Omi

https://docs.omi.me/
Admin
Omi is an advanced open-source AI wearable that captures, transcribes, and manages conversations,...
Tokens:66,616
Snippets:297
Trust Score:9.2
Update:11 months ago
Show doc for...
Tokens:
Raw
### Install PyOgg and Project Dependencies

Source: https://docs.omi.me/doc/developer/backend/Backend_Setup

Installs the PyOgg library and all other required Python dependencies for the Omi backend by utilizing the requirements.txt file.

```bash
pip install PyOgg
pip install -r requirements.txt
```

--------------------------------

### Install and Use Black for Code Formatting

Source: https://docs.omi.me/doc/developer/backend/Backend_Setup

Installs the 'black' Python package for code formatting and provides instructions to set up a pre-commit hook for automatic formatting.

```bash
pip install black
# From the root of the repository
ln -s -f ../../scripts/pre-commit .git/hooks/pre-commit
```

--------------------------------

### Clone Omi Backend Repository

Source: https://docs.omi.me/doc/developer/backend/Backend_Setup

Clones the Omi backend repository from GitHub and navigates into the backend directory. This is the first step after setting up the environment.

```bash
git clone https://github.com/BasedHardware/Omi.git
cd Omi
cd backend
```

--------------------------------

### Install Python and Dependencies (Windows)

Source: https://docs.omi.me/doc/developer/backend/Backend_Setup

Installs Python, Git, and FFmpeg on Windows using Chocolatey. These are essential dependencies for the Omi backend.

```bash
choco install python
choco install git.install ffmpeg
```

--------------------------------

### Install Google Cloud SDK using Chocolatey

Source: https://docs.omi.me/doc/developer/backend/Backend_Setup

Installs the Google Cloud SDK on Windows using the Chocolatey package manager. This SDK is required for managing Google Cloud resources and services.

```bash
choco install gcloudsdk
```

--------------------------------

### Run Uvicorn Backend Server with Reload and Environment File

Source: https://docs.omi.me/doc/developer/backend/Backend_Setup

Starts the backend server using uvicorn, enabling automatic reloading on code changes and loading environment variables from a .env file. It specifies the host and port for the server.

```bash
uvicorn main:app --reload --env-file .env --host 0.0.0.0 --port 8000
```

--------------------------------

### Install Python and Dependencies (Mac)

Source: https://docs.omi.me/doc/developer/backend/Backend_Setup

Installs Python, Git, FFmpeg, and Opus on macOS using Homebrew. These are essential dependencies for the Omi backend.

```bash
brew install python
brew install git ffmpeg
brew install opus
```

--------------------------------

### Configure and Run Pusher Service

Source: https://docs.omi.me/doc/developer/backend/Backend_Setup

Sets up and runs the Pusher service for webhook functionality. It involves copying a template environment file, setting a Google Cloud service account variable, and starting the Uvicorn server.

```bash
cd pusher
cp .env.template .env
# Set SERVICE_ACCOUNT_JSON environment variable in .env
uvicorn pusher.main:app --reload --env-file .env --port 8000
```

--------------------------------

### Install Google Cloud SDK using Brew

Source: https://docs.omi.me/doc/developer/backend/Backend_Setup

Installs the Google Cloud SDK on macOS using the Homebrew package manager. This SDK is essential for interacting with Google Cloud services from your terminal.

```bash
brew install google-cloud-sdk
```

--------------------------------

### Install Python Dependencies Directly

Source: https://docs.omi.me/doc/developer/backend/Backend_Setup

Installs required Python packages globally using pip and requirements.txt. This method is simpler but may lead to system-wide dependency conflicts.

```bash
pip install -r requirements.txt
```

--------------------------------

### Set up Environment File

Source: https://docs.omi.me/doc/developer/backend/Backend_Setup

Creates and populates the `.env` file with necessary API keys and credentials for services like OpenAI, Deepgram, Redis, Modal, and OAuth providers. This file is crucial for the backend to function correctly.

```bash
cp .env.template .env
# Open .env and fill in the required credentials
```

