docs: new docs

docs/docs/api/assistant.md

@@ -0,0 +1,3 @@
+---
+title: Thread
+---

docs/docs/api/chat.md

@@ -0,0 +1,3 @@
+---
+title: Chat
+---

docs/docs/api/files.md

@@ -0,0 +1,3 @@
+---
+title: File
+---

docs/docs/api/message.md

@@ -0,0 +1,3 @@
+---
+title: Message
+---

docs/docs/api/model.md

@@ -0,0 +1,3 @@
+---
+title: Model
+---

docs/docs/api/overview.md

@@ -0,0 +1,4 @@
+---
+title: Overview
+position: 1
+---

docs/docs/api/thread.md

@@ -0,0 +1,3 @@
+---
+title: Chat
+---

docs/docs/developers/developers.md

@@ -1,16 +0,0 @@
----
-title: Overview
----
-Jan's mission is to power the next-gen App with limitless extensibility by providing users with the following:
-
-- Unified API/ Helpers so that they only need to care about what matters.
-- Wide range of Optimized and state-of-the-art models that can help your App with Thinking/ Hearing/ Seeing capabilities. This is powered by our [Nitro](https://github.com/janhq/nitro).
-- Strong support for the App marketplace and Model marketplace that streamline value from end customers to builders at all layers.
-- The most important thing is: The users of Jan can use the Apps via UI and API for integration.
-
-At Jan, we strongly believe in `Portable AI` and `Personal AI` that is created once and run anywhere.
-
-## Downloads
-[Jan.ai](https://jan.ai/) - Desktop app
-
-[Jan Github](https://github.com/janhq/jan) - Opensource library for developers

docs/docs/developers/plugins/azure-openai.md

@@ -1,5 +0,0 @@
----
-title: "Azure OpenAI Plugin"
----
-
-NPM Package: [@janhq/azure-openai-plugin](https://www.npmjs.com/package/@janhq/azure-openai-plugin)

docs/docs/developers/plugins/data.md

@@ -1,5 +0,0 @@
----
-title: "Data Plugin"
----
-
-NPM Package: [@janhq/data-plugin](https://www.npmjs.com/package/@janhq/data-plugin)

docs/docs/developers/plugins/inference.md

@@ -1,5 +0,0 @@
----
-title: "Inference Plugin"
----
-
-NPM Package: [@janhq/inference-plugin](https://www.npmjs.com/package/@janhq/inference-plugin)

docs/docs/developers/plugins/model-management.md

@@ -1,5 +0,0 @@
----
-title: "Model Management Plugin"
----
-
-NPM Package: [@janhq/model-management-plugin](https://www.npmjs.com/package/@janhq/model-management-plugin)

docs/docs/developers/plugins/monitoring.md

@@ -1,5 +0,0 @@
----
-title: "Monitoring Plugin"
----
-
-NPM Package: [@janhq/monitoring-plugin](https://www.npmjs.com/package/@janhq/monitoring-plugin)

docs/docs/developers/plugins/rag.md

@@ -1,5 +0,0 @@
----
-title: "RAG Plugin"
----
-
-Coming soon.

