feat(docs): reworked the website (#1523)

Docs time !

docs/docs/Developers/_category_.json

@@ -0,0 +1,8 @@
+{
+  "label": "🧑‍💻 Developer Docs",
+  "position": 3,
+  "link": {
+    "type": "generated-index",
+    "description": "How to use Quivr as a Dev ?"
+  }
+}

docs/docs/Developers/backend/_category_.json

@@ -1,8 +1,8 @@
 {
-  "label": "Quivr's Brain",
-  "position": 3,
+  "label": "API",
+  "position": 1,
   "link": {
     "type": "generated-index",
     "description": "How does the backend works?"
   }
-}
+}

docs/docs/Developers/backend/api/chat.md

@@ -43,7 +43,7 @@ Users can create multiple chat sessions, each with its own set of chat messages.
    - Description: This endpoint allows adding a new question to a chat. It generates an answer for the question using different models based on the provided model type.
 
    Models like gpt-4-0613 and gpt-3.5-turbo-0613 use a custom OpenAI function-based answer generator.
-   ![Function based answer generator](../../../static/img/answer_schema.png)
+   ![Function based answer generator](../../../../static/img/answer_schema.png)
 
 6. **Get the chat history:**
    - HTTP method: GET

docs/docs/Developers/backend/chains/qa.md

@@ -4,7 +4,7 @@ sidebar_position: 1
 
 # Introduction to Chains
 
-Quivr uses a framework called [Langchain](https://python.langchain.com/docs/get_started/introduction.html) for the majority of the interaction with the Large Language Models (LLMs).
+Quivr uses a framework called [Langchain](https://python.langchain.com/docs/introduction.html) for the majority of the interaction with the Large Language Models (LLMs).
 
 Langchain provides functionality to connect multiple components such as LLMs, document retrievers, and other components together to form a "chain" of components.
 

docs/docs/Developers/backend/intro.md

@@ -31,5 +31,5 @@ Authorization: Bearer {api_key}
 
 Replace `{api_key}` with the generated API key obtained from the frontend
 
-You can find more information in the [Authentication](/docs/backend/api/getting_started) section of the documentation.
+You can find more information in the [Authentication](/docs/Developers/backend/api/getting_started) section of the documentation.
 

docs/docs/Developers/frontend/_category_.json

@@ -1,7 +1,7 @@
 {
-  "label": "Quivr's Face",
-  "position": 4,
+  "label": "Frontend",
+  "position": 2,
   "link": {
     "type": "generated-index"
   }
-}
+}

docs/docs/Developers/llm/_category_.json

@@ -1,6 +1,6 @@
 {
   "label": "LLM",
-  "position": 2,
+  "position": 3,
   "link": {
     "type": "generated-index",
     "description": "How does the LLM (Large Language Model Work)?"

docs/docs/Developers/llm/private-llm.md

@@ -0,0 +1,36 @@
+---
+sidebar_position: 1
+title: Hugging Face Integration 🤗
+---
+
+# Private Language Models with Quivr
+
+Quivr introduces the groundbreaking feature of integrating private Large Language Models (LLMs) powered by HuggingFace. This enhancement ensures your data's confidentiality, as all processing is performed locally on your server.
+
+## Running Mistral with Huggingface Inference Endpoint
+
+### 1. Deploy the Model
+- Navigate to the [Mistral AI model page](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on Huggingface.
+- Select the option for 'Inference Endpoints'.
+- Please note that we recommend the Mistral 7B Instruct model, especially tailored for chat applications.
+
+### 2. Create the Endpoint
+- Feel free to assign a custom name to your endpoint.
+- Select a location and adhere to the recommended instance size.
+- Click to confirm and create your endpoint.
+
+### 3. Obtain Credentials
+- Allow some time for your instance to initialize.
+- Securely copy both the API URL and your Bearer Token for future use.
+
+### 4. Install Quivr
+- To set up Quivr, kindly follow the concise 3-step installation guide provided in our [readme.md](https://github.com/Quivr/README.md).
+- Important: Configure environmental variables in your backend/.env file, including the Huggingface API key for seamless integration.
+
+### 5. Configure Your Supabase Instance
+- Within your Supabase instance, locate the user_settings table.
+- Here, input the following path: "huggingface/mistralai/Mistral-7B-Instruct-v0.1".
+
+As a result, you'll have Quivr running locally with Mistral, now hosted via Huggingface. For those interested in a hassle-free experience, visit [Quivr.app](https://quivr.app) to leverage Mistral at no cost, all thanks to Huggingface. The source code for this setup is [available here](https://github.com/Quivr/SourceCode).
+
+Experience the enhanced privacy and control with Quivr's Private LLM feature today!