--------------------------------

### Install Python Dependencies with Virtual Environment

Source: https://docs.omi.me/doc/developer/backend/Backend_Setup

Installs required Python packages within an isolated virtual environment using pip and requirements.txt. This method prevents dependency conflicts with other projects.

```bash
python -m venv venv
# On Windows:
venv\Scripts\activate
# On macOS/Linux:
source venv/bin/activate
pip install -r requirements.txt
```

--------------------------------

### Authenticate with Google Cloud

Source: https://docs.omi.me/doc/developer/backend/Backend_Setup

Sets up authentication for Google Cloud services. This involves logging in, configuring the project, and setting up application default credentials, which are stored in a JSON file for programmatic access.

```bash
gcloud auth login
gcloud config set project <project-id>
gcloud auth application-default login --project <project-id>
```

--------------------------------

### Local Development Setup for Omi Python SDK

Source: https://docs.omi.me/doc/developer/sdk/python

Sets up a local development environment for the Omi Python SDK, including cloning the repository, creating a virtual environment, and installing dependencies in editable mode.

```bash
git clone https://github.com/BasedHardware/omi.git
cd omi/sdks/python

# Create virtual environment
python3 -m venv venv
source venv/bin/activate

# Install in editable mode
pip install -e .

# Install dev dependencies
pip install -e ".[dev]"
```

--------------------------------

### Reinstall Python Dependencies with Force and Upgrade

Source: https://docs.omi.me/doc/developer/backend/Backend_Setup

Forces a reinstallation of all Python dependencies from requirements.txt, including upgrading existing packages. This is useful for resolving module not found errors.

```bash
pip install -r requirements.txt --upgrade --force-reinstall
```

--------------------------------

### Deactivate Python Virtual Environment

Source: https://docs.omi.me/doc/developer/backend/Backend_Setup

Command to exit the currently active Python virtual environment and return to the system's global Python environment.

```bash
deactivate
```

--------------------------------

### Install Omi Python SDK from PyPI

Source: https://docs.omi.me/doc/developer/sdk/python

Installs the Omi Python SDK from the Python Package Index (PyPI). This is the simplest installation method when the SDK is published.

```bash
pip install omi-sdk
```

--------------------------------

### Troubleshoot SSL Errors in Python

Source: https://docs.omi.me/doc/developer/backend/Backend_Setup

Provides a Python code snippet to bypass SSL certificate verification errors, often encountered during model downloads. This should be added to the specified file.

```python
import ssl
ssl._create_default_https_context = ssl._create_unverified_context
```

--------------------------------

### Copy Google Cloud Credentials (Windows)

Source: https://docs.omi.me/doc/developer/backend/Backend_Setup

Copies the generated Google Cloud application default credentials JSON file to the backend directory and renames it for application use on Windows systems. This facilitates automatic authentication with Google Cloud services.

```bash
copy %APPDATA%\gcloud\application_default_credentials.json google-credentials.json
```

--------------------------------

### Copy Google Cloud Credentials (Linux/macOS)

Source: https://docs.omi.me/doc/developer/backend/Backend_Setup

Copies the generated Google Cloud application default credentials JSON file to the backend directory and renames it for use by applications. This file enables seamless authentication with Google Cloud services.

```bash
cp ~/.config/gcloud/application_default_credentials.json ./google-credentials.json
```

