From bc55fe3ed72e675e648696d148063313f1c053d2 Mon Sep 17 00:00:00 2001 From: Yijia-Xiao Date: Sat, 3 Oct 2026 23:15:48 +0000 Subject: [PATCH] docs: ChatGPT plan sign-in and the start-up update check (#1475) - README and .env.example cover the chatgpt provider, `tradingagents login chatgpt` (also in Docker) and logout - README and .env.example name TRADINGAGENTS_NO_UPDATE_CHECK --- .env.example | 6 ++++++ README.md | 6 +++++- 2 files changed, 11 insertions(+), 1 deletion(-) diff --git a/.env.example b/.env.example index 1db9017cf..eaa51ca65 100644 --- a/.env.example +++ b/.env.example @@ -35,6 +35,9 @@ NVIDIA_API_KEY= #AWS_DEFAULT_REGION=us-west-2 #AWS_PROFILE= +# ChatGPT Plus or Pro plan: no key; sign in once with `tradingagents login chatgpt`. +#TRADINGAGENTS_LLM_PROVIDER=chatgpt + # Remote Ollama server. Unset uses http://localhost:11434/v1. #OLLAMA_BASE_URL=http://your-ollama-host:11434/v1 @@ -54,6 +57,9 @@ NVIDIA_API_KEY= #TRADINGAGENTS_MAX_TOOL_ROUNDS=20 #TRADINGAGENTS_CHECKPOINT_ENABLED=false +# Turn off the start-up note about a newer release and Tauric Research notices. +#TRADINGAGENTS_NO_UPDATE_CHECK=1 + # Docker: a host folder for results, reports and the memory log (unset: the tradingagents_data volume). #TRADINGAGENTS_DATA_DIR=./data diff --git a/README.md b/README.md index 03f19b039..5b5835bbc 100644 --- a/README.md +++ b/README.md @@ -183,6 +183,8 @@ export TYPESAFE_API_KEY=... # Jev social-post screening (optional) For Azure OpenAI, copy `.env.enterprise.example` to `.env.enterprise` and fill in your credentials. +To run on your ChatGPT Plus or Pro plan instead of an API key, choose "Subscription" in the CLI's provider menu, or set `llm_provider: "chatgpt"`. Sign in once with `tradingagents login chatgpt`: it prints an address to open in your browser, which returns to this machine on `127.0.0.1`. When the browser runs on another machine, or TradingAgents runs in Docker (`docker compose run --rm tradingagents login chatgpt`), paste the address the browser ends up on. The sign-in is kept in `~/.tradingagents/chatgpt-auth.json`, and `tradingagents logout chatgpt` revokes it. Runs count toward your plan's usage limits, and the plan does not accept `temperature` or `max_tokens`. + For AWS Bedrock, install the extra with `pip install ".[bedrock]"`, set `llm_provider: "bedrock"`, configure AWS credentials (environment variables, `~/.aws/credentials`, or an IAM role) and `AWS_DEFAULT_REGION`, and use a Bedrock model ID, e.g. `us.anthropic.claude-opus-5-5`. For local models, configure Ollama with `llm_provider: "ollama"`. The default endpoint is `http://localhost:11434/v1`; set `OLLAMA_BASE_URL` to point at a remote `ollama-serve`. Pull models with `ollama pull `, and pick "Custom model ID" in the CLI for any model not listed by default. @@ -213,6 +215,8 @@ tradingagents --ticker NVDA --date 2026-09-23 --analysts market,news,fundamental ``` Each flag skips only its own question. Run without a terminal, a missing answer stops the run before it starts and names the flag or variable to set. +At start-up the interactive CLI mentions a newer release and notices from Tauric Research. It checks at most once a day, in the background, and sends nothing about your runs; set `TRADINGAGENTS_NO_UPDATE_CHECK=1` to turn it off. Runs without a terminal never check. + A saved report also includes `complete_report.html`, the report as one page with its sections listed beside the text, for reading in a browser, on a phone or in print. Answering the save question at the prompt also asks about the page and can open it in your browser; `--no-html` skips it, and so does `ta.save_reports(state, "NVDA", html=False)` from Python. ### Markets and tickers @@ -243,7 +247,7 @@ An interface will appear showing results as they load, letting you track the age ### Implementation Details -We built TradingAgents with LangGraph to ensure flexibility and modularity. The framework supports multiple LLM providers: OpenAI, Google, Anthropic, xAI, DeepSeek, Qwen (Alibaba DashScope, international and China endpoints), GLM (Zhipu), MiniMax (global + China), OpenRouter, Ollama for local models, and Azure OpenAI for enterprise. +We built TradingAgents with LangGraph to ensure flexibility and modularity. The framework supports multiple LLM providers: OpenAI, Google, Anthropic, xAI, DeepSeek, Qwen (Alibaba DashScope, international and China endpoints), GLM (Zhipu), MiniMax (global + China), OpenRouter, Ollama for local models, Azure OpenAI for enterprise, and your own ChatGPT plan. ### Python Usage