Live LabsComing soon10 min

Build a Docs Chatbot with Qdrant

Split your docs, store them in Qdrant and answer questions with the right passages in the prompt.

Out on Sunday 15 November10 minutes, one build start to finish

Get it in your inbox the day it is out

One email when the recording is live, then the newsletter. Unsubscribe in one click.

We email you each new issue. You can leave at any time. Privacy

Why this matters

A chatbot that answers from your own documentation is often the first useful AI feature a team ships. The quality depends on finding the right passages and citing them, so readers can check every answer.

What you build

A chatbot that answers from your own documents and cites the page it used.

  1. Split your docs into passages and embed them.
  2. Store them in Qdrant with the page each one came from.
  3. Search for the passages closest to a question.
  4. Answer with those passages in the prompt, and cite the page.

The ideas behind it

  • Chunking

    Splitting docs into passages small enough to retrieve and large enough to make sense.

  • Embeddings and vector search

    Each passage is turned into numbers so the closest ones to a question can be found.

  • Grounded answers with citations

    The model answers from the retrieved passages and names the page each came from.

Before you start

You need
Python, Docker to run Qdrant, and an LLM API key.
Length
About 10 minutes, one build start to finish.

Questions

Why Qdrant?

It is open source, runs in one Docker container and is fast to start. Other vector databases work the same way.

How do I stop made-up answers?

Answer only from retrieved passages, cite them and say so when nothing relevant is found.

How do I keep it up to date?

Re-index pages when they change, keyed by the page they came from.

Is the recorded lab free?

Yes. Watch it any time, follow the steps and keep the code you build.

How is it different from a Live Lab?

A recorded lab is one short build you follow on your own. A Live Lab builds a bigger part of the system in an hour, with time for your questions.

Then take it further

This build is one piece. The Live Lab Build an AI Second Brain with Claude Code goes from here to a working part of a real system.

Capture into one brain
Claude Code files, tags and links what you add as you work.
Answer with sources
Every answer cites the note or issue it came from.
Share the memory
Serve the brain over MCP so any agent can read from it.

The parts of a production agent system that lab builds, lit on the map:

Week 1Architect
  • Roles and modelsOne job per agent, a model chosen for that job, and a token budget.
  • OrchestrationA queue agents pick work from, with hand-offs a person can follow.
  • Context and memoryRetrieval with sources, memory across sessions, prompts laid out for the cache.
  • Tool callingTyped tools that act in GitHub, Linear and Google.
Week 2Build
  • MCP serversEvery tool behind an MCP gateway, scoped to the role that needs it.
  • Durable executionRuns that resume after a crash and never repeat a write.
  • Human in the loopA person approves anything that cannot be undone.
Week 3Secure and deploy
  • Identity and permissionsEach agent signs in as itself and acts on behalf of a user.
  • LLM gatewayRouting, caching and a budget on every model call.
  • Traces, evals and costEvery run traced, scored and charged to the agent that made it.
  • Multi-tenancyEach team or customer kept apart, in data and in the bill.
Week 4Govern and extend
  • Policy as codeRules checked on every action, not written in a document.
  • Signed skillsNew roles built from reviewed, signed skills.

More recorded labs