TradingAgents/tradingagents/agents/trader/trader.py

58 lines
2.7 KiB
Python

import functools
import time
import json
def create_trader(llm, memory):
def trader_node(state, name):
ticker = state["ticker_of_interest"]
investment_plan = state["investment_plan"]
market_research_report = state["market_report"]
sentiment_report = state["sentiment_report"]
news_report = state["news_report"]
fundamentals_report = state["fundamentals_report"]
curr_situation = f"{market_research_report}\n\n{sentiment_report}\n\n{news_report}\n\n{fundamentals_report}"
past_memories = memory.get_memories(curr_situation, n_matches=2)
past_memory_str = ""
if past_memories:
for i, rec in enumerate(past_memories, 1):
past_memory_str += rec["recommendation"] + "\n\n"
else:
past_memory_str = "No past memories found."
base_asset = ""
quote_asset = ""
if isinstance(ticker, str) and "/" in ticker:
base_asset, quote_asset = ticker.split("/", 1)
pair_context = ticker
if base_asset and quote_asset:
pair_context = f"{ticker} (base={base_asset}, quote={quote_asset})"
context = {
"role": "user",
"content": f"Based on a comprehensive analysis by a team of analysts, here is an investment plan for the crypto pair {pair_context}. This plan incorporates insights from current technical market trends, macroeconomic indicators, and social media sentiment. Use this plan as a foundation for evaluating your next crypto trading decision.\n\nProposed Investment Plan: {investment_plan}\n\nLeverage these insights to make an informed and strategic decision for this crypto market.",
}
messages = [
{
"role": "system",
"content": f"""You are a crypto trading agent analyzing cryptocurrency market data for a specific trading pair (e.g., BTC/USDT). Based on your analysis, provide a specific recommendation to BUY, SELL, or HOLD the base asset relative to the quote asset for the pair {pair_context}, along with the quantity for BUY and SELL \
End with a firm decision and always conclude your response with 'FINAL TRANSACTION PROPOSAL: **BUY/HOLD/SELL** **QUANTITY**' to confirm your recommendation. \
Do not forget to utilize lessons from past decisions to learn from your mistakes. Here is some reflections from similar situations you traded in and the lessons learned: {past_memory_str}""",
},
context,
]
result = llm.invoke(messages)
return {
"messages": [result],
"trader_investment_plan": result.content,
"sender": name,
}
return functools.partial(trader_node, name="Trader")