Quickstart: your first cited answer

Getting a first cited answer takes four steps: create a collection, add a source and sync it, create an assistant over that collection, then ask it a question. All four are below, taking an empty organisation to a grounded, cited answer. It uses the HTTP API throughout, so each step can be copied as-is. The console equivalents are noted where they exist.

Before you begin

You need:

A MITHUNAI organisation. Your MITHUNAI administrator provisions organisations; there is no self-service sign-up.
An API key with the Editor role or higher. An Owner or Administrator creates it in the console under Operations → API keys. See API keys.
A documentation site, sitemap, GitHub repository or set of files to answer from.

Set two environment variables. Every example below uses them.

export MITHUNAI_URL="https://app.mithunai.com"  # your MITHUNAI host
export MITHUNAI_API_KEY="arukz_sk_..."          # the key you created

An API key is a secret. Keep it on servers and in secret managers. Never put it in a web page, a mobile app or a repository.

Confirm a model is available

curl "$MITHUNAI_URL/arukz/api/v1/models" \
  --header "Authorization: Bearer $MITHUNAI_API_KEY"

Pick a model whose capabilities include chat and save its id, such as openai/gpt-4o, as MODEL_ID. If the list is empty, contact your MITHUNAI administrator; no model provider is configured.

Create a collection

A collection is the corpus an assistant answers from. Its embedding model is fixed when you create it.

curl --request POST "$MITHUNAI_URL/arukz/api/v1/knowledge/collections" \
  --header "Authorization: Bearer $MITHUNAI_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{"name": "Product documentation"}'

Save the id from the response as COLLECTION_ID.

In the console, the Knowledge page creates a collection for you the first time you connect a source.

Connect a knowledge source

Register your documentation site. A sitemap is usually faster and more complete than a crawl; see Knowledge sources for every source type.

curl --request POST "$MITHUNAI_URL/arukz/api/v1/knowledge/sources" \
  --header "Authorization: Bearer $MITHUNAI_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "collection_id": "'"$COLLECTION_ID"'",
    "source_type": "sitemap",
    "name": "Docs site",
    "configuration": { "seed_url": "https://docs.example.com/sitemap.xml" }
  }'

Save the source id as SOURCE_ID. In the console: Knowledge → Connect a knowledge source.

Ingest it

Registering a source does not read it. Start an ingestion job, then poll it until it finishes.

curl --request POST "$MITHUNAI_URL/arukz/api/v1/knowledge/sources/$SOURCE_ID/sync" \
  --header "Authorization: Bearer $MITHUNAI_API_KEY"

curl "$MITHUNAI_URL/arukz/api/v1/knowledge/sources/$SOURCE_ID/job" \
  --header "Authorization: Bearer $MITHUNAI_API_KEY"

Ingestion runs in the background and a large site takes minutes. Wait for the job to complete before asking questions. See Ingestion.

Create an assistant over the collection

curl --request POST "$MITHUNAI_URL/arukz/api/v1/assistants" \
  --header "Authorization: Bearer $MITHUNAI_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "name": "Docs assistant",
    "model": "'"$MODEL_ID"'",
    "knowledge_base_ids": ["'"$COLLECTION_ID"'"]
  }'

Save the assistant id as ASSISTANT_ID. Without model, an assistant uses anthropic/claude-sonnet-5, which answers only if your deployment offers it.In the console: Assistants → New assistant, then tick the collection under Knowledge. See Create and configure assistants.

An assistant answers only from the knowledge attached to it, and refuses questions until at least one collection is attached.

Ask a question

Start a conversation, then ask.

CONVERSATION_ID=$(curl --silent --request POST "$MITHUNAI_URL/arukz/api/v1/conversations" \
  --header "Authorization: Bearer $MITHUNAI_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{"assistant_id": "'"$ASSISTANT_ID"'"}' | jq -r .id)

curl --request POST "$MITHUNAI_URL/arukz/api/v1/conversations/$CONVERSATION_ID/messages" \
  --header "Authorization: Bearer $MITHUNAI_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{"text": "How do I get started?"}'

The response contains the answer and its citations. If the answer has "abstained": true, your content did not support an answer. That is a correct result, not an error. See How answers work.You can also ask in the console on the Ask page.

Next steps

Embed the widget

Put the assistant on your website.

Stream answers

Show the answer as it is written.

Test before launch

Check grounded answers and abstentions against your own questions.

Connect MCP clients

Query your knowledge from Claude and IDE assistants.

Compare the channels

Which of the widget, the API and MCP suits who is asking.

When a step goes wrong

Empty model lists, failed ingestion jobs, and what a 401 or 429 means.

Get started

Knowledge

Assistants & Agents

Channels & Integration

Architecture & Solutions

Administration

Trust and support

Quickstart: your first cited answer

Before you begin

Next steps

Embed the widget

Stream answers

Test before launch

Connect MCP clients

Compare the channels

When a step goes wrong

​Before you begin

​Next steps

Embed the widget

Stream answers

Test before launch

Connect MCP clients

Compare the channels

When a step goes wrong

Before you begin

Next steps