docs/docs/Reference/_category_.json

@@ -1,3 +1,4 @@
 {
-  "position": 4
+  "position": 4,
+  "label": "📚 Reference"
 }

docs/docs/User_Guide/_category_.json

@@ -1,8 +1,8 @@
 {
-  "label": "Getting Started",
-  "position": 1,
+  "label": "🕺 User Guide",
+  "position": 2,
   "link": {
     "type": "generated-index",
     "description": "How to start using Quivr"
   }
-}
+}

docs/docs/backend/llm/private-llm.md

@@ -1,23 +0,0 @@
----
-sidebar_position: 1
----
-
-# Private LLM
-
-Quivr now has the capability to use a private LLM model powered by GPT4All (other open source models coming soon).
-
-This is similar to the functionality provided by the PrivateGPT project.
-
-This means that your data never leaves the server. The LLM is downloaded to the server and runs inference on your question locally.
-
-## How to use
-
-Set the 'private' flag to True in the /backend/.env file. You can also set other model parameters in the .env file.
-
-Download the GPT4All model from [here](https://gpt4all.io/models/ggml-gpt4all-j-v1.3-groovy.bin) and place it in the /backend/local_models folder. Or you can download any model from their ecosystem on their [website](https://gpt4all.io/index.html).
-
-## Future Plans
-
-We are planning to add more models to the private LLM feature. We are also planning on using a local embedding model from Hugging Face to reduce our reliance on OpenAI's API.
-
-We will also be adding the ability to use a private LLM model from the frontend and api. Currently it is only available if you self host the backend.

docs/docs/contributions.md

@@ -1,21 +1,31 @@
+---
+sidebar_position: 4
+title: 🆘 Contributing
+---
 # Contributing to Quivr
 
 Thanks for your interest in contributing to Quivr! Here you'll find guidelines for contributing and steps on how you can contribute.
 
 ## Table of Contents
 
-- [Community](#community)
-- [Roadmap](#roadmap-and-issues)
-- [How to Contribute](#how-to-contribute)
-  - [Reporting Bugs](#reporting-bugs)
-  - [Feature Requests](#feature-requests)
-  - [Code Contributions](#code-contributions)
-- [Submission Guidelines](#submission-guidelines)
-- [Coding Rules](#coding-rules)
-  - [Frontend Guidelines](#frontend-guidelines)
-  - [Backend Guidelines](#backend-guidelines)
-- [Making a Pull Request](#making-a-pull-request)
-- [Contact](#contact)
+- [Contributing to Quivr](#contributing-to-quivr)
+  - [Table of Contents](#table-of-contents)
+  - [Community](#community)
+  - [Roadmap and Issues](#roadmap-and-issues)
+  - [How to Contribute](#how-to-contribute)
+    - [Reporting Bugs](#reporting-bugs)
+    - [Feature Requests](#feature-requests)
+    - [Code Contributions](#code-contributions)
+  - [Submission Guidelines](#submission-guidelines)
+  - [Coding Rules](#coding-rules)
+    - [Frontend Guidelines](#frontend-guidelines)
+      - [Coding Conventions](#coding-conventions)
+      - [Testing](#testing)
+    - [Backend Guidelines](#backend-guidelines)
+      - [Coding Conventions](#coding-conventions-1)
+      - [Testing](#testing-1)
+  - [Making a Pull Request](#making-a-pull-request)
+  - [Contact](#contact)
 