--------------------------------

### Create Memory from Email (Python, cURL)

Source: https://docs.omi.me/doc/developer/apps/Import

Provides code examples for creating a memory from email content using the Omi.me API. It includes details like confirmation codes and dates, specifying 'email' as the text source.

```python
import requests
import json

# API configuration
APP_ID = "your_app_id_here"
API_KEY = "sk_your_api_key_here"
USER_ID = "user_123"
API_URL = f"https://api.omi.me/v2/integrations/{APP_ID}/user/memories"

# Memories data from email
memories_data = {
    "text": "Your flight to Paris has been confirmed for May 15th, 2024. Departure: JFK at 9:30 PM. Arrival: CDG at 11:00 AM local time. Confirmation code: ABC123. Your hotel reservation at Hotel de Paris is confirmed for May 16-20, 2024.",
    "text_source": "email",
    "text_source_spec": "travel_confirmation"
}

# Make the API request
headers = {
    "Authorization": f"Bearer {API_KEY}",
    "Content-Type": "application/json"
}

response = requests.post(
    f"{API_URL}?uid={USER_ID}",
    headers=headers,
    data=json.dumps(memories_data)
)

# Handle the response
if response.status_code == 200:
    print("Memories created successfully")
else:
    print(f"Error creating memories: {response.status_code}")
    print(response.text)
```

```bash
curl -X POST "https://api.omi.me/v2/integrations/your_app_id_here/user/memories?uid=user_123" \
  -H "Authorization: Bearer sk_your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Your flight to Paris has been confirmed for May 15th, 2024. Departure: JFK at 9:30 PM. Arrival: CDG at 11:00 AM local time. Confirmation code: ABC123. Your hotel reservation at Hotel de Paris is confirmed for May 16-20, 2024.",
    "text_source": "email",
    "text_source_spec": "travel_confirmation"
  }'
```

--------------------------------

### Basic Omi Device Connection and Interaction in React Native

Source: https://docs.omi.me/doc/developer/sdk/ReactNative

Example JavaScript code demonstrating how to use the OmiConnection class from the `@omiai/omi-react-native` SDK. It covers scanning for devices, connecting, retrieving audio codec, starting audio streaming, checking battery level, and disconnecting.

```javascript
import { OmiConnection, DeviceConnectionState, BleAudioCodec } from '@omiai/omi-react-native';

// Create an instance of OmiConnection
const omiConnection = new OmiConnection();

// Scan for devices
const stopScan = omiConnection.scanForDevices((device) => {
  console.log('Found device:', device.name, device.id);
}, 10000); // Scan for 10 seconds

// Connect to a device
async function connectToDevice(deviceId) {
  const success = await omiConnection.connect(deviceId, (id, state) => {
    console.log(`Device ${id} connection state changed to: ${state}`);
  });
  
  if (success) {
    console.log('Connected successfully!');
    
    // Get the audio codec
    const codec = await omiConnection.getAudioCodec();
    console.log('Device audio codec:', codec);
    
    // Start listening for audio data
    const subscription = await omiConnection.startAudioBytesListener((bytes) => {
      console.log('Received audio bytes:', bytes.length);
      // Process audio bytes here
    });
    
    // Get battery level
    const batteryLevel = await omiConnection.getBatteryLevel();
    console.log('Battery level:', batteryLevel);
    
    // Later, stop listening for audio
    await omiConnection.stopAudioBytesListener(subscription);
    
    // Disconnect when done
    await omiConnection.disconnect();
  }
}
```

--------------------------------

### Install Omi React Native SDK and Dependencies

Source: https://docs.omi.me/doc/developer/sdk/ReactNative

Commands to install the Omi SDK for React Native and its primary dependency, react-native-ble-plx, using npm or yarn. For iOS projects, a subsequent `pod install` is mandatory.

```bash
npm install @omiai/omi-react-native
# or
yarn add @omiai/omi-react-native

npm install react-native-ble-plx
# or
yarn add react-native-ble-plx

cd ios
pod install
```

