Spaces:
Running
Running
File size: 3,602 Bytes
ef18c90 016b413 ef18c90 016b413 ef18c90 016b413 e568430 016b413 e568430 016b413 ef18c90 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 |
# HuggingFace
HF_TOKEN=your_huggingface_token_here
# OpenAI (optional)
OPENAI_API_KEY=your_openai_key_here
# Anthropic (optional)
ANTHROPIC_API_KEY=your_anthropic_key_here
# Model names (optional - sensible defaults set in config.py)
# ANTHROPIC_MODEL=claude-sonnet-4-5-20250929
# OPENAI_MODEL=gpt-5.1
# ============================================
# Audio Processing Configuration (TTS)
# ============================================
# Kokoro TTS Model Configuration
TTS_MODEL=hexgrad/Kokoro-82M
TTS_VOICE=af_heart
TTS_SPEED=1.0
TTS_GPU=T4
TTS_TIMEOUT=60
# Available TTS Voices:
# American English Female: af_heart, af_bella, af_nicole, af_aoede, af_kore, af_sarah, af_nova, af_sky, af_alloy, af_jessica, af_river
# American English Male: am_michael, am_fenrir, am_puck, am_echo, am_eric, am_liam, am_onyx, am_santa, am_adam
# Available GPU Types (Modal):
# T4 - Cheapest, good for testing (default)
# A10 - Good balance of cost/performance
# A100 - Fastest, most expensive
# L4 - NVIDIA L4 GPU
# L40S - NVIDIA L40S GPU
# Note: GPU type is set at function definition time. Changes require app restart.
# ============================================
# Audio Processing Configuration (STT)
# ============================================
# Speech-to-Text API Configuration
STT_API_URL=nvidia/canary-1b-v2
STT_SOURCE_LANG=English
STT_TARGET_LANG=English
# Available STT Languages:
# English, Bulgarian, Croatian, Czech, Danish, Dutch, Estonian, Finnish, French, German, Greek, Hungarian, Italian, Latvian, Lithuanian, Maltese, Polish, Portuguese, Romanian, Slovak, Slovenian, Spanish, Swedish, Russian, Ukrainian
# ============================================
# Audio Feature Flags
# ============================================
ENABLE_AUDIO_INPUT=true
ENABLE_AUDIO_OUTPUT=true
# ============================================
# Image OCR Configuration
# ============================================
OCR_API_URL=prithivMLmods/Multimodal-OCR3
ENABLE_IMAGE_INPUT=true
# ============== EMBEDDINGS ==============
# OpenAI Embedding Model (used if LLM_PROVIDER is openai and performing RAG/Embeddings)
OPENAI_EMBEDDING_MODEL=text-embedding-3-small
# Local Embedding Model (used for local/offline embeddings)
LOCAL_EMBEDDING_MODEL=sentence-transformers/all-MiniLM-L6-v2
# ============== HUGGINGFACE (FREE TIER) ==============
# HuggingFace Token - enables Llama 3.1 (best quality free model)
# Get yours at: https://huggingface.co/settings/tokens
#
# WITHOUT HF_TOKEN: Falls back to ungated models (zephyr-7b-beta)
# WITH HF_TOKEN: Uses Llama 3.1 8B Instruct (requires accepting license)
#
# For HuggingFace Spaces deployment:
# Set this as a "Secret" in Space Settings -> Variables and secrets
# Users/judges don't need their own token - the Space secret is used
#
HF_TOKEN=hf_your-token-here
# ============== AGENT CONFIGURATION ==============
MAX_ITERATIONS=10
SEARCH_TIMEOUT=30
LOG_LEVEL=INFO
# ============================================
# Modal Configuration (Required for TTS)
# ============================================
# Modal credentials are required for TTS (Text-to-Speech) functionality
# Get your credentials from: https://modal.com/
MODAL_TOKEN_ID=your_modal_token_id_here
MODAL_TOKEN_SECRET=your_modal_token_secret_here
# ============== EXTERNAL SERVICES ==============
# PubMed (optional - higher rate limits)
NCBI_API_KEY=your-ncbi-key-here
# Vector Database (optional - for LlamaIndex RAG)
CHROMA_DB_PATH=./chroma_db
# Neo4j Knowledge Graph
NEO4J_URI=bolt://localhost:7687
NEO4J_USER=neo4j
NEO4J_PASSWORD=your_neo4j_password_here
NEO4J_DATABASE=your_database_name
|