 ## Community
 

docs/docs/get_started/intro.md

@@ -1,144 +0,0 @@
----
-sidebar_position: 1
-title: Getting Started
----
-
-# Intro
-
-Quivr, your second brain, utilizes the power of GenerativeAI to store and retrieve unstructured information. Think of it as Obsidian, but turbocharged with AI capabilities.
-
-## Key Features 🎯
-
-- **Universal Data Acceptance**: Quivr can handle almost any type of data you throw at it. Text, images, code snippets, we've got you covered.
-- **Generative AI**: Quivr employs advanced AI to assist you in generating and retrieving information.
-- **Fast and Efficient**: Designed with speed and efficiency at its core. Quivr ensures rapid access to your data.
-- **Secure**: Your data, your control. Always.
-- **File Compatibility**:
-  - Text
-  - Markdown
-  - PDF
-  - Powerpoint
-  - Excel
-  - Word
-  - Audio
-  - Video
-- **Open Source**: Freedom is beautiful, so is Quivr. Open source and free to use.
-
-## Demo Highlights 🎥
-
-### **Demo**:
-
-<video width="640" height="480" controls>
-  <source src="https://github.com/StanGirard/quivr/assets/19614572/a6463b73-76c7-4bc0-978d-70562dca71f5" type="video/mp4"/>
-  Your browser does not support the video tag.
-</video>
-
-## Getting Started: 🚀
-
-Follow these instructions to get a copy of the project up and running on your local machine for development and testing purposes.
-
-You can find everything on the documentation [here](https://brain.quivr.app/)
-
-### Prerequisites 📋
-
-Before you proceed, ensure you have the following installed:
-
-- Docker
-- Docker Compose
-
-Additionally, you'll need a [Supabase](https://supabase.com/) account for:
-
-- Creating a new Supabase project
-- Supabase Project API key
-- Supabase Project URL
-
-### Installation Steps 💽
-
-- **Step 0**: If needed, here is the installation explained on Youtube [here](https://youtu.be/rC-s4QdfY80)
-
-- **Step 1**: Clone the repository using **one** of these commands:
-
-  - If you don't have an SSH key set up:
-
-  ```bash
-  git clone https://github.com/StanGirard/Quivr.git && cd Quivr
-  ```
-
-  - If you have an SSH key set up or want to add it ([guide here](https://docs.github.com/en/authentication/connecting-to-github-with-ssh/adding-a-new-ssh-key-to-your-github-account))
-
-  ```bash
-  git clone git@github.com:StanGirard/Quivr.git && cd Quivr
-  ```
-
-- **Step 2**: Copy the `.XXXXX_env` files
-
-```bash
-cp .backend_env.example backend/.env
-cp .frontend_env.example frontend/.env
-```
-
-- **Step 3**: Update the `backend/.env` and `frontend/.env` file
-
-> _Your `supabase_service_key` can be found in your Supabase dashboard under Project Settings -> API. Use the `anon` `public` key found in the `Project API keys` section._
-
-> _Your `JWT_SECRET_KEY`can be found in your supabase settings under Project Settings -> API -> JWT Settings -> JWT Secret_
-
-> _The `NEXT_PUBLIC_BACKEND_URL` is set to localhost:5050 for the docker. Update it if you are running the backend on a different machine._
-
-> _To activate vertexAI with PaLM from GCP follow the instructions [here](https://python.langchain.com/en/latest/modules/models/llms/integrations/google_vertex_ai_palm.html) and update `backend/.env`- It is an advanced feature, please be expert in GCP before trying to use it_
-
-- [ ] Change variables in `backend/.env`
-- [ ] Change variables in `frontend/.env`
-
-- **Step 4**: Create your database tables and functions with one of these two options:
-  a. Run the following migration scripts on the Supabase database via the web interface (SQL Editor -> `New query`)
-
-[Creation Script 1](https://github.com/stangirard/quivr/tree/main/scripts/tables.sql)
-
-b. Use the `migration.sh` script to run the migration scripts
-
-    ```bash
-    chmod +x migration.sh
-    ./migration.sh
-    ```
-
-    Choose either create_scripts if it's your first time or migrations if you are updating your database.
-
-All the scripts can be found in the [scripts](https://github.com/stangirard/quivr/tree/main/scripts) folder
-
-> _If you come from an old version of Quivr, run the scripts in [migration script](https://github.com/stangirard/quivr/tree/main/scripts) to migrate your data to the new version in the order of date_
-
-- **Step 5**: Launch the app
-
-```bash
-docker compose up --build
-```
-
-- **Step 6**: Navigate to `localhost:3000` in your browser
-
-- **Step 7**: Want to contribute to the project?
-
-```
-docker compose -f docker-compose.dev.yml up --build
-```
-
-## Contributors ✨
-
-Thanks goes to these wonderful people:
-<a href="https://github.com/stangirard/quivr/graphs/contributors">
-<img src="https://contrib.rocks/image?repo=stangirard/quivr" />
-</a>
-
-## Contribute 🤝
-
-Got a pull request? Open it, and we'll review it as soon as possible. Check out our project board [here](https://github.com/users/StanGirard/projects/5) to see what we're currently focused on, and feel free to bring your fresh ideas to the table!
-
-- [Open Issues](https://github.com/StanGirard/quivr/issues)
-- [Open Pull Requests](https://github.com/StanGirard/quivr/pulls)
-- [Good First Issues](https://github.com/StanGirard/quivr/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22)
-- [Frontend Issues](https://github.com/StanGirard/quivr/issues?q=is%3Aopen+is%3Aissue+label%3Afrontend)
-- [Backend Issues](https://github.com/StanGirard/quivr/issues?q=is%3Aopen+is%3Aissue+label%3Abackend)
-
-## License 📄
-
-This project is licensed under the Apache 2.0 License - see the [LICENSE.md](https://github.com/StanGirard/quivr/blob/main/LICENSE) file for details