--------------------------------

### Run Omi Python SDK Example

Source: https://docs.omi.me/doc/developer/sdk/python

Instructions on how to run the Omi Python SDK example script after setting up the environment and updating the Omi device MAC address.

```bash
# 1. Set your Deepgram API key
export DEEPGRAM_API_KEY=your_actual_deepgram_key

# 2. Find your Omi device MAC address
    omi-scan

# 3. Update examples/main.py with your device's MAC address
# Edit line 10: OMI_MAC = "YOUR_DEVICE_MAC_HERE"

# 4. Run the example
python examples/main.py
```

--------------------------------

### Start omiGlass Application

Source: https://docs.omi.me/doc/hardware/omiGlass

These commands initiate the omiGlass application using either npm or yarn. The application is built with Expo, and starting it will provide a localhost link to access the web version.

```bash
npm start
```

```bash
yarn start
```

--------------------------------

### Get Conversations Example Request (Bash)

Source: https://docs.omi.me/doc/developer/api

This example demonstrates how to make a GET request to the Omi.me conversations endpoint using curl. It includes authentication headers and query parameters to specify the limit and include the transcript. This is useful for testing API access and understanding request formatting.

```bash
curl -H "Authorization: Bearer omi_dev_your_api_key" \
  "https://api.omi.me/v1/dev/user/conversations?limit=10&include_transcript=true"
```

--------------------------------

### Get Conversations Response Example (JSON)

Source: https://docs.omi.me/doc/developer/api

These JSON examples illustrate the structure of the response when retrieving conversations. One example shows the response without the transcript, detailing conversation metadata. The second example includes the transcript segments, providing the full conversational text.

```json
[
  {
    "id": "conv_202",
    "created_at": "2025-01-20T13:50:00Z",
    "started_at": "2025-01-20T13:50:00Z",
    "finished_at": "2025-01-20T14:10:00Z",
    "language": "en",
    "source": "omi",
    "structured": {
      "title": "Feature Discussion",
      "overview": "Brainstorming session for new features",
      "emoji": "💼",
      "category": "business",
      "action_items": [
        {
          "description": "Create mockups for new UI",
          "completed": false,
          "created_at": "2025-01-20T14:10:00Z",
          "updated_at": "2025-01-20T14:10:00Z",
          "due_at": null,
          "completed_at": null
        }
      ],
      "events": []
    }
  }
]
```

```json
[
  {
    "id": "conv_202",
    "created_at": "2025-01-20T13:50:00Z",
    "started_at": "2025-01-20T13:50:00Z",
    "finished_at": "2025-01-20T14:10:00Z",
    "language": "en",
    "source": "friend",
    "structured": {
      "title": "Feature Discussion",
      "overview": "Brainstorming session for new features",
      "emoji": "💼",
      "category": "business",
      "action_items": [
        {
          "description": "Create mockups for new UI",
          "completed": false,
          "created_at": "2025-01-20T14:10:00Z",
          "updated_at": "2025-01-20T14:10:00Z",
          "due_at": null,
          "completed_at": null
        }
      ],
      "events": []
    },
    "transcript_segments": [
      {
        "id": "seg_001",
        "text": "Let's discuss the new feature",
        "speaker_id": 0,
        "start": 0.0,
        "end": 2.5
      },
      {
        "id": "seg_002",
        "text": "I think we should focus on the user interface first",
        "speaker_id": 1,
        "start": 2.5,
        "end": 5.8
      }
    ]
  }
]
```

