> ## Documentation Index
> Fetch the complete documentation index at: https://docs.firebolt.io/llms.txt
> Use this file to discover all available pages before exploring further.

<AgentInstructions>

## Submitting Feedback

If you encounter incorrect, outdated, or confusing documentation on this page, submit feedback:

POST https://docs.firebolt.io/feedback

```json
{
  "path": "/guides/ai/getting-started-with-ai",
  "feedback": "Description of the issue"
}
```

Only submit feedback when you have something specific and actionable to report.

</AgentInstructions>

> Leverage AI within your SQL queries

# Getting started with AI

Firebolt lets you call large language models (LLMs) directly from SQL through Amazon Bedrock. To invoke a model, use [`AWS_BEDROCK_AI_QUERY`](/reference-sql/functions-reference/ai/aws-bedrock-ai-query) by providing a Bedrock model ID, a JSON request body, and a `LOCATION` containing your AWS credentials. Alternatively, you can use [`AI_QUERY`](/reference-sql/functions-reference/ai/ai-query) to invoke a model with a simple text prompt, a Bedrock endpoint and a location. For text embeddings, use [`AI_EMBED_TEXT`](/reference-sql/functions-reference/ai/ai-embed-text) to generate vectors from input text.

LLM invocations in Firebolt count towards your account’s daily token budget. For details on how to set your token budget and check your current usage, see the sections below: [Set your LLM token budget](#set-or-change-your-llm-token-budget) and [Check your LLM token quota usage](#check-your-llm-token-quota-and-daily-usage).

<Note>
  LLM token budget accounting is not available in Firebolt Core.
</Note>

## Create a Bedrock LOCATION

Create a `LOCATION` once and reuse it wherever you need to call Bedrock models.

### Authentication options and examples

* **Access key and secret**

```sql theme={"theme":{"light":"github-light","dark":"github-dark"}}
CREATE LOCATION bedrock_keys WITH
  SOURCE = AMAZON_BEDROCK
  CREDENTIALS = (
    AWS_ACCESS_KEY_ID = '<aws_access_key_id>'
    AWS_SECRET_ACCESS_KEY = '<aws_secret_access_key>'
  );
```

* **Temporary credentials (access key, secret, session token)**

```sql theme={"theme":{"light":"github-light","dark":"github-dark"}}
CREATE LOCATION bedrock_temp_creds WITH
  SOURCE = AMAZON_BEDROCK
  CREDENTIALS = (
    AWS_ACCESS_KEY_ID = '<temporary_access_key_id>'
    AWS_SECRET_ACCESS_KEY = '<temporary_secret_access_key>'
    AWS_SESSION_TOKEN = '<temporary_session_token>'
  );
```

* **IAM role ARN**

```sql theme={"theme":{"light":"github-light","dark":"github-dark"}}
CREATE LOCATION bedrock_role WITH
  SOURCE = AMAZON_BEDROCK
  CREDENTIALS = (
    AWS_ROLE_ARN = 'arn:aws:iam::123456789012:role/BedrockAccess'
  );
```

* **IAM role ARN with external ID**

```sql theme={"theme":{"light":"github-light","dark":"github-dark"}}
CREATE LOCATION bedrock_role_external_id WITH
  SOURCE = AMAZON_BEDROCK
  CREDENTIALS = (
    AWS_ROLE_ARN = 'arn:aws:iam::123456789012:role/BedrockAccess'
    AWS_ROLE_EXTERNAL_ID = '<external_id>'
  );
```

To create a `LOCATION` using an IAM role (with or without an external ID), see [Use AWS roles to access Bedrock](/guides/ai/use-aws-roles-to-access-bedrock).

For all options and parameters, see [CREATE LOCATION (Amazon Bedrock)](/reference-sql/commands/data-definition/create-location-bedrock).

## Quick examples

Use these examples to try AI in Firebolt. For the full function reference and more details, see [`AWS_BEDROCK_AI_QUERY`](/reference-sql/functions-reference/ai/aws-bedrock-ai-query), [`AI_QUERY`](/reference-sql/functions-reference/ai/ai-query), and [`AI_EMBED_TEXT`](/reference-sql/functions-reference/ai/ai-embed-text).