docs/docs/docs/introduction.md

@@ -0,0 +1,102 @@
+---
+title: Introduction
+---
+
+Jan can be used to build a variety of AI use cases, at every level of the stack:
+
+- An OpenAI compatible API, with feature parity for `models`, `assistants`, `files` and more
+- A standard data format on top of the user's local filesystem, allowing for transparency and composability
+- Automatically package and distribute to Mac, Windows and Linux. Cloud coming soon
+- An UI kit to customize user interactions with `assistants` and more
+- A standalone inference engine for low level use cases
+
+## Resources
+
+<!-- (@Rex: to add some quickstart tutorials) -->
+
+- Create an AI assistant
+- Run an OpenAI compatible API endpoint
+- Build a VSCode plugin with a local model
+- Build a Jan platform module
+
+## Key Concepts
+
+### Modules
+
+- Modules are modular, atomic implementations of a single OpenAI-compatible endpoint
+- Modules can be swapped out for alternate implementations
+  - The default `messages` module persists messages in thread-specific `.json`
+  - `messages-postgresql` uses Postgres for production-grade cloud-native environments
+
+| Jan Module | Description   | API Docs                     |
+| ---------- | ------------- | ---------------------------- |
+| Chat       | Inference     | [/chat](/api/chat)           |
+| Models     | Models        | [/model](/api/model)         |
+| Assistants | Apps          | [/assistant](/api/assistant) |
+| Threads    | Conversations | [/thread](/api/thread)       |
+| Messages   | Messages      | [/message](/api/message)     |
+
+![image](https://hackmd.io/_uploads/SkbP7LjmT.png)
+
+### Local Filesystem
+
+- Jan runs on top of standard structure of local files on user's filesystem
+- This allows for composability and tinkerability
+
+```sh=
+/janroot               # Jan's root folder (e.g. ~/jan)
+    /models            # For raw AI models
+    /threads           # For conversation history
+    /assistants        # For AI assistants' configs, knowledge, etc.
+```
+
+```sh=
+/models
+    /modelA
+        model.json        # Default model settings
+        llama-7b-q4.gguf  # Model binaries
+        llama-7b-q5.gguf  # Include different quantizations
+/threads
+    /jan-unixstamp-salt
+        model.json        # Overrides assistant/model-level model settings
+        thread.json       # thread metadata (e.g. subject)
+        messages.json     # messages
+        content.json      # What is this?
+        files/            # Future for RAG
+/assistants
+    /jan
+        assistant.json    # Assistant configs (see below)
+
+        # For any custom code
+        package.json      # Import npm modules
+                          # e.g. Langchain, Llamaindex
+        /src              # Supporting files (needs better name)
+            index.js      # Entrypoint
+            process.js    # For electron IPC processes (needs better name)
+
+        # `/threads` at root level
+        # `/models` at root level
+    /shakespeare
+        assistant.json
+        model.json        # Creator chooses model and settings
+        package.json
+        /src
+            index.js
+            process.js
+
+        /threads          # Assistants remember conversations in the future
+        /models           # Users can upload custom models
+            /finetuned-model
+```
+
+### Jan: a "global" assistant
+
+Jan provides `/jan`, a default assistant that is available to users out-of-the-box. It is a generic assistant to illustrate power of Jan. In the future, it will support additional features e.g. multi-assistant conversations
+
+- Your Assistant "Jan" lets you pick any model that is in the root /models folder
+- Right panel: pick LLM model and set model parameters
+- Jan’s threads will be at root level
+- `model.json` will reflect model chosen for that session
+- Be able to “add” other assistants in the future
+- Jan’s files will be at thread level
+- Jan is not a persistent memory assistant

docs/docs/docs/modules/01_chats.md

@@ -0,0 +1,29 @@
+---
+title: "Chats"
+---
+
+Chats are essentially inference requests to a model
+
+> OpenAI Equivalent: https://platform.openai.com/docs/api-reference/chat
+
+## Chat Object
+
+- Equivalent to: https://platform.openai.com/docs/api-reference/chat/object
+
+## Chat API
+
+See [/chat](/api/chat)
+
+- Equivalent to: https://platform.openai.com/docs/api-reference/chat
+
+```sh=
+POST https://localhost:1337/v1/chat/completions
+
+TODO:
+# Figure out how to incorporate tools
+```
+
+## Chat Filesystem
+
+- Chats will be persisted to `messages` within `threads`
+- There is no data structure specific to Chats

docs/docs/docs/modules/02_models.md

@@ -0,0 +1,79 @@
+---
+title: "Models"
+---
+
+Models are AI models like Llama and Mistral
+
+> OpenAI Equivalent: https://platform.openai.com/docs/api-reference/models
+
+## Model Object
+
+- `model.json`
+
+> Equivalent to: https://platform.openai.com/docs/api-reference/models/object
+
+```json=
+{
+    // OpenAI model compatibility
+    // https://platform.openai.com/docs/api-reference/models)
+    "id": "llama-2-uuid",
+    "object": "model",
+    "created": 1686935002,
+    "owned_by": "you"
+
+    // Model settings (benchmark: Ollama)
+    // https://github.com/jmorganca/ollama/blob/main/docs/modelfile.md#template
+    "model_name": "llama2",
+    "model_path": "ROOT/models/...",
+    "parameters": {
+        "temperature": "..",
+        "token-limit": "..",
+        "top-k": "..",
+        "top-p": ".."
+    },
+    "template": "This is a full prompt template",
+    "system": "This is a system prompt",
+
+    // Model metadata (benchmark: HuggingFace)
+    "version": "...",
+    "author": "...",
+    "tags": "...",
+    ...
+}
+```
+
+## Model API
+
+See [/model](/api/model)
+
+- Equivalent to: https://platform.openai.com/docs/api-reference/models
+
+```sh=
+GET https://localhost:1337/v1/models             # List models
+GET https://localhost:1337/v1/models/{model}     # Get model object
+DELETE https://localhost:1337/v1/models/{model}  # Delete model
+
+TODO:
+# Start model
+# Stop model
+```
+
+## Model Filesystem
+
+```sh
+/janroot
+    /models
+        /modelA
+            model.json         # Default model params
+            modelA.gguf
+            modelA.bin
+        /modelB/*
+            model.json
+            modelB.gguf
+    /assistants
+        model.json             # Defines model, default: looks in `/models`
+        /models                # Optional /models folder that overrides root
+            /modelA
+                model.json
+                modelA.bin
+```