--------------------------------

### GET /v2/integrations/{app_id}/memories

Source: https://docs.omi.me/doc/developer/apps/Import

Read all memories in a user's knowledge base. This endpoint allows programmatic access to a user's stored memories.

```APIDOC
## GET /v2/integrations/{app_id}/memories

### Description
Read all memories in a user's knowledge base. This endpoint allows programmatic access to a user's stored memories.

### Method
GET

### Endpoint
https://api.omi.me/v2/integrations/{app_id}/memories?uid={user_id}

### Parameters
#### Path Parameters
- **app_id** (string) - Required - Your app's unique identifier

#### Query Parameters
- **uid** (string) - Required - The OMI user ID whose memories you want to access.
- **limit** (integer) - Optional - Maximum number of memories to return (default: 100, max: 1000).
- **offset** (integer) - Optional - Number of memories to skip (for pagination).

### Request Example
```http
GET https://api.omi.me/v2/integrations/your_app_id/memories?uid=user_id_123&limit=50
```

### Authentication
Include your API key in the request headers:
```
Authorization: Bearer sk_your_api_key_here
```
> **Important**: The API key must be associated with the app specified in the URL path.

### Response
#### Success Response (200)
- **memories** (array[object]) - An array of memory objects.
  - **id** (string) - Unique identifier for the memory.
  - **content** (string) - The content of the memory.
  - **created_at** (string) - Timestamp when the memory was created.
  - **tags** (array[string]) - Tags associated with the memory.

#### Response Example
```json
{
  "memories": [
    {
      "id": "memory_id_1",
      "content": "User prefers vegetarian food options",
      "created_at": "2024-03-15T12:00:00Z",
      "tags": ["preferences", "food"]
    },
    {
      "id": "memory_id_2",
      "content": "User's anniversary is on June 12th",
      "created_at": "2024-03-15T12:05:00Z",
      "tags": ["dates", "personal"]
    }
  ]
}
```

### Error Handling
- `400 Bad Request`: Invalid request format.
- `401 Unauthorized`: Missing or invalid Authorization header.
- `403 Forbidden`: Invalid API key, app not enabled for user, or app lacks read_memories capability.
- `404 Not Found`: App not found.
- `429 Too Many Requests`: Rate limit exceeded.
```

--------------------------------

### GET /v2/integrations/{app_id}/conversations

Source: https://docs.omi.me/doc/developer/apps/Import

Read all conversations in a user's OMI account. This endpoint allows programmatic access to a user's conversation history.

```APIDOC
## GET /v2/integrations/{app_id}/conversations

### Description
Read all conversations in a user's OMI account. This endpoint allows programmatic access to a user's conversation history.

### Method
GET

### Endpoint
https://api.omi.me/v2/integrations/{app_id}/conversations?uid={user_id}

### Parameters
#### Path Parameters
- **app_id** (string) - Required - Your app's unique identifier

#### Query Parameters
- **uid** (string) - Required - The OMI user ID whose conversations you want to access.
- **limit** (integer) - Optional - Maximum number of conversations to return (default: 100, max: 1000).
- **offset** (integer) - Optional - Number of conversations to skip (for pagination).
- **include_discarded** (boolean) - Optional - Whether to include discarded conversations (default: false).
- **statuses** (string) - Optional - Filter by conversation statuses (comma-separated list).

### Request Example
```http
GET https://api.omi.me/v2/integrations/your_app_id/conversations?uid=user_id_123&limit=50&include_discarded=true
```

### Authentication
Include your API key in the request headers:
```
Authorization: Bearer sk_your_api_key_here
```
> **Important**: The API key must be associated with the app specified in the URL path.

### Response
#### Success Response (200)
- **conversations** (array[object]) - An array of conversation objects.
  - **id** (string) - Unique identifier for the conversation.
  - **created_at** (string) - Timestamp when the conversation was created.
  - **started_at** (string) - Timestamp when the conversation started.
  - **finished_at** (string) - Timestamp when the conversation ended.
  - **text** (string) - Full conversation text content.
  - **structured** (object) - Structured data about the conversation.
    - **title** (string) - Title of the conversation.
    - **overview** (string) - Brief overview of the conversation.
  - **transcript_segments** (array[object]) - Segments of the conversation transcript.
    - **text** (string) - Text of the segment.
    - **start_time** (number) - Start time of the segment in seconds.
    - **end_time** (number) - End time of the segment in seconds.
  - **geolocation** (object) - Geolocation information.
    - **latitude** (number) - Latitude coordinate.
    - **longitude** (number) - Longitude coordinate.

#### Response Example
```json
{
  "conversations": [
    {
      "id": "conversation_id_1",
      "created_at": "2024-03-15T12:00:00Z",
      "started_at": "2024-03-15T12:00:00Z",
      "finished_at": "2024-03-15T12:05:00Z",
      "text": "Full conversation text content...",
      "structured": {
        "title": "Conversation Title",
        "overview": "Brief overview of the conversation"
      },
      "transcript_segments": [
        {
          "text": "Segment text...",
          "start_time": 0,
          "end_time": 10
        }
      ],
      "geolocation": {
        "latitude": 37.7749,
        "longitude": -122.4194
      }
    }
  ]
}
```

### Error Handling
- `400 Bad Request`: Invalid request format.
- `401 Unauthorized`: Missing or invalid Authorization header.
- `403 Forbidden`: Invalid API key, app not enabled for user, or app lacks read_conversations capability.
- `404 Not Found`: App not found.
- `429 Too Many Requests`: Rate limit exceeded.
```

