Build an AI customer support bot that answers from your own documents

Blueprint

AnythingLLM holds your documents and answers questions from them using Ollama. Chatwoot runs the website widget and the shared inbox; its webhooks send each new customer message to Activepieces, which asks AnythingLLM and posts the reply back or assigns the conversation to a person.

1. You →Your manuals, policies and FAQs AnythingLLM
2. Chatwoot →A new customer message (webhook) Activepieces
3. Activepieces →The question AnythingLLM
4. AnythingLLM →The question with matching passages Ollama
5. Ollama →A draft answer AnythingLLM
6. AnythingLLM →The answer and its sources Activepieces
7. Activepieces →The reply, or a hand-off to a person Chatwoot

The repos

1. 01 · Answer from your docs AnythingLLM

   All-in-one desktop or Docker app to chat with your documents using local or cloud LLMs, with agents and a built-in vector database.

   Setup

   Easy; desktop installer, or Docker for multi-user source

   Hardware

   Recommended 16GB RAM, 8-core CPU; GPU recommended on Windows; storage varies by model source

   Paid extras

   None required; local LLM, embedder and vector DB by default; cloud optional

   ★ 67k MIT Confirmed: 8/8 facts Official docsGitHubReplaces ChatGPT Plus
2. 02 · Run the model Ollama

   Local model runner that downloads and serves open LLMs (Gemma, Qwen, DeepSeek, gpt-oss and more) with a CLI and local API.

   Setup

   Easy; one-line install script or installer, then ollama run source

   Hardware

   Apple M-series or x86 (CPU only) on Mac; 4GB for Windows binary; RAM not stated source

   Paid extras

   None for local use; Ollama Cloud plans optional (Pro $20/month)

   ★ 184k MIT Confirmed: 8/8 facts Official docsGitHubReplaces ChatGPT Plus
3. 03 · Inbox and chat widget Chatwoot

   Self-hosted customer support inbox with website live chat, email and social channels, a help center and an optional AI agent (Captain).

   Setup

   Medium; install script on an Ubuntu server or Docker Compose, then set environment variables (mail, storage, domain) source

   Hardware

   Minimum 2 CPU cores, 4 GB RAM and 20 GB SSD; 4+ cores and 8 GB+ RAM recommended for production source

   Paid extras

   The core inbox is free to self-host; the Captain AI agent needs a paid Premium or Enterprise self-hosted licence and your own OpenAI key (an OpenAI-compatible endpoint for a self-hosted model is optional)

   ★ — MIT Confirmed: 8/8 facts Official docsGitHubReplaces Intercom
4. 04 · Connect the steps Activepieces

   Self-hostable no-code automation builder with 280+ TypeScript integrations ("pieces") that are also exposed as MCP servers.

   Setup

   Medium, install script or a single docker run with embedded database source

   Hardware

   Production sizing: app 1 vCPU / 1 GB per ten workers; each worker 0.5 vCPU / 1 GB; Postgres 2 vCPU / 4 GB; Redis 1 vCPU / 1 GB source

   Paid extras

   None required; enterprise licence and Activepieces Cloud are optional

   ★ 25k MIT Confirmed: 8/8 facts Official docsGitHubReplaces Zapier, Make

Step by step

Install commands change, so each step links to the repo's own docs for the exact commands.

1. 1

   Load your documents into AnythingLLM

   Install AnythingLLM, create a workspace for support and upload your help articles, policies and product manuals. Ask it twenty real customer questions and fix the documents where its answers are wrong or vague.

   Uses AnythingLLM · its docs

2. 2

   Point it at a local model

   Set Ollama as AnythingLLM's model provider. In the workspace prompt, tell it to answer only from the documents, to keep answers short, and to say "I'll pass this to the team" when the documents don't cover the question.

   Uses Ollama · its docs

3. 3

   Set up Chatwoot

   Install Chatwoot, add the website widget to your site and connect your support email. Create a team and an "AI" label so you can see which conversations the bot handled.

   Uses Chatwoot · its docs

4. 4

   Connect them with Activepieces

   Add a webhook in Chatwoot that fires on new messages and points at an Activepieces flow. The flow sends the question to AnythingLLM's API, posts the answer back through Chatwoot's API, and assigns the conversation to a person when the answer says it can't help.

   Uses Activepieces · its docs

5. 5

   Run it on last month's tickets first

   Replay real questions and compare its answers with what your team sent. Only switch it on for customers once it is right most of the time and always hands off the rest.