TradingAgents/tradingagents/agents/analysts/news_analyst.py

64 lines
3.0 KiB
Python

from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
import time
import json
from tradingagents.agents.utils.agent_utils import get_news, get_global_news
from tradingagents.agents.utils.data_prefetch import prefetch_news_data, format_news_context
from tradingagents.dataflows.config import get_config
def create_news_analyst(llm):
def news_analyst_node(state):
current_date = state["trade_date"]
ticker = state["company_of_interest"]
# Pre-fetch data so it's available even if the backend doesn't support tool calling
prefetched = prefetch_news_data(ticker, current_date)
data_context = format_news_context(prefetched)
tools = [
get_news,
get_global_news,
]
system_message = (
"You are a news researcher tasked with analyzing recent news and trends over the past week. Please write a comprehensive report of the current state of the world that is relevant for trading and macroeconomics. Use the provided news data below for your analysis. If you have access to callable tools (get_news, get_global_news), you may use them for additional data. Do not simply state the trends are mixed, provide detailed and finegrained analysis and insights that may help traders make decisions."
+ """ Make sure to append a Markdown table at the end of the report to organize key points in the report, organized and easy to read."""
)
prompt = ChatPromptTemplate.from_messages(
[
(
"system",
"You are a helpful AI assistant, collaborating with other assistants."
" Use the provided data below to write your analysis report."
" If you have access to callable tools, you may use them for additional data."
" If you or any other assistant has the FINAL TRANSACTION PROPOSAL: **BUY/HOLD/SELL** or deliverable,"
" prefix your response with FINAL TRANSACTION PROPOSAL: **BUY/HOLD/SELL** so the team knows to stop."
"\n{system_message}"
"\nFor your reference, the current date is {current_date}. We are looking at the company {ticker}"
"\n\n--- PRE-FETCHED NEWS DATA ---\n{data_context}\n--- END PRE-FETCHED DATA ---",
),
MessagesPlaceholder(variable_name="messages"),
]
)
prompt = prompt.partial(system_message=system_message)
prompt = prompt.partial(current_date=current_date)
prompt = prompt.partial(ticker=ticker)
prompt = prompt.partial(data_context=data_context)
chain = prompt | llm.bind_tools(tools)
result = chain.invoke(state["messages"])
report = ""
if len(result.tool_calls) == 0:
report = result.content
return {
"messages": [result],
"news_report": report,
}
return news_analyst_node