "model",
+ "embedding",
+ "usage"
+ ]
},
"PullModelRequest": {
"type": "object",
- "required": ["model"],
+ "required": [
+ "model"
+ ],
"properties": {
"model": {
"type": "string",
@@ -5507,7 +6066,9 @@
},
"files": {
"description": "The URL sources from which the model downloaded or accessed.",
- "example": ["https://huggingface.co/cortexso/mistral/tree/gguf"],
+ "example": [
+ "https://huggingface.co/cortexso/mistral/tree/gguf"
+ ],
"oneOf": [
{
"type": "array",
@@ -5527,7 +6088,9 @@
},
"stop": {
"description": "Defines specific tokens or phrases that signal the model to stop producing further output.",
- "example": ["End"],
+ "example": [
+ "End"
+ ],
"type": "array",
"items": {
"type": "string"
@@ -5597,7 +6160,10 @@
"default": ""
}
},
- "required": ["model", "files"]
+ "required": [
+ "model",
+ "files"
+ ]
},
"StartModelSuccessDto": {
"type": "object",
@@ -5611,7 +6177,10 @@
"description": "The unique identifier of the model."
}
},
- "required": ["message", "modelId"]
+ "required": [
+ "message",
+ "modelId"
+ ]
},
"ModelStartDto": {
"type": "object",
@@ -5658,7 +6227,9 @@
"example": "/tmp/model.gguf"
}
},
- "required": ["model"]
+ "required": [
+ "model"
+ ]
},
"ModelStopDto": {
"type": "object",
@@ -5669,7 +6240,9 @@
"description": "A downloaded model name."
}
},
- "required": ["model"]
+ "required": [
+ "model"
+ ]
},
"ImportModelRequest": {
"type": "object",
@@ -5689,10 +6262,16 @@
"option": {
"type": "string",
"description": "Import options such as symlink or copy.",
- "enum": ["symlink", "copy"]
+ "enum": [
+ "symlink",
+ "copy"
+ ]
}
},
- "required": ["model", "modelPath"]
+ "required": [
+ "model",
+ "modelPath"
+ ]
},
"ImportModelResponse": {
"type": "object",
@@ -5711,7 +6290,11 @@
"example": "OK"
}
},
- "required": ["message", "modelHandle", "result"]
+ "required": [
+ "message",
+ "modelHandle",
+ "result"
+ ]
},
"CommonResponseDto": {
"type": "object",
@@ -5721,7 +6304,9 @@
"description": "The response success or error message."
}
},
- "required": ["message"]
+ "required": [
+ "message"
+ ]
},
"EngineUninstallationResponseDto": {
"type": "object",
@@ -5777,7 +6362,11 @@
"example": "OK"
}
},
- "required": ["data", "object", "result"]
+ "required": [
+ "data",
+ "object",
+ "result"
+ ]
},
"Engine": {
"type": "object",
@@ -5807,7 +6396,12 @@
"example": "0.1.34"
}
},
- "required": ["description", "name", "productName", "status"]
+ "required": [
+ "description",
+ "name",
+ "productName",
+ "status"
+ ]
},
"CpuModeDto": {
"type": "object",
@@ -5872,7 +6466,9 @@
"description": "A predefined text or framework that guides the AI model's response generation."
},
"stop": {
- "example": ["End"],
+ "example": [
+ "End"
+ ],
"description": "Defines specific tokens or phrases that signal the model to stop producing further output.",
"type": "array",
"items": {
@@ -5988,7 +6584,9 @@
"$ref": "#/components/schemas/RecommendDto"
}
},
- "required": ["id"]
+ "required": [
+ "id"
+ ]
},
"ListModelsResponseDto": {
"type": "object",
@@ -5996,7 +6594,9 @@
"object": {
"type": "string",
"example": "list",
- "enum": ["list"]
+ "enum": [
+ "list"
+ ]
},
"data": {
"description": "List of models",
@@ -6006,7 +6606,10 @@
}
}
},
- "required": ["object", "data"]
+ "required": [
+ "object",
+ "data"
+ ]
},
"UpdateModelDto": {
"type": "object",
@@ -6025,7 +6628,9 @@
"items": {
"type": "string"
},
- "example": [""]
+ "example": [
+ ""
+ ]
},
"stream": {
"type": "boolean",
@@ -6215,7 +6820,11 @@
"description": "Indicates whether the model was successfully deleted."
}
},
- "required": ["id", "object", "deleted"]
+ "required": [
+ "id",
+ "object",
+ "deleted"
+ ]
},
"CreateThreadAssistantDto": {
"type": "object",
@@ -6305,7 +6914,10 @@
"tool_resources": {
"type": "object",
"example": {
- "resources": ["database1", "database2"]
+ "resources": [
+ "database1",
+ "database2"
+ ]
},
"description": "Tool resources for the assistant."
