asyncawait547/grammar-constrained-hallucination-free-llm-engine

Unknown stack

14 environment variables found in .env.template

Set these on your host before deploying. Each platform has an “Environment Variables” section in the deploy flow.

OPENAI_API_KEY secret Option 1: OpenAI API (default) Get your key from: https://platform.openai.com/api-keys
OPENROUTER_API_KEY secret Option 2: OpenRouter API (supports multiple providers: GPT-4, Claude, Gemini, Llama, etc.) Get your key from: https://openrouter.ai/keys
USE_OPENROUTER Set to "true" to use OpenRouter instead of OpenAI
TAVILY_API_KEY secret Tavily API Key (required for web search fallback) Get your key from: https://tavily.com/
DEFAULT_MODEL MODEL CONFIGURATION For OpenAI: use model names like "gpt-4o-mini", "gpt-4o" For OpenRouter: use format "provider/model" Examples:…
SMART_MODEL
EMBEDDING_MODEL
CHROMA_DB_PATH CHROMADB CONFIGURATION
COLLECTION_NAME
CHUNK_SIZE RETRIEVAL CONFIGURATION
CHUNK_OVERLAP
TOP_K_RETRIEVAL
MAX_RETRIES EVALUATION CONFIGURATION
ITERATION_LIMIT

Best match Fly.io Anything Dockerized — requires the Fly CLI.

macOS

brew install flyctl && fly launch --from https://github.com/asyncawait547/grammar-constrained-hallucination-free-llm-engine

Linux

curl -L https://fly.io/install.sh | sh && fly launch --from https://github.com/asyncawait547/grammar-constrained-hallucination-free-llm-engine

Windows (PowerShell)

iwr https://fly.io/install.ps1 -useb | iex; fly launch --from https://github.com/asyncawait547/grammar-constrained-hallucination-free-llm-engine

Or deploy to a different host