diff --git a/docs/src/pages/docs/_assets/jan-app.png b/docs/src/pages/docs/_assets/jan-app.png index a45943055..2490d925a 100644 Binary files a/docs/src/pages/docs/_assets/jan-app.png and b/docs/src/pages/docs/_assets/jan-app.png differ diff --git a/docs/src/pages/docs/index.mdx b/docs/src/pages/docs/index.mdx index b6306498e..23c5e3ae9 100644 --- a/docs/src/pages/docs/index.mdx +++ b/docs/src/pages/docs/index.mdx @@ -25,7 +25,7 @@ import FAQBox from '@/components/FaqBox' ![Jan's Cover Image](./_assets/jan-app.png) -Jan is a ChatGPT-alternative that runs 100% offline on your [Desktop](/docs/desktop-installation). Our goal is to make it easy for a layperson[^1] to download and run LLMs and use AI with full control and [privacy](https://www.reuters.com/legal/legalindustry/privacy-paradox-with-ai-2023-10-31/). +Jan is a ChatGPT-alternative that runs 100% offline on your desktop & mobile (*comming soon*). Our goal is to make it easy for a layperson[^1] to download and run LLMs and use AI with full control and [privacy](https://www.reuters.com/legal/legalindustry/privacy-paradox-with-ai-2023-10-31/). Jan is powered by [Cortex](https://cortex.so/), our embeddable local AI engine. @@ -38,10 +38,10 @@ You'll be able to use it with [Continue.dev](https://jan.ai/integrations/coding/ ### Features - Download popular open-source LLMs (Llama3, Gemma or Mistral,...) from [Model Hub](./docs/models/manage-models.mdx) or import any GGUF models -- Connect to [cloud model services](https://jan.ai/docs/remote-inference/openai) (OpenAI, Anthropic, Mistral, Groq,...) +- Connect to [cloud model services](/docs/remote-models/openai) (OpenAI, Anthropic, Mistral, Groq,...) - [Chat](./docs/threads.mdx) with AI models & [customize their parameters](./docs/models/model-parameters.mdx) in an intuitive interface - Use [local API server](https://jan.ai/api-reference) with OpenAI-equivalent API -- Customize Jan with [extensions](https://jan.ai/docs/extensions) +- Customize Jan with [extensions](/docs/extensions) ### Philosophy @@ -50,7 +50,7 @@ Jan is built to be [user-owned](about#-user-owned): - [Local-first](https://www.inkandswitch.com/local-first/), with all data stored locally - Runs 100% offline, with privacy by default - Free choice of AI models, both local and cloud-based -- We do not [collect or sell user data](/privacy) +- We do not collect or sell user data. See our [Privacy](/privacy). You can read more about our [philosophy](/about#philosophy) here. @@ -77,25 +77,27 @@ Jan is built on the shoulders of many upstream open-source projects: - Download Jan Desktop on your computer, download a compatible LLM, connect to a remote AI with the API key, and start chatting. You can switch between models as needed. + Download Jan on your computer, download a compatible model or connect to a cloud AI, and start chatting. See details in our [Quick Start](/docs/quickstart) guide. - Jan is available for Mac, Windows, and Linux, ensuring wide compatibility. + See our comapatibility guide for [Mac](/docs/desktop/mac#compatibility), [Windows](/docs/desktop/windows#compatibility), and [Linux](docs/desktop/linux). GPU-wise, Jan supports: - NVIDIA GPUs (CUDA) - AMD GPUs (Vulkan) - Intel Arc GPUs (Vulkan) - Other GPUs with Vulkan support + + - + No data is collected. Everything stays local on your device. When using cloud AI services (like GPT-4 or Claude) through Jan, their data collection is outside our control. Please check their privacy policies. - You can help improve Jan by choosing to opt in anonymous basic usage data (like feature usage and user counts). Even so, your chats and personal information are never collected. Read more about what data you can contribute to us at [Privacy](./docs/privacy.mdx). + You can help improve Jan by choosing to opt in anonymous basic usage data. Even so, your chats and personal information are never collected. Read