docs/docs/docs/modules/03_assistants.md

@@ -0,0 +1,80 @@
+---
+title: "Assistants"
+---
+
+Assistants can use models and tools.
+
+- Jan's `Assistants` are even more powerful than OpenAI due to customizable code in `index.js`
+
+> OpenAI Equivalent: https://platform.openai.com/docs/api-reference/assistants
+
+## Assistant Object
+
+- `assistant.json`
+- Equivalent to: https://platform.openai.com/docs/api-reference/assistants/object
+
+```json=
+{
+  // Jan specific properties
+  "avatar": "https://lala.png"
+  "thread_location": "ROOT/threads"  // Default to root (optional field)
+  // TODO: add moar
+
+  // OpenAI compatible properties: https://platform.openai.com/docs/api-reference/assistants
+  "id": "asst_abc123",
+  "object": "assistant",
+  "created_at": 1698984975,
+  "name": "Math Tutor",
+  "description": null,
+  "model": reference model.json,
+  "instructions": reference model.json,
+  "tools": [
+    {
+      "type": "rag"
+    }
+  ],
+  "file_ids": [],
+  "metadata": {}
+}
+```
+
+## Assistants API
+
+- _TODO_: What would modifying Assistant do? (doesn't mutate `index.js`?)
+
+```sh=
+GET https://api.openai.com/v1/assistants                       # List
+POST https://api.openai.com/v1/assistants                      # C
+GET https://api.openai.com/v1/assistants/{assistant_id}        # R
+POST https://api.openai.com/v1/assistants/{assistant_id}       # U
+DELETE https://api.openai.com/v1/assistants/{assistant_id}     # D
+```
+
+## Assistants Filesystem
+
+```sh=
+/assistants
+    /jan
+        assistant.json    # Assistant configs (see below)
+
+        # For any custom code
+        package.json      # Import npm modules
+                          # e.g. Langchain, Llamaindex
+        /src              # Supporting files (needs better name)
+            index.js      # Entrypoint
+            process.js    # For electron IPC processes (needs better name)
+
+        # `/threads` at root level
+        # `/models` at root level
+    /shakespeare
+        assistant.json
+        model.json        # Creator chooses model and settings
+        package.json
+        /src
+            index.js
+            process.js
+
+        /threads          # Assistants remember conversations in the future
+        /models           # Users can upload custom models
+            /finetuned-model
+```

docs/docs/docs/modules/04_threads.md

@@ -0,0 +1,53 @@
+---
+title: "Threads"
+---
+
+Threads contain `messages` history with assistants. Messages in a thread share context.
+
+- Note: For now, threads "lock the model" after a `message` is sent
+  - When a new `thread` is created with Jan, users can choose the models
+  - Users can still edit model parameters/system prompts
+  - Note: future Assistants may customize this behavior
+- Note: Assistants will be able to specify default thread location in the future
+  - Jan uses root-level threads, to allow for future multi-assistant threads
+  - Assistant Y may store threads in its own folder, to allow for [long-term assistant memory](https://github.com/janhq/jan/issues/344)
+
+> OpenAI Equivalent: https://platform.openai.com/docs/api-reference/threads
+
+## Thread Object
+
+- `thread.json`
+- Equivalent to: https://platform.openai.com/docs/api-reference/threads/object
+
+```json
+{
+  // Jan specific properties:
+  "summary": "HCMC restaurant recommendations",
+  "messages": {see below}
+
+  // OpenAI compatible properties: https://platform.openai.com/docs/api-reference/threads)
+  "id": "thread_abc123",
+  "object": "thread",
+  "created_at": 1698107661,
+  "metadata": {}
+}
+```
+
+## Threads API
+
+- Equivalent to: https://platform.openai.com/docs/api-reference/threads
+
+```sh=
+POST https://localhost:1337/v1/threads/{thread_id}   # Create thread
+GET https://localhost:1337/v1/threads/{thread_id}    # Get thread
+DELETE https://localhost:1337/v1/models/{thread_id}      # Delete thread
+```
+
+## Threads Filesystem
+
+```sh
+/assistants
+    /homework-helper
+        /threads                # context is "permanently remembered" by assistant in future conversations
+/threads                        # context is only retained within a single thread
+```

