Skip to main content

Deploy batch inference pipelines

Preview

This feature is in Public Preview.

This page shows how you can integrate AI Functions into other Databricks data and AI products to build complete batch inference pipelines. These pipelines can perform end-to-end workflows that include ingestion, preprocessing, inference, and post-processing. Pipelines can be authored in SQL or Python and deployed as:

  • Lakeflow Declarative Pipelines
  • Scheduled workflows using Databricks workflows
  • Streaming inference workflows using Structured Streaming

Requirements​

  • A workspace in a Foundation Model APIs supported region.
  • Databricks Runtime 15.4 LTS or above is required for batch inference workloads using AI Functions.
  • Query permission on the Delta table in Unity Catalog that contains the data you want to use.
  • Set the pipelines.channel in the table properties as 'preview' to use ai_query(). See Requirements for an example query.

Perform incremental batch inference on Lakeflow Declarative Pipelines​

The following example performs incremental batch inference using Lakeflow Declarative Pipelines for when data is continuously updated.

Step 1: Ingest raw news data from a volume​

SQL

CREATE OR REFRESH STREAMING TABLE news_raw
COMMENT "Raw news articles ingested from volume."
AS SELECT *
FROM STREAM(read_files(
  '/Volumes/databricks_news_summarization_benchmarking_data/v01/csv',
  format => 'csv',
  header => true,
  mode => 'PERMISSIVE',
  multiLine => 'true'
));

Step 2: Apply LLM inference to extract title and category​

SQL

CREATE OR REFRESH MATERIALIZED VIEW news_categorized
COMMENT "Extract category and title from news articles using LLM inference."
AS
SELECT
  inputs,
  ai_query(
    "databricks-meta-llama-3-3-70b-instruct",
    "Extract the category of the following news article: " || inputs,
    responseFormat => '{
      "type": "json_schema",
      "json_schema": {
        "name": "news_extraction",
        "schema": {
          "type": "object",
          "properties": {
            "title": { "type": "string" },
            "category": {
              "type": "string",
              "enum": ["Politics", "Sports", "Technology", "Health", "Entertainment", "Business"]
            }
          }
        },
        "strict": true
      }
    }'
  ) AS meta_data
FROM news_raw
LIMIT 2;

Step 3: Validate the LLM inference output before summarization​

SQL
CREATE OR REFRESH MATERIALIZED VIEW news_validated (
  CONSTRAINT valid_title EXPECT (size(split(get_json_object(meta_data, '$.title'), ' ')) >= 3),
  CONSTRAINT valid_category EXPECT (get_json_object(meta_data, '$.category') IN ('Politics', 'Sports', 'Technology', 'Health', 'Entertainment', 'Business'))
)
COMMENT "Validated news articles ensuring the title has at least 3 words and the category is valid."
AS
SELECT *
FROM news_categorized;

Step 4: Summarize news articles from the validated data​

SQL
CREATE OR REFRESH MATERIALIZED VIEW news_summarized
COMMENT "Summarized political news articles after validation."
AS
SELECT
  get_json_object(meta_data, '$.category') as category,
  get_json_object(meta_data, '$.title') as title,
  ai_query(
    "databricks-meta-llama-3-3-70b-instruct",
    "Summarize the following political news article in 2-3 sentences: " || inputs
  ) AS summary
FROM news_validated;

Automate batch inference jobs using Databricks workflows​

Schedule batch inference jobs and automate AI pipelines.

SQL
SELECT
   *,
   ai_query('databricks-meta-llama-3-3-70b-instruct', request => concat("You are an opinion mining service. Given a piece of text, output an array of json results that extracts key user opinions, a classification, and a Positive, Negative, Neutral, or Mixed sentiment about that subject.
AVAILABLE CLASSIFICATIONS
Quality, Service, Design, Safety, Efficiency, Usability, Price
Examples below:
DOCUMENT
I got soup. It really did take only 20 minutes to make some pretty good soup. The noises it makes when it's blending are somewhat terrifying, but it gives a little beep to warn you before it does that. It made three or four large servings of soup. It's a single layer of steel, so the outside gets pretty hot. It can be hard to unplug the lid without knocking the blender against the side, which is not a nice sound. The soup was good and the recipes it comes with look delicious, but I'm not sure I'll use it often. 20 minutes of scary noises from the kitchen when I already need comfort food is not ideal for me. But if you aren't sensitive to loud sounds it does exactly what it says it does..
RESULT
[
 {'Classification': 'Efficiency', 'Comment': 'only 20 minutes','Sentiment': 'Positive'},
 {'Classification': 'Quality','Comment': 'pretty good soup','Sentiment': 'Positive'},
 {'Classification': 'Usability', 'Comment': 'noises it makes when it's blending are somewhat terrifying', 'Sentiment': 'Negative'},
 {'Classification': 'Safety','Comment': 'outside gets pretty hot','Sentiment': 'Negative'},
 {'Classification': 'Design','Comment': 'Hard to unplug the lid without knocking the blender against the side, which is not a nice sound', 'Sentiment': 'Negative'}
]
DOCUMENT
", REVIEW_TEXT, '\n\nRESULT\n')) as result
FROM catalog.schema.product_reviews
LIMIT 10

AI Functions using Structured Streaming​

Apply AI inference in near real-time or micro-batch scenarios using ai_query and Structured Streaming.

Step 1. Read your static Delta table​

Read your static Delta table as if it were a stream.

Python

from pyspark.sql import SparkSession
import pyspark.sql.functions as F

spark = SparkSession.builder.getOrCreate()

# Spark processes all existing rows exactly once in the first micro-batch.
df = spark.table("enterprise.docs")  # Replace with your table name containing enterprise documents
df.repartition(50).write.format("delta").mode("overwrite").saveAsTable("enterprise.docs")
df_stream = spark.readStream.format("delta").option("maxBytesPerTrigger", "50K").table("enterprise.docs")

# Define the prompt outside the SQL expression.
prompt = (
    "You are provided with an enterprise document. Summarize the key points in a concise paragraph. "
    "Do not include extra commentary or suggestions. Document: "
)

Step 2. Apply ai_query​

Spark processes this only once for static data unless new rows arrive in the table.

Python

df_transformed = df_stream.select(
    "document_text",
    F.expr(f"""
      ai_query(
        'databricks-meta-llama-3-1-8b-instruct',
        CONCAT('{prompt}', document_text)
      )
    """).alias("summary")
)

Step 3: Write the summarized output​

Write the summarized output to another Delta table

Python

# Time-based triggers apply, but only the first trigger processes all existing static data.
query = df_transformed.writeStream \
    .format("delta") \
    .option("checkpointLocation", "/tmp/checkpoints/_docs_summary") \
    .outputMode("append") \
    .toTable("enterprise.docs_summary")

query.awaitTermination()
Last updated on