Enriching metadata for correct text-to-SQL technology for Amazon Athena

Extracting invaluable insights from huge datasets is crucial for companies striving to realize a aggressive edge. Enterprise information is introduced into information lakes and information warehouses to hold out analytical, reporting, and information science use circumstances utilizing AWS analytical providers like Amazon Athena, Amazon Redshift, Amazon EMR, and so forth. Amazon Athena supplies interactive analytics service for analyzing the information in Amazon Easy Storage Service (Amazon S3). Amazon Redshift is used to investigate structured and semi-structured information throughout information warehouses, operational databases, and information lakes. Amazon EMR supplies a giant information setting for information processing, interactive evaluation, and machine studying utilizing open supply frameworks similar to Apache Spark, Apache Hive, and Presto. These information processing and analytical providers assist Structured Question Language (SQL) to work together with the information.

Writing SQL queries requires not simply remembering the SQL syntax guidelines, but in addition information of the tables metadata, which is information about desk schemas, relationships among the many tables, and attainable column values. Massive language mannequin (LLM)-based generative AI is a brand new expertise development for comprehending a big corpora of knowledge and helping with complicated duties. Can it additionally assist write SQL queries? The reply is sure.

Generative AI fashions can translate pure language questions into legitimate SQL queries, a functionality referred to as text-to-SQL technology. Though LLMs can generate syntactically right SQL queries, they nonetheless want the desk metadata for writing correct SQL question. On this submit, we reveal the crucial position of metadata in text-to-SQL technology by way of an instance applied for Amazon Athena utilizing Amazon Bedrock. We focus on the challenges in sustaining the metadata in addition to methods to beat these challenges and enrich the metadata.

Answer overview

This submit demonstrates text-to-SQL technology for Athena utilizing an instance applied utilizing Amazon Bedrock. We use Anthropic’s Claude 2.1 basis mannequin (FM) in Amazon Bedrock because the LLM. Amazon Bedrock fashions are invoked utilizing Amazon SageMaker. Working examples are designed to reveal how varied particulars included within the metadata influences the SQL generated by the mannequin. These examples use artificial datasets created in AWS Glue and Amazon S3. After we evaluate the importance of those metadata particulars, we’ll delve into the challenges encountered in gathering the required degree of metadata. Subsequently, we’ll discover methods for overcoming these challenges.

The examples applied within the workflow are illustrated within the following diagram.

Determine 1. The answer structure and workflow.

The workflow follows the next sequence:

1. A consumer asks a text-based query which may be answered by querying related AWS Glue tables by way of Athena.
2. Desk metadata is fetched from AWS Glue.
3. The tables’ metadata and SQL producing directions are added to the immediate template. The Claude AI mannequin is invoked by passing the immediate and the mannequin parameters.
4. The Claude AI mannequin interprets the consumer intent (query) to SQL based mostly on the directions and tables’ metadata.
5. The generated Athena SQL question is run.
6. The generated Athena SQL question and the SQL question outcomes are returned to the consumer.

Conditions

These stipulations are given If you wish to do that instance your self. You may skip this stipulations part if you wish to perceive the instance with out implementing it. The instance facilities on invoking Amazon Bedrock fashions utilizing SageMaker, so we have to arrange a couple of assets in an AWS Account. The related CloudFormation template, Jupyter Notebooks, and particulars of launching the mandatory AWS providers are lined on this part. The CloudFormation template creates the SageMaker occasion with the mandatory S3 bucket and IAM position permissions to run AWS Glue instructions, Athena SQL, and invoke Amazon Bedrock AI fashions. The 2 Jupyter Notebooks (0_create_tables_with_metadata.ipynb and 1_text-to-sql-for-athena.ipynb) present working code snippets to create the mandatory tables and generate the SQL utilizing the Claude AI mannequin on Amazon Bedrock.

