Welcome to the Omi backend setup guide! Omi is an innovative, multimodal AI assistant that combines cutting-edge technologies to provide a seamless user experience. This guide will help you set up the backend infrastructure that powers Omi’s intelligent capabilities.
brew install google-cloud-sdkchoco install gcloudsdk<project-id> with your Google Cloud project ID:
application_default_credentials.json file in the ~/.config/gcloud directory. This file is used for automatic authentication with Google Cloud services in Python.brew install pythonchoco install pythonbrew install git ffmpegchoco install git.install ffmpegbrew install opuspip install PyOggbrew install -r requirements.txt.env.template file and rename it to .env:
SERVICE_ACCOUNT_JSON environment variable in the .env file to the string representation of your Google Cloud service account credentials (google-credentials.json). This is used to authenticate with Google Cloudmemories and use the schema provided in the typesense/memories.schema fileusers/{userId}/memoriesstructured,transcript_segments,created_at,deleted,discarded,started_at,id,finished_at,geolocation,userIdtypesense_sync collection and add a document named backfill with data {'trigger' : true} (required only if you already have memories in Firestore and want to sync them to Typesense)TYPESENSE_HOST, TYPESENSE_HOST_PORT and TYPESENSE_API_KEY environment variables in the .env file to the host URL and API key provided by Typesense.env.template file and rename it to .env:
.env file and fill in the following:
123) for local development.env.template provides a default key suitable for local development (e.g., omi_ZwB2ZNqB2HHpMK6wStk7sTpavJiPTFg7gXUHnc4tFABPU6pZ2c2DKgehtfgi4RZv). For production, you must generate a new secure key.True to disable the socket timeout for the backend server (socket will stay connected for as long as the app is open)(venv) at the beginning of your command prompt, indicating that the virtual environment is activeblack for formatting with a line length of 120 characters.black installed:
8000 (the default port for the backend). For example:
https://example.ngrok-free.app) that points to your local backend--reload automatically restarts the server when code changes are saved, making development easier--env-file .env loads environment variables from your .env file--host 0.0.0.0 listens to every interface on your computer so you don’t have to set up ngrok when developing in your network--port 8000 port for backend to listenutils/stt/vad.py:
.env file. Ensure there are no trailing spacesAPI_BASE_URL to the public URL provided by Ngrok (e.g., https://example.ngrok-free.app/) (don’t forget the trailing / )source venv/bin/activate on macOS/Linux or venv\Scripts\activate on Windows).env file:
HUGGINGFACE_TOKEN: Your Hugging Face Hub API token, used to download models for speech processing (like voice activity detection)BUCKET_SPEECH_PROFILES: The name of the Google Cloud Storage bucket where user speech profiles are storedBUCKET_PLUGIN_LOGOS: The name of the Google Cloud Storage bucket where to put logos for uploaded appsBUCKET_BACKUPS: The name of the Google Cloud Storage bucket used for backups (if applicable)GOOGLE_APPLICATION_CREDENTIALS: The path to your Google Cloud service account credentials file (google-credentials.json). This is generated in step 3 of I. Setting Up Google Cloud & Firebase
google-credentials.json in the same directory where the application is runningapplication_default_credentials.json file (e.g., ~/.config/gcloud/application_default_credentials.json on macOS/Linux or %APPDATA%\gcloud\application_default_credentials.json on Windows)PINECONE_API_KEY: Your Pinecone API key, used for vector database operations. Storing Memory Embeddings: Each memory is converted into a numerical representation (embedding). Pinecone efficiently stores these embeddings and allows Omi to quickly find the most relevant memories related to a user’s queryPINECONE_INDEX_NAME: The name of your Pinecone index where memory embeddings are storedREDIS_DB_HOST: The host address of your Redis instanceREDIS_DB_PORT: The port number of your Redis instanceREDIS_DB_PASSWORD: The password for your Redis instance (blank by default)DEEPGRAM_API_KEY: Your Deepgram API key, used for real-time and pre-recorded audio transcriptionADMIN_KEY: A temporary key used for authentication during local development (replace with a more secure method in production)OPENAI_API_KEY: Your OpenAI API key, used for accessing OpenAI’s language models for chat, memory processing, and moreENCRYPTION_SECRET: A secret key used to encrypt sensitive user data, such as conversations, memories, and chat messages. The key must be at least 32 bytes long. The .env.template file includes a default key (e.g., omi_ZwB2ZNqB2HHpMK6wStk7sTpavJiPTFg7gXUHnc4tFABPU6pZ2c2DKgehtfgi4RZv) which is sufficient for local development. For a production environment, it is crucial to replace this with your own securely generated random string.GITHUB_TOKEN: Your GitHub personal access token, used to access GitHub’s API for retrieving the latest firmware versionWORKFLOW_API_KEY: Your custom API key for securing communication with external workflows or integrationsHOSTED_PUSHER_API_URL: URL of your omi-pusher service if you’re using one. Example: http://omi-push:8081TYPESENSE_HOST: URL of your typesense server.TYPESENSE_API_KEY: Typesense API key<api-key>, <bucket-name>, etc.) with your actual values.