charieswei
/
TradingAgents
mirror of https://github.com/TauricResearch/TradingAgents.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

doc:add doc to researchers model

This commit is contained in:
2403_87681582 2025-12-07 11:33:44 +08:00
parent 13b826a31d
commit c130b8f395
4 changed files with 94 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
.env.example
View File

@ -1,2 +1,2 @@
ALPHA_VANTAGE_API_KEY=alpha_vantage_api_key_placeholder
OPENAI_API_KEY=openai_api_key_placeholder
ALPHA_VANTAGE_API_KEY=W47FRS433AD7DVGQ
OPENAI_API_KEY=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

4
cli/utils.py
View File

@ -204,8 +204,8 @@ def select_deep_thinking_agent(provider) -> str:
"google": [
("Gemini 2.0 Flash-Lite - Cost efficiency and low latency", "gemini-2.0-flash-lite"),
("Gemini 2.0 Flash - Next generation features, speed, and thinking", "gemini-2.0-flash"),
("Gemini 2.5 Flash - Adaptive thinking, cost efficiency", "gemini-2.5-flash-preview-05-20"),
("Gemini 2.5 Pro", "gemini-2.5-pro-preview-06-05"),
("Gemini 2.5 Flash - Adaptive thinking, cost efficiency", "gemini-2.5-flash"),
("Gemini 2.5 Pro", "gemini-2.5-pro"),
],
"openrouter": [
("DeepSeek V3 - a 685B-parameter, mixture-of-experts model", "deepseek/deepseek-chat-v3-0324:free"),

62
tradingagents/agents/researchers/bear_researcher.py
View File

@ -3,37 +3,58 @@ import time
import json
# 定义一个创建“看空”研究员（Bear Researcher）节点的工厂函数
def create_bear_researcher(llm, memory):
def bear_node(state) -> dict:
investment_debate_state = state["investment_debate_state"]
history = investment_debate_state.get("history", "")
bear_history = investment_debate_state.get("bear_history", "")
"""
创建看空分析师（Bear Analyst）的 LangGraph 节点函数。
Args:
llm: 语言模型实例，用于生成分析和论点。
memory: 外部记忆/检索系统，用于获取历史教训。
Returns:
Callable: 接受当前状态并返回更新后的状态的节点函数 (bear_node)。
"""
def bear_node(state) -> dict:
"""
看空分析师节点的核心逻辑。
根据全局状态中的报告和辩论历史，生成看空论点并更新状态。
"""
# --- 1. 获取当前状态数据 ---
investment_debate_state = state["investment_debate_state"]
# 提取辩论历史和上一轮多头（Bull）的回复
history = investment_debate_state.get("history", "")
current_response = investment_debate_state.get("current_response", "")
# 提取所有研究报告作为论证的证据
market_research_report = state["market_report"]
sentiment_report = state["sentiment_report"]
news_report = state["news_report"]
fundamentals_report = state["fundamentals_report"]
# --- 2. 记忆检索与格式化 ---
# 合并所有报告，作为检索记忆的查询（寻找相似情况下的历史教训）
curr_situation = f"{market_research_report}\n\n{sentiment_report}\n\n{news_report}\n\n{fundamentals_report}"
# 从外部记忆中检索历史记录/教训
past_memories = memory.get_memories(curr_situation, n_matches=2)
# 格式化检索到的历史教训，作为 Prompt 的一部分
past_memory_str = ""
for i, rec in enumerate(past_memories, 1):
past_memory_str += rec["recommendation"] + "\n\n"
for rec in past_memories:
past_memory_str += rec.get("recommendation", "") + "\n\n"
# --- 3. 构建 Prompt 并调用 LLM ---
prompt = f"""You are a Bear Analyst making the case against investing in the stock. Your goal is to present a well-reasoned argument emphasizing risks, challenges, and negative indicators. Leverage the provided research and data to highlight potential downsides and counter bullish arguments effectively.
Key points to focus on:
- Risks and Challenges: Highlight factors like market saturation, financial instability, or macroeconomic threats that could hinder the stock's performance.
- Competitive Weaknesses: Emphasize vulnerabilities such as weaker market positioning, declining innovation, or threats from competitors.
- Negative Indicators: Use evidence from financial data, market trends, or recent adverse news to support your position.
- Bull Counterpoints: Critically analyze the bull argument with specific data and sound reasoning, exposing weaknesses or over-optimistic assumptions.
- Engagement: Present your argument in a conversational style, directly engaging with the bull analyst's points and debating effectively rather than simply listing facts.
- Risks and Challenges: Highlight factors like market saturation, financial instability, or macroeconomic threats.
- Bull Counterpoints: Critically analyze the bull argument with specific data and sound reasoning.
- Engagement: Present your argument in a conversational style, directly engaging with the bull analyst's points.
Resources available:
Market research report: {market_research_report}
Social media sentiment report: {sentiment_report}
Latest world affairs news: {news_report}
@ -41,21 +62,32 @@ Company fundamentals report: {fundamentals_report}
Conversation history of the debate: {history}
Last bull argument: {current_response}
Reflections from similar situations and lessons learned: {past_memory_str}
Use this information to deliver a compelling bear argument, refute the bull's claims, and engage in a dynamic debate that demonstrates the risks and weaknesses of investing in the stock. You must also address reflections and learn from lessons and mistakes you made in the past.
"""
# 调用 LLM 生成看空分析师的回复
response = llm.invoke(prompt)
# 格式化看空分析师的论点，加上身份前缀
argument = f"Bear Analyst: {response.content}"
# --- 4. 更新全局状态 ---
new_investment_debate_state = {
# 更新完整的辩论历史
"history": history + "\n" + argument,
"bear_history": bear_history + "\n" + argument,
"bull_history": investment_debate_state.get("bull_history", ""),
# 更新看空方的历史记录 (便于后续总结和自我反思)
"bear_history": investment_debate_state.get("bear_history", "") + "\n" + argument,
# 将当前回复设置为看空方的论点，供下一轮（如看多方）使用
"current_response": argument,
# 增加辩论的轮数计数
"count": investment_debate_state["count"] + 1,
# 保持看多方的历史不变 (从旧状态中获取)
"bull_history": investment_debate_state.get("bull_history", ""),
}
# 返回包含更新后的投资辩论状态的字典，用于 LangGraph 传递
return {"investment_debate_state": new_investment_debate_state}
# 返回定义的节点函数
return bear_node

