Document QA chatbot with vector search and Groq LLM

This automation enables fast deployment of a local document-based Q&A system. Built on n8n and LangChain, it uses in-memory vector storage and Groq´s LLM to deliver accurate, context-aware responses via a chat interface. Ideal for internal knowledge bases, reports, and technical documentation.

## Who it´s for
- Document specialists needing quick access to information
- Support teams managing internal knowledge bases
- Developers prototyping document-based chatbots
- Analysts processing textual reports and queries

## What the automation does
- Loads a text file from the local file system
- Splits content into chunks using Recursive Text Splitter
- Embeds chunks via Cohere and stores them in an in-memory vector store
- On receiving a query via chat trigger, retrieves relevant context
- Sends context to Groq´s Llama model for response generation
- Returns a natural-language answer through the chat interface

## What´s included
- Ready-to-use n8n workflow with LangChain agent logic
- Trigger handlers: manual start and chat input
- Integrations with Cohere (embeddings), Groq (LLM), and local file system
- Basic Markdown setup guide for deployment and adaptation

## Requirements for setup
- n8n instance (self-hosted or cloud)
- API keys for Cohere and Groq
- Access to a plain text file on local disk
- Installed dependencies: langchain, cohere, groq, faiss (or equivalent)

## Benefits and outcomes
- Rapid information retrieval from large text documents
- Automated solution lookup in technical docs
- Reduced support team workload via self-service answers
- Prototype QA systems without external databases
- Test chatbots on real internal data

## Important: template only
Important: you are purchasing a ready-made automation workflow template only. Rollout into your infrastructure, connecting specific accounts and services, 1:1 setup help, custom adjustments for non-standard stacks and any consulting support are provided as a separate paid service at an individual rate. To discuss custom work or 1:1 help, contact via Telegram: @gleb923.