# Create an all-in-one Discord assistant with Gemini and Llama: n8n workflow > Started by another system calling it. It calls services over plain HTTP rather than through connectors. Source: https://millionrounds.com/workflow/create-an-all-in-one-discord-assistant-with-gemini-and-llama (Millionrounds; every figure on the page links to its filing or article) [Automation library](https://millionrounds.com/workflows) · [AI assistants](https://millionrounds.com/workflows?category=AI+assistants#library) # Create an all-in-one Discord assistant with Gemini and Llama Started by another system calling it. It calls services over plain HTTP rather than through connectors. It puts Gemini and OpenRouter behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 36 steps, 3 branches: large, and worth reading before you trust it with anything live. Large Calls a model: Gemini, OpenRouter Retrieval [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fcreate-an-all-in-one-discord-assistant-with-gemini-and-llama) **36 steps** Large: read it before trusting it with anything live **3** Branches: places the flow splits **0** Loops or waits **0** Services by connector: it calls them over plain HTTP ## The flow Starts it 5 Model 11 Logic 16 Service 4 The steps in the order they run, from what starts it. - 1 **Webhook** Webhook *Starts it* - 2 **Simple Memory** Memory Buffer Window *Model* - 3 **Google Gemini Chat Model1** Lm Chat Google Gemini *Model* - 4 **Simple Memory1** Memory Buffer Window *Model* - 5 **Simple Memory2** Memory Buffer Window *Model* - 6 **Google Gemini Chat Model** Lm Chat Google Gemini *Model* - 7 **OpenRouter Chat Model** Lm Chat Open Router *Model* - 8 **Google Gemini Chat Model2** Lm Chat Google Gemini *Model* - 9 **Has Atc** If *Logic* - 10 **Discord AI Response Agent** Agent *Model* - 11 **AI Agent - Create Image From Prompt** Agent *Model* - 12 **Discord AI Response Agent1** Agent *Model* - 13 **Discord AI Response Agent2** Agent *Model* - 14 **Code1** Code *Logic* - 15 **If** If *Logic* - 16 **correctNaming** Code *Logic* - 17 **Code - Clean Json** Code *Logic* - 18 **correctNaming1** Code *Logic* - 19 **correctNaming3** Code *Logic* - 20 **If1** If *Logic* - 21 **Code** Code *Logic* - 22 **Respond to Webhook** Respond To Webhook *Starts it* - 23 **Code - Get Prompt** Code *Logic* - 24 **Respond to Webhook3** Respond To Webhook *Starts it* - 25 **Respond to Webhook4** Respond To Webhook *Starts it* - 26 **HTTP Request** Http Request *Service* - 27 **HTTP Request1** Http Request *Service* - 28 **Fields - Set Values** Set *Logic* - 29 **Code - Set Filename** Code *Logic* - 30 **correctNaming2** Code *Logic* - 31 **Create Image** Http Request *Service* - 32 **Error Handler** Code *Logic* - 33 **Handle Respons** Code *Logic* - 34 **Change Link To Be Sort** Http Request *Service* - 35 **Format Discord Response** Code *Logic* - 36 **Respond to Webhook2** Respond To Webhook *Starts it* ## How it's built - **Starts on:** Another system calling it - **Steps:** 36, with 3 branches - **Size:** Large: read it before trusting it with anything live - **Connects to:** Nothing by connector; it calls services over plain HTTP - **Model:** Gemini, OpenRouter - **Retrieval:** Answers are drawn from documents you supply, not from the model alone ## Questions What does it need to run? An n8n account, and a key for Gemini and OpenRouter. You connect your own accounts after importing it; none are included. What starts it? It starts on another system calling it. Does it use AI? Yes. It calls Gemini and OpenRouter. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n. How long does it take to set up? Take your time. At 36 steps it is large: read it before trusting it with anything live. How do I import it? Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts. **Before you run it** Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 36 steps before you point it at anything that matters. ## Run it in n8n - **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n) - **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fcreate-an-all-in-one-discord-assistant-with-gemini-and-llama) - **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts. Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind. ## Workflows like it Also ai assistants, with the same services where possible, closest in size first. - [**Send GoHighLevel WhatsApp and email auto-replies with Redis** 36 steps · calls a model · Google Drive, Pinecone](https://millionrounds.com/workflow/send-gohighlevel-whatsapp-and-email-auto-replies-with-redis) - [**ULTIMATE RAG - vectorization search system with OpenAI** 36 steps · calls a model · Qdrant](https://millionrounds.com/workflow/ultimate-rag-vectorization-search-system-with-openai) - [**Automate code reviews for GitLab MRs with Gemini and Jira** 35 steps · calls a model · Jira](https://millionrounds.com/workflow/automate-code-reviews-for-gitlab-mrs-with-gemini-and-jira) - [**Complete AI graphic design suite with OpenAI and Replicate** 35 steps · calls a model · Google Drive](https://millionrounds.com/workflow/complete-ai-graphic-design-suite-with-openai-and-replicate) - [**Filter cybersecurity news for your tech stack with OpenAI** 35 steps · calls a model · Gmail, Pinecone](https://millionrounds.com/workflow/filter-cybersecurity-news-for-your-tech-stack-with-openai) - [**Generate AI ads from website and images with Claude** 35 steps · calls a model · Google Drive](https://millionrounds.com/workflow/generate-ai-ads-from-website-and-images-with-claude)