Build AI Business Solutions with Workflow Automation | NappAI - Template: Atencion al Cliente Ecommerce

graph TD %%{init: {'theme': 'mc','layout': 'elk'}}%% ChatInput-larrt[<div><img src="/_astro/messages-square.BaSDmT6g.svg" style="height: 20px !important;width: 20px !important"/></div>Chat Input] style ChatInput-larrt stroke:#a170ff LanggraphReactAgent-e7sh0[Detector de Intención] style LanggraphReactAgent-e7sh0 stroke:#a170ff ConditionalRouter-e0whx[Conditional Router] style ConditionalRouter-e0whx stroke:#a170ff ConditionalRouter-k37bb[Conditional Router2] style ConditionalRouter-k37bb stroke:#a170ff ConditionalRouter-7onzp[Conditional Router3] style ConditionalRouter-7onzp stroke:#a170ff GoogleGenerativeAIModel-hrflu[Gemini] style GoogleGenerativeAIModel-hrflu stroke:#a170ff LanggraphReactAgent-feiuj[Agent] style LanggraphReactAgent-feiuj stroke:#a170ff GoogleGenerativeAIModel-0aobu[Gemini2] style GoogleGenerativeAIModel-0aobu stroke:#a170ff GoogleGenerativeAIEmbeddings-fnjt0[Google Generative AI Embeddings] style GoogleGenerativeAIEmbeddings-fnjt0 stroke:#a170ff LanggraphReactAgent-r6l2z[Agent2] style LanggraphReactAgent-r6l2z stroke:#a170ff APIRequest-78xr1[API Request] style APIRequest-78xr1 stroke:#a170ff LanggraphReactAgent-py6gc[Agent3] style LanggraphReactAgent-py6gc stroke:#a170ff GoogleGenerativeAIModel-y15kz[Gemini3] style GoogleGenerativeAIModel-y15kz stroke:#a170ff GoogleGenerativeAIModel-gta86[Gemini4] style GoogleGenerativeAIModel-gta86 stroke:#a170ff TelegramMessage-zvrp9[Telegram Message] style TelegramMessage-zvrp9 stroke:#a170ff ChatOutput-16z2g[<div><img src="/_astro/messages-square.BaSDmT6g.svg" style="height: 20px !important;width: 20px !important"/></div>Chat Output] style ChatOutput-16z2g stroke:#a170ff ChatOutput-0vfib[<div><img src="/_astro/messages-square.BaSDmT6g.svg" style="height: 20px !important;width: 20px !important"/></div>Chat Output2] style ChatOutput-0vfib stroke:#a170ff ChatOutput-7h910[<div><img src="/_astro/messages-square.BaSDmT6g.svg" style="height: 20px !important;width: 20px !important"/></div>Chat Output3] style ChatOutput-7h910 stroke:#a170ff Prompt-c8k88[<div><img src="/_astro/square-terminal.BMOXc-nZ.svg" style="height: 20px !important;width: 20px !important"/></div>Prompt] style Prompt-c8k88 stroke:#a170ff LanggraphRAGAgent-4j24w[RAG Agent] style LanggraphRAGAgent-4j24w stroke:#a170ff GoogleGenerativeAIModel-lcmte[Gemini5] style GoogleGenerativeAIModel-lcmte stroke:#a170ff GoogleGenerativeAIEmbeddings-mn2ew[Google Generative AI Embeddings2] style GoogleGenerativeAIEmbeddings-mn2ew stroke:#a170ff SplitText-xm92m[<div><img src="/_astro/scissors-line-dashed.CajsPhTx.svg" style="height: 20px !important;width: 20px !important"/></div>Split Text] style SplitText-xm92m stroke:#a170ff GDriveFilesComponent-q2n9y[<div><img src="/_astro/google_drive.wKmDsV2c.svg" style="height: 20px !important;width: 20px !important"/></div>Google Drive File Manager] style GDriveFilesComponent-q2n9y stroke:#a170ff ParseData-dpd2k[<div><img src="/_astro/braces.Djq0PW4_.svg" style="height: 20px !important;width: 20px !important"/></div>Parse Data] style ParseData-dpd2k stroke:#a170ff Chroma-d83zz[<div><img src="/_astro/chroma.CDTUBZSx.svg" style="height: 20px !important;width: 20px !important"/></div>Chroma DB] style Chroma-d83zz stroke:#a170ff Chroma-0gshk[<div><img src="/_astro/chroma.CDTUBZSx.svg" style="height: 20px !important;width: 20px !important"/></div>Chroma DB2] style Chroma-0gshk stroke:#a170ff ChatInput-larrt -.- LanggraphReactAgent-e7sh0 linkStyle 0 stroke:#a170ff GoogleGenerativeAIModel-hrflu -.- LanggraphReactAgent-e7sh0 linkStyle 1 stroke:#a170ff LanggraphReactAgent-e7sh0 -.- ConditionalRouter-e0whx linkStyle 2 stroke:#a170ff ChatInput-larrt -.- ConditionalRouter-e0whx linkStyle 3 stroke:#a170ff ChatInput-larrt -.- ConditionalRouter-k37bb linkStyle 4 stroke:#a170ff ChatInput-larrt -.- ConditionalRouter-7onzp linkStyle 5 stroke:#a170ff LanggraphReactAgent-e7sh0 -.- ConditionalRouter-k37bb linkStyle 6 stroke:#a170ff LanggraphReactAgent-e7sh0 -.- ConditionalRouter-7onzp linkStyle 7 stroke:#a170ff ConditionalRouter-e0whx -.- LanggraphReactAgent-feiuj linkStyle 8 stroke:#a170ff GoogleGenerativeAIModel-0aobu -.- LanggraphReactAgent-feiuj linkStyle 9 stroke:#a170ff ConditionalRouter-k37bb -.- LanggraphReactAgent-r6l2z linkStyle 10 stroke:#a170ff APIRequest-78xr1 -.- LanggraphReactAgent-r6l2z linkStyle 11 stroke:#a170ff ConditionalRouter-7onzp -.- LanggraphReactAgent-py6gc linkStyle 12 stroke:#a170ff GoogleGenerativeAIModel-y15kz -.- LanggraphReactAgent-r6l2z linkStyle 13 stroke:#a170ff GoogleGenerativeAIModel-gta86 -.- LanggraphReactAgent-py6gc linkStyle 14 stroke:#a170ff TelegramMessage-zvrp9 -.- LanggraphReactAgent-py6gc linkStyle 15 stroke:#a170ff LanggraphReactAgent-py6gc -.- ChatOutput-0vfib linkStyle 16 stroke:#a170ff LanggraphReactAgent-r6l2z -.- ChatOutput-7h910 linkStyle 17 stroke:#a170ff LanggraphReactAgent-feiuj -.- ChatOutput-16z2g linkStyle 18 stroke:#a170ff Prompt-c8k88 -.- LanggraphReactAgent-r6l2z linkStyle 19 stroke:#a170ff GoogleGenerativeAIModel-lcmte -.- LanggraphRAGAgent-4j24w linkStyle 20 stroke:#a170ff ParseData-dpd2k -.- SplitText-xm92m linkStyle 21 stroke:#a170ff GDriveFilesComponent-q2n9y -.- ParseData-dpd2k linkStyle 22 stroke:#a170ff LanggraphRAGAgent-4j24w -.- LanggraphReactAgent-feiuj linkStyle 23 stroke:#a170ff Chroma-d83zz -.- LanggraphRAGAgent-4j24w linkStyle 24 stroke:#a170ff GoogleGenerativeAIEmbeddings-fnjt0 -.- Chroma-d83zz linkStyle 25 stroke:#a170ff SplitText-xm92m -.- Chroma-0gshk linkStyle 26 stroke:#a170ff GoogleGenerativeAIEmbeddings-mn2ew -.- Chroma-0gshk linkStyle 27 stroke:#a170ff

