Snowflake Gen AI Functions · Topic 22 of 26

Chat Conversations: Multi-turn Architecture, Message History and Snowflake Intelligence

Build multi-turn chat on stateless Cortex calls by resending the messages array, and know when to use Snowflake Intelligence to chat with data.

  • 5 min
In a nutshell
  • Cortex calls are stateless. Resend the whole messages array each turn.
  • Roles: system (optional, first, once), user, assistant. Analyst uses user and analyst.
  • Cost and tokens grow with every turn.

What it is

A chat feels continuous to the user, but Cortex model calls are stateless. The model does not remember the previous call. To make a multi-turn conversation, your application stores the history and sends it again with every new question.

Snowflake Intelligence (documented as Snowflake CoWork in current docs) is the ready made alternative. It is a Snowflake provided chat experience where business users ask questions of their data in natural language, without building an app.

User messageappendMessages arrayhistorysend allCortex callstatelessreplyAssistant messageappendMessages arrayhistory

How it works

The messages array

Multi-turn calls use an array of objects, each with a role and a content, in chronological order.

RoleMeaning
systemOptional instructions that set behavior; first in the array and only once
userA question from the person
assistantA previous reply from the model

After the optional system message, user and assistant turns alternate. The latest user question goes last.

SELECT SNOWFLAKE.CORTEX.COMPLETE(
  'claude-sonnet-4-5',
  [
    {'role': 'system', 'content': 'You are a concise support agent.'},
    {'role': 'user', 'content': 'What is a virtual warehouse?'},
    {'role': 'assistant', 'content': 'Compute that runs queries.'},
    {'role': 'user', 'content': 'How do I make it smaller?'}
  ],
  {'temperature': 0, 'max_tokens': 300}
);

The array form is documented for SNOWFLAKE.CORTEX.COMPLETE, and an array is required whenever the options object is present. Its page states the rule directly: the function does not retain any state from one call to the next, so you include every prior user and assistant message each time. It also recommends AI_COMPLETE for new work and states that the legacy function will be deprecated by the end of 2026. Cortex Analyst follows the same pattern, using a messages array with roles user and analyst.

Multi-turn architecture

A typical app has four parts.

  1. UI collects the question, for example a Streamlit chat box.
  2. History store keeps the messages, in session state for a simple app or in a table for persistence across sessions.
  3. Orchestration builds the array, adds retrieved context when needed, and calls Cortex.
  4. Cortex services answer: AI_COMPLETE or the Complete REST API for text, Cortex Search for retrieval, Cortex Analyst for SQL.

For Streamlit the history usually sits in st.session_state. Each turn appends the user message, calls the model with the whole list, then appends the reply.

Updating the parameters on each turn

What changes between turns:

  • The messages array grows by two entries per turn (user, then assistant).
  • Model options such as temperature, top_p, max_tokens and guardrails can be set per call. Without the options argument the function returns a plain string; with it, a JSON string with choices, created, model and usage. In the REST API the chat body also carries the model and the messages.
  • Retrieved context is refreshed per question, not stored forever.

Costs and limits grow with the history, because the whole conversation is processed again on each call. Token use and cost rise every turn, and a long conversation can reach the model's context window.

Ways to keep it under control:

  • Window: send only the last N turns.
  • Summarize: replace old turns with a short summary produced by AI_COMPLETE.
  • Reset: start a new conversation when the topic changes. Cortex Analyst docs also note that long or shifting conversations may need a reset.
  • Check size: use AI_COUNT_TOKENS to estimate before sending.
Exam tip

"The assistant forgot what the user said earlier" means the app did not resend the history. The model is not at fault.

Snowflake Intelligence

Snowflake Intelligence lets people chat with their data using natural language. It draws on Cortex Analyst for structured data through semantic views and Cortex Search for unstructured documents, and it can use custom tools. It keeps conversational context, shows results in text, tables and charts, and inherits Snowflake governance, including row access policies and column level security.

ChooseWhen
Snowflake IntelligenceBusiness users need chat over governed data quickly, with no app code
Custom Streamlit appYou need your own UI, workflow or extra logic
Cortex Analyst REST API directlyYou embed text-to-SQL in another application

The docs also point to Cortex Agents as the way to orchestrate Analyst and Search together, and Snowflake recommends moving from the standalone Analyst API to Cortex Agents.

Common mistakes

Sending only the latest question. The model has no memory, so context is lost.

Putting the system message at the end or repeating it. It goes first, once.

Letting history grow forever. Cost and context limits grow with it.

Building a custom chat app when Snowflake Intelligence already meets the need.

Watch out

Chat history that contains sensitive data is resent to the model on every call. Store and trim it with the same care as the source data.

What to remember for the exam

  • Cortex calls are stateless. Resend the whole messages array each turn.
  • Roles: system (optional, first, once), user, assistant. Analyst uses user and analyst.
  • Cost and tokens grow with every turn.
  • Snowflake Intelligence: ready made chat over Analyst and Search, with governance inherited.
  • Use a window or summary to keep history short.

Check yourself

  • Why does a chat app resend earlier messages on every call?

    Cortex calls are stateless, so the model only knows what is in the current request.

  • Where does the system message go in the array?

    First, and only once.

  • What does Snowflake Intelligence use to answer questions about tables and documents?

    Cortex Analyst for structured data and Cortex Search for unstructured text.

Topic 22 of 26 in Snowflake Gen AI Functions

Test yourself on Snowflake Gen AI Functions

The full Snowflake GES-C02 question bank has 585 questions, with timed practice exams and an explanation for every answer.

This study guide is independent and is not affiliated with, endorsed by, or sponsored by Snowflake. Vendor names, certification names and exam codes are trademarks of their respective owners and are used for identification only.