Update README.md

data-max-hq · Jul 31, 2024 · 3eabab4 · 3eabab4
1 parent ceb8827
commit 3eabab4
Showing 1 changed file with 78 additions and 35 deletions.
diff --git a/README.md b/README.md
@@ -1,52 +1,95 @@
-# Open-Memory
+### Open-Memory
 
-## Introduction:
+## Introduction
 
 In response to growing privacy concerns and Microsoft's "Windows Recall" feature, which records and analyzes screen activities by transmitting data to the cloud, we have developed an open-source pilot that offers similar functionality without compromising user privacy.
 
+## Usage Flow
 
-## Usage Flow:
+- The user runs `screenshot-desktop.py` whenever they want to start recording their screens.
+- The extracted text from the screenshots is processed by the DocTR OCR tool and stored in the ChromaDB vector database, along with their corresponding embeddings generated by the JinaAI embedding model.
+- When the user has a query or needs to retrieve relevant information, they can input their request into `LLM Prompt`.
+- The query is then processed by the JinaAI reranker model, which retrieves the most relevant text chunks from the ChromaDB database based on the semantic similarity of the embeddings.
+- The retrieved information is presented to the user, providing them with the necessary context and insights without ever leaving their local device.
+- This approach ensures that all data processing and storage remain under the user's control, eliminating the risks associated with cloud-based solutions and empowering users to maintain their privacy.
 
-The user runs ‘screenshot-desktop.py’ whenever they want to start recording their screens
+## Setup Guide
 
-
-The extracted text from the screenshots is processed by the DocTR OCR tool and stored in the ChromaDB vector database, along with their corresponding embeddings generated by the JinaAI embedding model.
+### Prerequisites
 
-
-When the user has a query or needs to retrieve relevant information, they can input their request into ‘LLM Prompt’.
+- Python 3.11 
+- Docker
+- Docker Compose
+- Make
 
-
-The query is then processed by the JinaAI reranker model, which retrieves the most relevant text chunks from the ChromaDB database based on the semantic similarity of the embeddings.
+### Installation Steps
 
-
-The retrieved information is presented to the user, providing them with the necessary context and insights without ever leaving their local device.
+1. **Install Docker:**
 
-
-This approach ensures that all data processing and storage remain under the user's control, eliminating the risks associated with cloud-based solutions and empowering users to maintain their privacy.
+   Follow the official Docker installation guide for your operating system:
+   - [Docker for Windows](https://docs.docker.com/docker-for-windows/install/)
+   - [Docker for macOS](https://docs.docker.com/docker-for-mac/install/)
+   - [Docker for Linux](https://docs.docker.com/engine/install/)
 
+   After installing Docker, ensure it's running correctly by executing:
+   ```sh
+   docker --version
+   ```
 
+2. **Install Docker Compose:**
 
-## Setup Guide
-* Tested using ```Python 3.11 ```
-* Clone the repository (data-max-hq/open-memory)
-
-  ```
-  cd /open-memory
-  pip install pyautogui
-  make build
-  make run
-  ```
-
-* After a couple of minutes then head over to "localhost:8080"
-* In "ADD LLM" type out the LLM you want to use (we recomend qwen2:1.5b or qwen2:0.5b) and press "Add LLM"
-
-
+   Docker Compose is included in Docker Desktop for Windows and macOS. For Linux, you can install it by following these steps:
+   ```sh
+   sudo curl -L "https://github.com/docker/compose/releases/download/v2.11.1/docker-compose-$(uname -s)-$(uname -m)" -o /usr/local/bin/docker-compose
+   sudo chmod +x /usr/local/bin/docker-compose
+   ```
 
-## Functionality
-Run "screenshot-desktop.py" to start capturin the screen
+   Verify the installation:
+   ```sh
+   docker-compose --version
+   ```
+
+3. **Install Make:**
+
+   Depending on your operating system, install Make:
+
+   - **Windows:** Install [Make for Windows](http://gnuwin32.sourceforge.net/packages/make.htm).
+   - **macOS:** Use Homebrew (if not installed, follow [Homebrew installation](https://brew.sh/)):
+     ```sh
+     brew install make
+     ```
+   - **Linux:** Install Make using your distribution's package manager:
+     ```sh
+     sudo apt-get install build-essential  # For Debian/Ubuntu
+     sudo yum group install 'Development Tools'  # For CentOS/RHEL
+     ```
+
+4. **Clone the Repository and Install Python Dependencies:**
 
-
-Query ChromaDB: Test the database to retrieve relevant pieces of context for a specific query.
+   ```sh
+   git clone https://github.com/data-max-hq/open-memory.git
+   cd open-memory
+   pip install pyautogui
+   ```
+
+5. **Build and Run the Docker Containers:**
+
+   ```sh
+   make build
+   make run
+   ```
+
+6. **Access the Application:**
+
+   After the containers are up and running, open your web browser and navigate to:
+   ```
+   http://localhost:8080
+   ```
+
+   In the "ADD LLM" section, type the LLM you want to use (we recommend `qwen2:1.5b` or `qwen2:0.5b`) and press "Add LLM".
+
+## Functionality
 
-
-LLM Prompt: Pass a query to QWEN2:1.5b to get an explanation of what the user was doing based on the retrieved context.
+- **Run `screenshot-desktop.py` to start capturing the screen.**
+- **Query ChromaDB:** Test the database to retrieve relevant pieces of context for a specific query.
+- **LLM Prompt:** Pass a query to QWEN2:1.5b to get an explanation of what the user was doing based on the retrieved context.