docs/docs/intro.md

@@ -0,0 +1,34 @@
+---
+sidebar_position: 1
+title: 🚀 Welcome to Quivr
+---
+
+# Intro
+
+Quivr, your second brain, utilizes the power of GenerativeAI to store and retrieve unstructured information. Think of it as Obsidian, but turbocharged with AI capabilities.
+
+## Key Features 🎯
+
+- **Universal Data Acceptance**: Quivr can handle almost any type of data you throw at it. Text, images, code snippets, we've got you covered.
+- **Generative AI**: Quivr employs advanced AI to assist you in generating and retrieving information.
+- **Fast and Efficient**: Designed with speed and efficiency at its core. Quivr ensures rapid access to your data.
+- **Secure**: Your data, your control. Always.
+- **File Compatibility**:
+  - Text
+  - Markdown
+  - PDF
+  - Powerpoint
+  - Excel
+  - Word
+  - Audio
+  - Video
+- **Open Source**: Freedom is beautiful, so is Quivr. Open source and free to use.
+
+## Demo Highlights 🎥
+
+### **Demo**:
+
+<video width="640" height="480" controls>
+  <source src="https://github.com/StanGirard/quivr/assets/19614572/a6463b73-76c7-4bc0-978d-70562dca71f5" type="video/mp4"/>
+  Your browser does not support the video tag.
+</video>

docs/docs/privacy_policy.md

@@ -1,6 +1,6 @@
 ---
 sidebar_position: 6
-title: Privacy Policy
+title: 👀 Privacy Policy
 ---
 
 ## Privacy Policy for Quivr

docs/docs/roadmap.md

@@ -1,48 +1,9 @@
 ---
 sidebar_position: 5
+title: 🎯 Roadmap
 ---
 
 # Roadmap
 
-## 🚀 What's next?
-
-<iframe  width="800" height="450" src="https://whimsical.com/embed/U1XffvPhZxXtNT5Y2ucGvg"></iframe>
-
-
-
-## The Vision
-
-Quivr is a platform for building second brains and personnal assistants. It is a tool for thinking, learning and creating. 
-
-- [X] **v0.1** - the Webapp
-  - [x] Basic CRUD operations
-  - [X] Basic authentication
-  - [X] One brain per user
-  - [X] Multiple chats
-  - [X] Use own keys
-- [ ] **v0.2** - Time to share
-  - [X] Improved Documentation
-    - [ ] Add a tutorial
-    - [ ] Add a FAQ
-    - [X] Create a website - https://brain.quivr.app
-  - [X] Create public & private brains
-  - [ ] Allow users to share/subcribe brains 
-  - [ ] Improved UX/UI
-    - [ ] Stream response
-    - [X] Better error handling
-    - [X] Mobile friendly
-  - [ ] Chat with one or more files
-  - [X] Better API Interface 
-  - [ ] Refactor backend & frontend for better development experience
-- [ ] **v0.3** - Make it smarter & private
-  - [ ] Private Brains
-    - [X] Use PrivateGPT as LLM and Embedding
-  - [ ] Better Storage
-    - [ ] Use a vectorstore for storing embeddings
-  - [ ] Add metadata
-    - [ ] Improve metadata for files
-  - [ ] Autonomous Agents - Eureka!
-    - [ ] Create AGI agents tools
-      - [ ] Summarization
-
-Good for now ?! 😙
+A personal assistant that can help you with your daily tasks, such as scheduling meetings, taking notes, and answering questions.
+![](/img/north-star-quivr.png)

docs/docusaurus.config.js

@@ -95,7 +95,7 @@ const config = {
             items: [
               {
                 label: 'Get Started',
-                to: '/docs/get_started/intro',
+                to: '/docs/intro',
               },
             ],
           },

docs/src/pages/index.js

@@ -1,5 +1,5 @@
 import { Redirect } from "@docusaurus/router";
 import React from "react";
 export default function Home() {
-  return <Redirect to="docs/get_started/intro.html" />;
+  return <Redirect to="docs/intro.html" />;
 }