docs/docs/docs/modules/05_messages.md

@@ -0,0 +1,53 @@
+---
+title: "Messages"
+---
+
+Messages are within `threads` and capture additional metadata.
+
+- Equivalent to: https://platform.openai.com/docs/api-reference/messages
+
+## Message Object
+
+- Equivalent to: https://platform.openai.com/docs/api-reference/messages/object
+
+```json
+{
+  // Jan specific properties
+  "updatedAt": "..." // that's it I think
+
+  // OpenAI compatible properties: https://platform.openai.com/docs/api-reference/messages)
+  "id": "msg_dKYDWyQvtjDBi3tudL1yWKDa",
+  "object": "thread.message",
+  "created_at": 1698983503,
+  "thread_id": "thread_RGUhOuO9b2nrktrmsQ2uSR6I",
+  "role": "assistant",
+  "content": [
+    {
+      "type": "text",
+      "text": {
+        "value": "Hi! How can I help you today?",
+        "annotations": []
+      }
+    }
+  ],
+  "file_ids": [],
+  "assistant_id": "asst_ToSF7Gb04YMj8AMMm50ZLLtY",
+  "run_id": "run_BjylUJgDqYK9bOhy4yjAiMrn",
+  "metadata": {}
+}
+```
+
+## Messages API
+
+- Equivalent to: https://platform.openai.com/docs/api-reference/messages
+
+```sh=
+POST https://api.openai.com/v1/threads/{thread_id}/messages # create msg
+GET https://api.openai.com/v1/threads/{thread_id}/messages  # list messages
+GET https://api.openai.com/v1/threads/{thread_id}/messages/{message_id}
+
+# Get message file
+GET https://api.openai.com/v1/threads/{thread_id}/messages/{message_id}/files/{file_id}
+# List message files
+GET https://api.openai.com/v1/threads/{thread_id}/messages/{message_id}/files
+```

docs/docs/docs/modules/06_files.md

@@ -0,0 +1,43 @@
+---
+title: "Files"
+---
+
+Files can be used by `threads`, `assistants` and `fine-tuning`
+
+> Equivalent to: https://platform.openai.com/docs/api-reference/files
+
+## Files Object
+
+- Equivalent to: https://platform.openai.com/docs/api-reference/files
+- Note: OAI's struct doesn't seem very well designed
+- `files.json`
+
+```json
+{
+  // Public properties (OpenAI Compatible: https://platform.openai.com/docs/api-reference/files/object)
+  "id": "file-BK7bzQj3FfZFXr7DbL6xJwfo",
+  "object": "file",
+  "bytes": 120000,
+  "created_at": 1677610602,
+  "filename": "salesOverview.pdf",
+  "purpose": "assistants"
+}
+```
+
+## File API
+
+## Files Filesystem
+
+- Files can exist in several parts of Jan's filesystem
+- TODO: are files hard copied into these folders? Or do we define a `files.json` and only record the relative filepath?
+
+```sh=
+/files                  # root `/files` for finetuning, etc
+/assistants
+    /jan
+        /files          # assistant-specific files
+/threads
+    /jan-12938912
+        /files          # thread-specific files
+
+```

