mirror of
https://github.com/TauricResearch/TradingAgents.git
synced 2026-06-16 21:06:15 +03:00
895ed130f9
Bedrock uses the Converse API (langchain-aws) and the AWS credential chain, so it has its own client like Anthropic/Google rather than the OpenAI-compatible registry. langchain-aws is an optional dependency (pip install ".[bedrock]"), lazy-imported with a clear install hint; importing the package never requires it. The model name is a Bedrock model ID / inference profile ID.
55 lines
2.1 KiB
Plaintext
55 lines
2.1 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=
|
|
|
|
# AWS Bedrock (provider "bedrock", install with: pip install ".[bedrock]").
|
|
# Auth uses the standard AWS credential chain; set the region (and optionally a
|
|
# named profile). No single API key.
|
|
#AWS_DEFAULT_REGION=us-west-2
|
|
#AWS_PROFILE=
|
|
|
|
# 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
|