Files
tradingagents/.env.example
Yijia-Xiao 295e84cd54 feat(llm): add NVIDIA NIM, Kimi, Groq, and Mistral providers
Each is a one-row entry in the OpenAI-compatible provider registry (base_url,
key env, CLI option); the model is user-specified since they serve many models.
2026-06-14 04:13:39 +00:00

49 lines
1.8 KiB
Plaintext

# LLM Providers (set the one you use)
OPENAI_API_KEY=
GOOGLE_API_KEY=
ANTHROPIC_API_KEY=
XAI_API_KEY=
DEEPSEEK_API_KEY=
DASHSCOPE_API_KEY=
DASHSCOPE_CN_API_KEY=
ZHIPU_API_KEY=
ZHIPU_CN_API_KEY=
MINIMAX_API_KEY=
MINIMAX_CN_API_KEY=
OPENROUTER_API_KEY=
MISTRAL_API_KEY=
MOONSHOT_API_KEY=
GROQ_API_KEY=
NVIDIA_API_KEY=
# Optional: a custom OpenAI-compatible endpoint (vLLM, LM Studio, llama.cpp,
# relay). Select provider "openai_compatible" and set the base URL; the key is
# optional (local servers need none).
#OPENAI_COMPATIBLE_API_KEY=
# Optional: point at a remote Ollama server. When unset, defaults to
# the local instance at http://localhost:11434/v1. Convention follows
# the broader Ollama ecosystem; both the CLI dropdown and programmatic
# client pick this up.
#OLLAMA_BASE_URL=http://your-ollama-host:11434/v1
# Optional: override DEFAULT_CONFIG without editing code.
# Any TRADINGAGENTS_* variable below, when set, replaces the matching key
# in tradingagents/default_config.py. Values are coerced to the type of
# the existing default (bool / int / str), so "true"/"3" work as expected.
# In the CLI, setting the LLM provider / models / backend URL / language
# also skips the matching interactive selection step (useful for
# OpenAI-compatible endpoints like opencode or LM Studio, and unattended runs).
#TRADINGAGENTS_LLM_PROVIDER=openai
#TRADINGAGENTS_DEEP_THINK_LLM=gpt-5.4
#TRADINGAGENTS_QUICK_THINK_LLM=gpt-5.4-mini
#TRADINGAGENTS_LLM_BACKEND_URL=
#TRADINGAGENTS_OUTPUT_LANGUAGE=English
#TRADINGAGENTS_MAX_DEBATE_ROUNDS=1
#TRADINGAGENTS_MAX_RISK_ROUNDS=1
#TRADINGAGENTS_CHECKPOINT_ENABLED=false
# Sampling temperature (lower = less run-to-run variation on models that
# honor it). Unset leaves each provider at its default. See the README
# "Reproducibility" note — no setting makes LLM output fully deterministic.
#TRADINGAGENTS_TEMPERATURE=0.0