docs/docs/docs/user-interface.md

@@ -0,0 +1,67 @@
+---
+title: User Interface
+---
+
+Jan provides a UI Kit for customize the UI for your use case. This means you can personalize the entire application according to your own brand and visual styles.
+
+This page gives you an overview of how to customize the UI.
+
+You can see some of the user interface components when you first open Jan.
+
+To Link:
+
+- Ribbon
+- LeftSidebar
+- Main
+- RightSidebar
+- StatusBar
+
+## Views
+
+![Jan Views](./img/jan-views.png)
+TODO: add a better image.
+
+### Ribbon
+
+Assistants shortcuts and Modules settings show up here.
+
+```js
+import .. from "@jan"
+sample code here
+```
+
+### LeftSidebar
+
+Conversation threads show up here. This is customizable, so custom assistants can add additional menu items here.
+
+```js
+import .. from "@jan"
+sample code here
+```
+
+### Main
+
+The main view for interacting with assistants. This is customizable, so custom assistants can add in additional UI components. By default, this is a chat thread with assistants.
+
+```js
+import .. from "@jan"
+sample code here
+```
+
+### RightSidebar
+
+A "settings" view for each thread. Users should be able to edit settings or other configs to customize the assistant experience within each thread.
+
+```js
+import .. from "@jan"
+sample code here
+```
+
+### StatusBar
+
+A global status bar that shows processes, hardware/disk utilization and more.
+
+```js
+import .. from "@jan"
+sample code here
+```

docs/docs/guides/install/cloud-native.md

@@ -1,44 +0,0 @@
----
-title: Cloud Native
----
-
-# Installing Jan Cloud Native
-
-Cloud Native is useful when you want to deploy Jan to a shared/remote/cloud server, rather than running it as a local Desktop app.
-
-> This is an experimental feature - expect breaking changes!
-
-### Getting Started
-
-#### Run from source code
-
-```bash
-git clone https://github.com/janhq/jan
-cd jan
-git checkout feat-255 && git pull
-yarn install
-yarn start:server
-```
-
-Open your browser at [http://localhost:4000](http://localhost:4000)
-
-### Run from docker file
-
-```bash
-git clone https://github.com/janhq/jan
-cd jan
-git checkout feat-255 && git pull
-docker build --platform linux/x86_64 --progress=plain  -t jan-server .
-docker run --platform linux/x86_64 --name jan-server  -p4000:4000 -p3928:3928 -it jan-server
-```
-
-Open your browser at [http://localhost:4000](http://localhost:4000)
-
-### Architecture
-
-![cloudnative](../../developers/img/cloudnative.png)
-
-### TODOs
-
-- [Authencation Plugins](https://github.com/janhq/jan/issues/334)
-- [Remote server](https://github.com/janhq/jan/issues/200)

docs/docs/nitro/nitro.md

@@ -1,5 +1,5 @@
 ---
-title: Nitro 
+title: Nitro
 slug: /nitro
 ---
 
@@ -73,4 +73,4 @@ curl -X POST 'http://localhost:3928/inferences/llamacpp/loadmodel' \
 
 ## Architecture diagram
 
-![Nitro Architecture](../developers/img/architecture.png)
+![Nitro Architecture](../docs/img/architecture.png)

docs/docusaurus.config.js

@@ -129,9 +129,15 @@ const config = {
           },
           {
             type: "docSidebar",
-            sidebarId: "devSidebar",
+            sidebarId: "docsSidebar",
             position: "left",
-            label: "Developers",
+            label: "Documentation",
+          },
+          {
+            type: "docSidebar",
+            sidebarId: "apiSidebar",
+            position: "left",
+            label: "API Reference",
           },
           // Navbar right
           {

docs/sidebars.js

@@ -38,51 +38,43 @@ const sidebars = {
       collapsed: true,
       link: { type: "doc", id: "guides/install/install" },
       items: [
-        "guides/install/linux",
-        "guides/install/windows",
-        "guides/install/mac",
-        "guides/install/cloud-native",
+        {
+          type: "autogenerated",
+          dirName: "guides/install",
+        },
       ],
     },
     "guides/troubleshooting",
   ],
 
-  devSidebar: [
-    "developers/developers",
-    "nitro/nitro",
+  docsSidebar: [
+    "docs/introduction",
     {
       type: "category",
-      label: "Apps",
+      label: "Modules",
       collapsible: true,
-      collapsed: true,
+      collapsed: false,
       items: [
         {
           type: "autogenerated",
-          dirName: "developers/apps",
+          dirName: "docs/modules",
         },
       ],
     },
+    "docs/user-interface",
+  ],
+
+  apiSidebar: [
+    "api/overview",
     {
       type: "category",
-      label: "Plugins",
+      label: "Endpoints",
       collapsible: true,
-      collapsed: true,
+      collapsed: false,
       items: [
         {
           type: "autogenerated",
-          dirName: "developers/plugins",
-        },
-      ],
-    },
-    {
-      type: "category",
-      label: "API Reference",
-      collapsible: true,
-      collapsed: true,
-      items: [
-        {
-          type: "autogenerated",
-          dirName: "reference",
+          dirName: "api",
         },
       ],
     },