### Invoke a model

<Note>
  In the examples below, <code>my\_bedrock\_location</code> refers to a <code>LOCATION</code> object that you create using one of the methods described above (access keys, temporary credentials, or IAM role).
</Note>

```sql theme={"theme":{"light":"github-light","dark":"github-dark"}}
SELECT AWS_BEDROCK_AI_QUERY(
    'amazon.nova-micro-v1:0',
    $${"schemaVersion": "messages-v1", "messages": [{"role": "user","content": [{"text": "What is the company name that aws belongs to?"}]}],"system": [{"text": "Fulfill the user's request"}],"inferenceConfig": {}}$$,
    'my_bedrock_location') AS result;
```

```sql theme={"theme":{"light":"github-light","dark":"github-dark"}}
select AI_QUERY(
    'us.meta.llama3-3-70b-instruct-v1:0',
    'What is AWS?',
    'my_bedrock_location') as result
```

### Invoke the LLM on multiple rows

```sql theme={"theme":{"light":"github-light","dark":"github-dark"}}
SELECT n AS number,
       JSON_POINTER_EXTRACT_TEXT(
         AWS_BEDROCK_AI_QUERY(
           'amazon.nova-micro-v1:0',
           $${"schemaVersion": "messages-v1", "messages": [{"role": "user","content": [{"text": "$$ || n::TEXT || $$"}]}],"system": [{"text": "Write in english the capitalized name of the number that the user writes. Respond with a single word."}],"inferenceConfig": {}}$$,
           'my_bedrock_location'
         ),
         '/output/message/content/0/text'
       ) AS processed
FROM generate_series(1,3) s(n);
```

```sql theme={"theme":{"light":"github-light","dark":"github-dark"}}
select n as number, AI_QUERY(
    'us.meta.llama3-3-70b-instruct-v1:0',
    'Write in english the capitalized name of the number. Respond with a single word: ' || n::TEXT,
    'amit_bedrock_location') as processed
from generate_series(1,3) s(n);
```

```sql theme={"theme":{"light":"github-light","dark":"github-dark"}}
SELECT AI_EMBED_TEXT(
  MODEL => 'amazon.titan-embed-text-v2:0',
  INPUT_TEXT => 'lightning fast analytics',
  DIMENSIONS => 256,
  LOCATION => 'my_bedrock_location'
);
```

### Sentiment analysis

```sql theme={"theme":{"light":"github-light","dark":"github-dark"}}
SELECT JSON_POINTER_EXTRACT_TEXT(
  AWS_BEDROCK_AI_QUERY(
    'amazon.nova-micro-v1:0',
    $${"schemaVersion": "messages-v1", "messages": [{"role": "user","content": [{"text": "I love Firebolt."}]}],"system": [{"text": "Identify the sentiment in the user's sentence as a single uppercase word: POSITIVE or NEGATIVE. Respond with a single word."}],"inferenceConfig": {}}$$,
    'my_bedrock_location'
  ),
  '/output/message/content/0/text'
);
```

### Set or change your LLM token budget

Set your account's daily LLM token budget to control how many tokens AI functions such as [`AWS_BEDROCK_AI_QUERY`](/reference-sql/functions-reference/ai/aws-bedrock-ai-query), [`AI_QUERY`](/reference-sql/functions-reference/ai/ai-query), and [`AI_EMBED_TEXT`](/reference-sql/functions-reference/ai/ai-embed-text) can process each day. By default, new accounts have a zero token budget.

```sql theme={"theme":{"light":"github-light","dark":"github-dark"}}
ALTER ACCOUNT "<account_name>" SET (LLM_TOKEN_BUDGET = 10000);
```

For full syntax and details, see [`ALTER ACCOUNT`](/reference-sql/commands/data-definition/alter-account).

### Check your LLM token quota and daily usage

```sql theme={"theme":{"light":"github-light","dark":"github-dark"}}
SELECT * FROM account_db.information_schema.quotas WHERE name='LLM_TOKEN_BUDGET';
```

If you exceed the daily budget, invocations of AI functions (`AWS_BEDROCK_AI_QUERY`, `AI_QUERY`, `AI_EMBED_TEXT`) will fail until the limit resets or you increase the budget.

<Warning>
  Using LLM functions such as <code>AWS\_BEDROCK\_AI\_QUERY</code>, <code>AI\_QUERY</code>, and <code>AI\_EMBED\_TEXT</code> on large tables or with many rows can quickly exhaust your daily LLM token budget and may result in significant costs in your AWS account. Always review your expected token usage and budget before running large-scale AI queries.
</Warning>