graph TD %%{init: {'theme': 'mc','layout': 'elk'}}%% Prompt-sistq[<div><img alt="logo" src="/_astro/square-terminal.BMOXc-nZ.svg" style="height: 20px !important;width: 20px !important"/></div>Prompt] style Prompt-sistq stroke:#a170ff ChatInput-s9apd[<div><img alt="logo" src="/_astro/messages-square.BaSDmT6g.svg" style="height: 20px !important;width: 20px !important"/></div>Entrada de Usuario] style ChatInput-s9apd stroke:#a170ff Prompt-3ogxb[<div><img alt="logo" src="/_astro/square-terminal.BMOXc-nZ.svg" style="height: 20px !important;width: 20px !important"/></div>Prompt] style Prompt-3ogxb stroke:#a170ff OpenAIModel-kp0l0[<div><img alt="logo" src="/_astro/openAI.BhmuxEs3.svg" style="height: 20px !important;width: 20px !important"/></div>Analizador de Intención] style OpenAIModel-kp0l0 stroke:#a170ff OpenAIModel-712yx[<div><img alt="logo" src="/_astro/openAI.BhmuxEs3.svg" style="height: 20px !important;width: 20px !important"/></div>Generador de Respuesta] style OpenAIModel-712yx stroke:#a170ff Prompt-3y0vr[<div><img alt="logo" src="/_astro/square-terminal.BMOXc-nZ.svg" style="height: 20px !important;width: 20px !important"/></div>Constructor de Respuesta Final] style Prompt-3y0vr stroke:#a170ff ChatOutput-up1u4[<div><img alt="logo" src="/_astro/messages-square.BaSDmT6g.svg" style="height: 20px !important;width: 20px !important"/></div>Chat Output] style ChatOutput-up1u4 stroke:#a170ff OpenAIModel-o282l[<div><img alt="logo" src="/_astro/openAI.BhmuxEs3.svg" style="height: 20px !important;width: 20px !important"/></div>OpenAI] style OpenAIModel-o282l stroke:#a170ff YFinanceToolComponent-zoqeh[<div><img alt="logo" src="/_astro/badge-euro.b_yZ5I36.svg" style="height: 20px !important;width: 20px !important"/></div>YFinance Tool] style YFinanceToolComponent-zoqeh stroke:#a170ff AdvancedAgent-n79by[Agent] style AdvancedAgent-n79by stroke:#a170ff OpenAIModel-712yx -.- ChatOutput-up1u4 linkStyle 0 stroke:#a170ff Prompt-3y0vr -.- OpenAIModel-712yx linkStyle 1 stroke:#a170ff Prompt-sistq -.- OpenAIModel-kp0l0 linkStyle 2 stroke:#a170ff ChatInput-s9apd -.- Prompt-sistq linkStyle 3 stroke:#a170ff ChatInput-s9apd -.- Prompt-3y0vr linkStyle 4 stroke:#a170ff OpenAIModel-kp0l0 -.- Prompt-3ogxb linkStyle 5 stroke:#a170ff AdvancedAgent-n79by -.- Prompt-3y0vr linkStyle 6 stroke:#a170ff Prompt-3ogxb -.- AdvancedAgent-n79by linkStyle 7 stroke:#a170ff YFinanceToolComponent-zoqeh -.- AdvancedAgent-n79by linkStyle 8 stroke:#a170ff OpenAIModel-o282l -.- AdvancedAgent-n79by linkStyle 9 stroke:#a170ff

Stock Queries Workflow Documentation

🧩 Overview

This workflow automates the process of answering user queries about financial markets. A user submits a question, the system extracts relevant ticker symbols, retrieves up‑to‑date market data via Yahoo Finance, and synthesises a concise, data‑driven response.

⚙️ Main Features

User‑friendly chat input that captures natural language questions.
Automatic ticker extraction using a language model prompt.
Tool‑enabled agent that queries Yahoo Finance for the required data.
Two‑stage reasoning: the agent first gathers data, then generates the final answer.
Seamless integration of prompts, models, tools, and output display.

🔄 Workflow Steps

Component Name	Role in the Workflow	Key Inputs	Key Outputs
Chat Input	Receives the user’s natural‑language question.	User message	Text message
Prompt (Ticker Extraction)	Forms a prompt that asks the LLM to list tickers mentioned in the user’s message.	User message	Prompt message
OpenAI Model	Generates a list of ticker symbols from the prompt.	Prompt message	Text list of tickers
Prompt (Agent Instruction)	Creates a detailed instruction prompt for the agent, embedding the extracted ticker list.	List of tickers	Prompt message
Advanced Agent	Processes the instruction, decides which tool to invoke, and compiles the raw data into a structured format.	Prompt message	Structured ticker data
YFinance Tool	Retrieves current market information for the specified ticker(s) using Yahoo Finance.	Ticker symbol(s)	Financial data (price, news, etc.)
Prompt (Final Response)	Builds a prompt that asks the LLM to produce a user‑friendly answer based on the retrieved data and the original question.	Financial data, original user message	Prompt message
OpenAI Model	Generates the final, polished answer to the user.	Prompt message	Text answer
Chat Output	Sends the answer back to the user in the chat interface.	Text answer	Displayed chat message

🧠 Notes

The workflow relies on an OpenAI API key for all language model calls; ensure the key is kept secure.
Yahoo Finance data retrieval requires network access and may be subject to rate limits or temporary outages.
The agent’s decision logic can be overridden by changing the Agent Description or by adding additional tools.
The system can be extended with fallback models or additional data sources if the primary OpenAI model fails or if higher‑frequency data is required.
All components are stateless except the agent, which maintains short‑term memory for multi‑turn interactions.
The prompt templates are designed to be concise and avoid excessive token usage, improving response latency.