GitHub Viewer

# ============================================================================= # Journal Utilities - Environment Configuration # ============================================================================= # This file contains all environment variables needed for both the transcription # pipeline (WhisperX) and entity extraction pipeline (journal_utilities.rag / Cohere) # ============================================================================= # Copy to `.env` and fill in real values. Never commit a real `.env` file. # ----------------------------------------------------------------------------- # Application Settings # ----------------------------------------------------------------------------- APP_NAME=Journal-Utilities VERSION=0.1.0 DEBUG=False # ----------------------------------------------------------------------------- # Transcription Pipeline (WhisperX) # ----------------------------------------------------------------------------- # Hugging Face token for WhisperX diarization models # Get from: https://huggingface.co/settings/tokens # Required models: pyannote/segmentation-3.0, pyannote/speaker-diarization-3.1 # `transcribe_worklist.py` accepts either name; the legacy WhisperX pipeline # (`transcribe/transcribe.py`) reads `HF_TOKEN`. HUGGINGFACE_TOKEN=your_huggingface_token_here HF_TOKEN=your_huggingface_token_here # Coda API Token for fetching session data # Get from: https://coda.io/account (API settings section) CODA_API_TOKEN=your_coda_api_token_here # Legacy WhisperX pipeline directories (transcribe/transcribe.py only — # the modern workflow is scripts/transcribe_worklist.py + the journal repo) WAV_DIRECTORY=/path/to/audio/wavs OUTPUT_DIR=/path/to/project/data/output # ----------------------------------------------------------------------------- # Entity Extraction Pipeline (journal_utilities.rag / Cohere) # ----------------------------------------------------------------------------- # Cohere API Configuration for entity extraction # Get from: https://dashboard.cohere.com/api-keys COHERE_API_KEY=your_cohere_api_key_here COHERE_MODEL=command-a-03-2025 # Processing settings for entity extraction BATCH_SIZE=10 MAX_RETRIES=3 # ----------------------------------------------------------------------------- # SurrealDB Configuration (shared by both pipelines) # ----------------------------------------------------------------------------- # Database connection settings # `journal_utilities.data` uses the DB_* prefix; `journal_utilities.rag` # settings use the SURREALDB_* prefix. Both are read from the environment. # Primary configuration (used by journal_utilities.data) DB_URL=ws://0.0.0.0:8080/rpc DB_USER=root DB_PASSWORD=root DB_NAME=actinf DB_NAMESPACE=actinf # Alternative configuration (used by journal_utilities.rag) # Set to the same values as above for consistency SURREALDB_URL=ws://0.0.0.0:8080/rpc SURREALDB_USERNAME=root SURREALDB_PASSWORD=root SURREALDB_DATABASE=actinf SURREALDB_NAMESPACE=actinf