# Bitrix24 AI-Powered RAG Chatbot for Open Line Channels: n8n workflow > Started by another system calling it, and works across Qdrant. It puts Gemini behind a retrieval step, so answers are drawn from documents you supply rather... Source: https://millionrounds.com/workflow/bitrix24-ai-powered-rag-chatbot-for-open-line-channels (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) # Bitrix24 AI-Powered RAG Chatbot for Open Line Channels Started by another system calling it, and works across Qdrant. It puts Gemini behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 33 steps, 2 branches: large, and worth reading before you trust it with anything live. Large Calls a model: Gemini Retrieval [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fbitrix24-ai-powered-rag-chatbot-for-open-line-channels) **33 steps** Large: read it before trusting it with anything live **2** Branches: places the flow splits **0** Loops or waits **1** Service it connects to ## The flow Starts it 4 Model 9 Logic 12 Service 8 The steps in the order they run, from what starts it. - 1 **Bitrix24 Handler** Webhook *Starts it* - 2 **Recursive Character Text Splitter** Text Splitter Recursive Character Text Splitter *Model* - 3 **Execute Workflow Trigger** Execute Workflow trigger *Starts it* - 4 **Embeddings Ollama** Embeddings Ollama *Model* - 5 **Embeddings Ollama1** Embeddings Ollama *Model* - 6 **Google Gemini Chat Model** Lm Chat Google Gemini *Model* - 7 **Credentials** Set *Logic* - 8 **Default Data Loader** Document Default Data Loader *Model* - 9 **Get a list of available storages** Http Request *Service* - 10 **Qdrant Vector Store** Vector Store Qdrant *Model* - 11 **Qdrant Vector Store1** Vector Store Qdrant *Model* - 12 **Question and Answer Chain** Chain Retrieval Qa *Model* - 13 **Validate Token** If *Logic* - 14 **Merge parameters for Subworkflow** Merge *Logic* - 15 **Get a list of List of Files and Folders** Http Request *Service* - 16 **Vector Store Retriever** Retriever Vector Store *Model* - 17 **Prepare output parameters** Set *Logic* - 18 **Route Event** Switch *Logic* - 19 **Error Response** Respond To Webhook *Starts it* - 20 **Execute subworkflow** Execute Workflow *Logic* - 21 **Get a list of Folders files** Http Request *Service* - 22 **Send Message** Http Request *Service* - 23 **Process Message** Function *Logic* - 24 **Process Join** Function *Logic* - 25 **Process Install** Function *Logic* - 26 **Process Delete** No Op *Logic* - 27 **Success Response** Respond To Webhook *Starts it* - 28 **Split Out folder files and folders** Split Out *Logic* - 29 **Send Join Message** Http Request *Service* - 30 **Register Bot** Http Request *Service* - 31 **Filter for files** Filter *Logic* - 32 **Download file** Http Request *Service* - 33 **Move files to Vector stored folder** Http Request *Service* ## How it's built - **Starts on:** Another system calling it - **Steps:** 33, with 2 branches - **Size:** Large: read it before trusting it with anything live - **Connects to:** Qdrant - **Model:** Gemini - **Retrieval:** Answers are drawn from documents you supply, not from the model alone ## Questions What does it need to run? An n8n account, plus your own Qdrant account, and a key for Gemini. 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. 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 33 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 33 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%2Fbitrix24-ai-powered-rag-chatbot-for-open-line-channels) - **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. ## Connects to Each opens the other workflows that use it. [Qdrant](https://millionrounds.com/workflows?service=Qdrant#library) ## Workflows like it Also ai assistants, with the same services where possible, closest in size first. - [**Adaptive RAG strategy with Gemini and Qdrant** 30 steps · calls a model · Qdrant](https://millionrounds.com/workflow/adaptive-rag-strategy-with-gemini-and-qdrant) - [**Adaptive RAG with Gemini and Qdrant:** 30 steps · calls a model · Qdrant](https://millionrounds.com/workflow/adaptive-rag-with-gemini-and-qdrant) - [**Create adaptive RAG chat agent with Gemini and Qdrant** 30 steps · calls a model · Qdrant](https://millionrounds.com/workflow/create-adaptive-rag-chat-agent-with-gemini-and-qdrant) - [**ULTIMATE RAG - vectorization search system with OpenAI** 36 steps · calls a model · Qdrant](https://millionrounds.com/workflow/ultimate-rag-vectorization-search-system-with-openai) - [**Vision RAG and image embeddings with Cohere Command-A** 27 steps · calls a model · Qdrant](https://millionrounds.com/workflow/vision-rag-and-image-embeddings-with-cohere-command-a) - [**Voice AI chatbot with OpenAI and RAG** 27 steps · calls a model · Google Drive, Qdrant](https://millionrounds.com/workflow/voice-ai-chatbot-with-openai-and-rag)