47
tradingagents/agents/researchers/bull_researcher.py
View File

@ -3,25 +3,54 @@ import time
import json
# 定义一个创建“看多”研究员（Bull Researcher）节点的工厂函数
def create_bull_researcher(llm, memory):
"""
创建看多分析师（Bull Analyst）的 LangGraph 节点函数。
Args:
llm: 语言模型实例，用于生成分析和论点。
memory: 外部记忆/检索系统，用于获取历史经验和教训。
Returns:
Callable: 接受当前状态并返回更新后的状态的节点函数 (bull_node)。
"""
# 内部定义的节点函数，接收整个状态字典
def bull_node(state) -> dict:
"""
看多分析师节点的核心逻辑。
根据全局状态中的报告和辩论历史，生成看多论点并更新状态。
"""
# --- 1. 获取当前状态数据 ---
investment_debate_state = state["investment_debate_state"]
# 提取辩论的完整历史和上一轮空头（Bear）的回复
history = investment_debate_state.get("history", "")
bull_history = investment_debate_state.get("bull_history", "")
current_response = investment_debate_state.get("current_response", "")
# 提取所有研究报告作为论证的证据
market_research_report = state["market_report"]
sentiment_report = state["sentiment_report"]
news_report = state["news_report"]
fundamentals_report = state["fundamentals_report"]
# --- 2. 记忆检索与格式化 ---
# 合并所有报告，作为检索记忆的查询
curr_situation = f"{market_research_report}\n\n{sentiment_report}\n\n{news_report}\n\n{fundamentals_report}"
# 从外部记忆中检索历史记录/教训
past_memories = memory.get_memories(curr_situation, n_matches=2)
# 格式化检索到的历史教训，作为 Prompt 的一部分
past_memory_str = ""
for i, rec in enumerate(past_memories, 1):
past_memory_str += rec["recommendation"] + "\n\n"
for rec in past_memories:
# 假设每个记忆记录包含一个 "recommendation" 字段
past_memory_str += rec.get("recommendation", "") + "\n\n"
# --- 3. 构建 Prompt 并调用 LLM ---
# 构建发送给 LLM 的提示（Prompt），指导其扮演看多分析师的角色
prompt = f"""You are a Bull Analyst advocating for investing in the stock. Your task is to build a strong, evidence-based case emphasizing growth potential, competitive advantages, and positive market indicators. Leverage the provided research and data to address concerns and counter bearish arguments effectively.
Key points to focus on:
@ -42,18 +71,28 @@ Reflections from similar situations and lessons learned: {past_memory_str}
Use this information to deliver a compelling bull argument, refute the bear's concerns, and engage in a dynamic debate that demonstrates the strengths of the bull position. You must also address reflections and learn from lessons and mistakes you made in the past.
"""
# 调用 LLM 生成看多分析师的回复
response = llm.invoke(prompt)
# 格式化看多分析师的论点，加上身份前缀
argument = f"Bull Analyst: {response.content}"
# --- 4. 更新全局状态 ---
new_investment_debate_state = {
# 更新完整的辩论历史
"history": history + "\n" + argument,
# 更新看多方的历史记录 (便于后续总结)
"bull_history": bull_history + "\n" + argument,
# 保持看空方的历史不变 (从旧状态中获取)
"bear_history": investment_debate_state.get("bear_history", ""),
# 将当前回复设置为看多方的论点，供下一轮（如看空方）使用
"current_response": argument,
# 增加辩论的轮数计数
"count": investment_debate_state["count"] + 1,
}
# 返回包含更新后的投资辩论状态的字典，用于 LangGraph 传递
return {"investment_debate_state": new_investment_debate_state}
return bull_node
# 返回定义的节点函数 (工厂函数模式)
return bull_node