}
@@ -6333,7 +6945,9 @@
}
}
},
- "required": ["assistants"]
+ "required": [
+ "assistants"
+ ]
},
"ContentDto": {
"type": "object",
@@ -6352,7 +6966,10 @@
"description": "Text content of the message along with any annotations."
}
},
- "required": ["type", "text"]
+ "required": [
+ "type",
+ "text"
+ ]
},
"GetMessageResponseDto": {
"type": "object",
@@ -6526,7 +7143,13 @@
"description": "Indicates whether there are more messages to retrieve."
}
},
- "required": ["object", "data", "first_id", "last_id", "has_more"]
+ "required": [
+ "object",
+ "data",
+ "first_id",
+ "last_id",
+ "has_more"
+ ]
},
"CreateMessageDto": {
"type": "object",
@@ -6542,7 +7165,10 @@
"description": "The text contents of the message."
}
},
- "required": ["role", "content"]
+ "required": [
+ "role",
+ "content"
+ ]
},
"UpdateMessageDto": {
"type": "object",
@@ -6568,7 +7194,11 @@
"description": "Indicates whether the message was successfully deleted."
}
},
- "required": ["id", "object", "deleted"]
+ "required": [
+ "id",
+ "object",
+ "deleted"
+ ]
},
"GetThreadResponseDto": {
"type": "object",
@@ -6589,7 +7219,9 @@
"description": "Unix timestamp representing the creation time of the thread."
},
"assistants": {
- "example": ["assistant-001"],
+ "example": [
+ "assistant-001"
+ ],
"description": "List of assistants involved in the thread.",
"type": "array",
"items": {
@@ -6643,7 +7275,11 @@
"description": "Indicates whether the thread was successfully deleted."
}
},
- "required": ["id", "object", "deleted"]
+ "required": [
+ "id",
+ "object",
+ "deleted"
+ ]
},
"CPUDto": {
"type": "object",
@@ -6686,7 +7322,12 @@
"description": "The model name of the CPU."
}
},
- "required": ["arch", "cores", "instructions", "model"]
+ "required": [
+ "arch",
+ "cores",
+ "instructions",
+ "model"
+ ]
},
"GPUDto": {
"type": "object",
@@ -6710,7 +7351,10 @@
"description": "The version of the installed driver."
}
},
- "required": ["compute_cap", "driver_version"]
+ "required": [
+ "compute_cap",
+ "driver_version"
+ ]
},
"free_vram": {
"type": "integer",
@@ -6768,7 +7412,10 @@
"description": "The version of the operating system."
}
},
- "required": ["name", "version"]
+ "required": [
+ "name",
+ "version"
+ ]
},
"PowerDto": {
"type": "object",
@@ -6789,7 +7436,11 @@
"description": "Indicates if the power-saving mode is enabled."
}
},
- "required": ["battery_life", "charging_status", "is_power_saving"]
+ "required": [
+ "battery_life",
+ "charging_status",
+ "is_power_saving"
+ ]
},
"RAMDto": {
"type": "object",
@@ -6810,7 +7461,11 @@
"description": "The type of RAM."
}
},
- "required": ["available", "total", "type"]
+ "required": [
+ "available",
+ "total",
+ "type"
+ ]
},
"StorageDto": {
"type": "object",
@@ -6831,8 +7486,12 @@
"description": "The type of storage."
}
},
- "required": ["available", "total", "type"]
+ "required": [
+ "available",
+ "total",
+ "type"
+ ]
}
}
}
-}
+}
\ No newline at end of file
diff --git a/engine/README.md b/engine/README.md
index 884e5efae..dec30887a 100644
--- a/engine/README.md
+++ b/engine/README.md
@@ -1,11 +1,11 @@
# cortex-cpp - Embeddable AI
> ⚠️ **cortex-cpp is currently in Development**: Expect breaking changes and bugs!
@@ -41,7 +41,7 @@ Ensure that your system meets the following requirements to run Cortex:
## Quickstart
To install Cortex CLI, follow the steps below:
-1. Download cortex-cpp here: https://github.com/janhq/cortex/releases
+1. Download cortex-cpp here: https://github.com/menloresearch/cortex/releases
2. Install cortex-cpp by running the downloaded file.
3. Download a Model:
@@ -121,37 +121,37 @@ Below is the available list of the model parameters you can set when loading a m
- 
- 
+ 
+ 
+ 
+ 
CPU
Intel
CPU