more about what data you can contribute to us at [Privacy](./docs/privacy.mdx). @@ -104,35 +106,31 @@ When using cloud AI services (like GPT-4 or Claude) through Jan, their data coll - Jan prioritizes your privacy by running open-source AI models 100% offline on your computer. Conversations, documents, and files stay on your device in the Jan Data Folder located at: + Jan prioritizes your privacy by running open-source AI models 100% offline on your computer. Conversations, documents, and files stay on your device in [Jan Data Folder](/docs/data-folder) located at: - Windows: `%APPDATA%/Jan/data` - Linux: `$XDG_CONFIG_HOME/Jan/data` or `~/.config/Jan/data` - macOS: `~/Library/Application Support/Jan/data` - - Jan stands for โ€œJust a Name". We are, admittedly, bad at marketing ๐Ÿ˜‚. - - - Yes, Jan can run without an internet connection, but you'll need to download a local model first. Once you've downloaded your preferred models, Jan will work entirely offline by default. + Yes, Jan can run without an internet connection, but you'll need to [download a local model](/docs/models/manage-models#1-download-from-jan-hub-recommended) first. Once you've downloaded your preferred models, Jan will work entirely offline by default. Jan is free and open-source. There are no subscription fees or hidden costs for all local models & features. - To use cloud AI models (like GPT-4 or Claude): + To use [cloud AI models](/docs/models/manage-models#cloud-model) (like GPT-4 or Claude): - You'll need to have your own API keys & pay the standard rates charged by those providers. - Jan doesn't add any markup. - - Models from Jan's Hub are recommended for best compatibility. - - You can also import GGUF models from Hugging Face or your device. + - Models from [Jan Hub](/docs/models/manage-models#1-download-from-jan-hub-recommended) are recommended for best compatibility. + - You can also [import GGUF models](/docs/models/manage-models#2-import-from-hugging-face) from Hugging Face or from your local files. -Jan has an extensible architecture like VSCode and Obsidian - you can build custom features using our extensions API. Most of Jan's features are actually built as extensions. +Jan has an extensible architecture like VSCode and Obsidian - you can build custom features using our extensions API. Most of Jan's features are actually built as [extensions](/docs/extensions). @@ -145,6 +143,7 @@ Jan has an extensible architecture like VSCode and Obsidian - you can build cust For troubleshooting, please visit [Troubleshooting](./docs/troubleshooting.mdx). + In case you can't find what you need in our troubleshooting guide, please reach out to us for extra help on our [Discord](https://discord.com/invite/FTk2MvZwJH) in the **#๐Ÿ†˜|get-help** channel. @@ -154,6 +153,10 @@ Jan has an extensible architecture like VSCode and Obsidian - you can build cust - Fork and build from our [GitHub](https://github.com/janhq/jan) repository. + + Jan stands for โ€œJust a Name". We are, admittedly, bad at marketing ๐Ÿ˜‚. + + Yes! We love hiring from our community. Check out our open positions at [Careers](https://homebrew.bamboohr.com/careers). diff --git a/docs/src/pages/docs/models/manage-models.mdx b/docs/src/pages/docs/models/manage-models.mdx index b67d825e2..69df4cfcb 100644 --- a/docs/src/pages/docs/models/manage-models.mdx +++ b/docs/src/pages/docs/models/manage-models.mdx @@ -57,7 +57,7 @@ You can import GGUF models directly from [Hugging Face](https://huggingface.co/) 5. Select your preferred quantized version to download
-![Download Model](../_assets/model-management-02.png) +![Import Model](../_assets/model-management-02.png)
##### Option B: Use Deep Link @@ -81,7 +81,7 @@ Deep linking won't work for models requiring API tokens or usage agreements. You
-![Downlosd Model](../_assets/model-management-03.png) +![Deep Link](../_assets/model-management-03.png)