🧩 Overview

The workflow is a customer‑service assistant that interprets a user’s message, classifies the request into one of three intent levels, and routes it to the appropriate automated responder.
At the lowest level it performs knowledge‑base retrieval using a Retrieval‑Augmented Generation (RAG) agent.
At the medium level it calls an external API and returns the result.
At the highest level it escalates the request to human staff by sending a Telegram notification.
All agents produce a reply that is displayed in the chat interface, keeping the user experience seamless and consistent.

⚙️ Main Features

Intention classification that determines whether a query is informational, requires data retrieval, or needs human intervention.
RAG retrieval that consults a vector database built from company documents.
API integration that retrieves real‑time data from an external service.
Telegram escalation that notifies the support team when a request cannot be auto‑handled.
Unified chat interface that shows the result of each agent in the same conversational flow.

🔄 Workflow Steps

Component Name	Role in the Workflow	Key Inputs	Key Outputs
Chat Input	Receives the raw text from the user.	User message	User message
Intent Detection Agent	Classifies the intent as nivel1, nivel2 or nivel3.	User message	Intent keyword
Intent Router (nivel1)	Directs nivel1 intent to the RAG agent.	Intent keyword	True/False route
Level 1 Retrieval Agent	Performs RAG using embeddings and a vector store, then generates a natural‑language answer.	User message	Answer text
Level 1 Chat Output	Displays the RAG answer to the user.	Answer text	Displayed chat message
Intent Router (nivel2)	Directs nivel2 intent to the API agent.	Intent keyword	True/False route
Level 2 API Agent	Calls an external HTTP endpoint, parses the result, and formats a response.	User message	API response text
Level 2 Chat Output	Displays the API result to the user.	API response text	Displayed chat message
Intent Router (nivel3)	Directs nivel3 intent to the Telegram notification agent.	Intent keyword	True/False route
Level 3 Notification Agent	Sends a Telegram message to the support team to request manual handling.	User message	Telegram notification
Level 3 Chat Output	Confirms to the user that their request has been escalated.	Escalation confirmation	Displayed chat message

The embeddings, vector database, and tool configurations are instantiated once during workflow initialization and are reused for every request.

🧠 Notes

The intent detection agent is a lightweight LLM classifier that outputs a single keyword; it uses the system prompt to enforce strict, one‑word responses.
The RAG agent employs a Chroma vector store and Google Gemini embeddings. It is configured to use a retrieval pipeline that embeds incoming text, searches for the most relevant documents, and augments the LLM response.
The API agent is supplied with an APIRequest tool; its system prompt guarantees that the LLM will only formulate calls using the provided tool interface.
The Telegram agent uses a dedicated Telegram bot token. It only sends plain text notifications (Send Text operation).
All agents are wrapped as Langgraph React agents, so they can be composed as tools for each other, allowing dynamic routing within a single graph.
The workflow assumes that the user’s query will always match one of the three intent categories; if none match, the default branch is silent, and no reply is produced.
The ConditionalRouter components perform string equality checks; they are case‑insensitive by default.
The vector store and embeddings are set up with a 1000‑character chunk size and a 200‑character overlap, which balances context length and semantic continuity.