--------------------------------

### Create Development Environment File

Source: https://docs.omi.me/doc/developer/AppSetup

Copies the template environment file to a new file specifically for development. This new file will be used to store local configuration settings and API keys.

```shell
cd ..
cat .env.template > .dev.env
```

--------------------------------

### Read Conversations (cURL)

Source: https://docs.omi.me/doc/developer/apps/Import

An alternative method to fetch conversations using cURL. This command-line tool sends a GET request to the Omi.me API with specified parameters, headers, and authentication.

```bash
curl -X GET "https://api.omi.me/v2/integrations/your_app_id_here/conversations?uid=user_123&limit=50&offset=0" \
  -H "Authorization: Bearer sk_your_api_key_here" \
  -H "Content-Type: application/json"

```

--------------------------------

### Verify Flutter Installation

Source: https://docs.omi.me/doc/developer/AppSetup

This command checks your Flutter installation and identifies any missing dependencies or configuration issues. It's crucial for ensuring a healthy development environment. The output provides details about your Flutter version, SDK paths, and connected devices.

```shell
flutter doctor -v
```

--------------------------------

### Read OMI Conversations

Source: https://docs.omi.me/doc/developer/apps/Import

Enables programmatic access to read all conversations in a user's OMI account. This requires a GET request to the conversations endpoint, with options for filtering and pagination.

```HTTP
GET https://api.omi.me/v2/integrations/{app_id}/conversations?uid={user_id}&limit=100&offset=0&include_discarded=false&statuses=open,closed
Authorization: Bearer sk_your_api_key_here
```

--------------------------------

### Install Omi Python SDK from Source

Source: https://docs.omi.me/doc/developer/sdk/python

Installs the Omi Python SDK directly from its source code repository. This is useful for development or when using the latest unreleased changes.

```bash
git clone https://github.com/BasedHardware/omi.git
cd omi/sdks/python
pip install -e .
```

--------------------------------

### Install Project Dependencies with npm or yarn

Source: https://docs.omi.me/doc/hardware/omiGlass

This snippet shows how to clone the omiGlass repository and install its dependencies using either npm or yarn. It's a standard step for setting up Node.js projects.

```bash
git clone https://github.com/BasedHardware/omi.git
cd omi/OmiGlass
npm install
```

```bash
git clone https://github.com/BasedHardware/omi.git
cd omi/OmiGlass
yarn install
```

--------------------------------

### Read OMI Memories

Source: https://docs.omi.me/doc/developer/apps/Import

Allows an application to programmatically access and read all memories stored in a user's OMI knowledge base. This uses a GET request to the memories endpoint with optional pagination parameters.

```HTTP
GET https://api.omi.me/v2/integrations/{app_id}/memories?uid={user_id}&limit=100&offset=0
Authorization: Bearer sk_your_api_key_here
```
Tokens:
Raw