Granting Anthropic’s Claude permissions on Amazon Bedrock 

• Have an AWS account and sign up utilizing the AWS Administration Console.
• Change the AWS Area to US West (Oregon).
• Navigate to the AWS Service Catalog console and select Amazon Bedrock.
• On the Amazon Bedrock console, select Mannequin Entry within the navigation pane.
• Select Handle mannequin entry.
• Choose the Claude
• Select Request mannequin entry if you happen to’re requesting the mannequin entry for the primary time. In any other case select Save Modifications.

Deploying the CloudFormation stack

After launching the CloudFormation stack:

• On the Create stack web page, select Subsequent
• On the Specify stack particulars web page, select Subsequent
• On the Configure stack choices web page, select Subsequent
• On the Overview and create web page, choose I acknowledge that AWS CloudFormation may create IAM assets
• Select Submit

Downloading Jupyter Notebooks to  SageMaker 

• Within the AWS Administration Console, select the title of the presently displayed Area and alter it to US West (Oregon).
• Navigate to the AWS Service Catalog console and select Amazon SageMaker.
• On the Amazon SageMaker console, select Pocket book within the navigation pane.
• Select Pocket book situations.
• Choose the SageMakerNotebookInstance created by the texttosqlmetadata CloudFormation stack.
• Underneath Actions, select Open Jupyter
• Navigate to Jupyter console, choose New, after which select Console.
• Run the next Shell script instructions within the console to repeat the Jupyter Notebooks.

  cd /residence/ec2-user/SageMaker
  BASE_S3_PATH="s3://aws-blogs-artifacts-public/artifacts/BDB-4265"
  aws s3 cp "${BASE_S3_PATH}/0_create_tables_with_metadata.ipynb" ./
  aws s3 cp "${BASE_S3_PATH}/1_text_to_sql_for_athena.ipynb" ./
  

• Open every downloaded Pocket book and replace the values of the athena_results_bucket, aws_region, and athena_workgroup variables based mostly on the outputs from the texttosqlmetadata CloudFormation

Answer implementation

If you wish to do that instance your self, strive the CloudFormation template supplied within the earlier part. Within the subsequent sections, we are going to illustrate how every aspect of the metadata included within the immediate influences the SQL question generated by the mannequin.

1. The steps within the 0_create_tables_with_metadata.ipynb Jupyter Pocket book create Amazon S3 recordsdata with artificial information for worker and division datasets, creates employee_dtls and department_dtls Glue tables pointing to these S3 buckets, and extracts the next metadata for these two tables.

   CREATE EXTERNAL TABLE employee_dtls (
   	id int COMMENT 'Worker id',
   	title string COMMENT 'Worker title',
   	age int COMMENT 'Worker age',
   	dept_id int COMMENT 'Worker Departments ID',
   	emp_category string COMMENT 'Worker class. Incorporates TEMP For momentary, PERM for everlasting, CONTR for contractors ',
   	location_id int COMMENT 'Location identifier of the Worker',
   	joining_date date COMMENT 'Becoming a member of date of the Worker',
   	CONSTRAINT pk_1 PRIMARY KEY  (id) ,
   	CONSTRAINT FK_1 FOREIGN KEY (dept_id) REFERENCES department_dtls(id)
   ) 
   PARTITIONED BY (
   	region_id string COMMENT 'Area identifier. Incorporates AMER for Americas, EMEA for Europe, the Center East, and Africa, APAC for Asia Pacific international locations'
   );
   
   CREATE EXTERNAL TABLE department_dtls (
   	id int COMMENT 'Division id',
   	title string COMMENT 'Division title',
   	location_id int COMMENT 'Location identifier of the Division'
   )

2. The metadata extracted within the earlier step supplies column descriptions. For the region_id partition column and emp_category column, the outline supplies attainable values together with their that means. The metadata additionally has overseas key constraint particulars. AWS Glue doesn’t present a option to specify the first key and overseas key constraints, so use customized keys within the AWS Glue table-level parameters as an alternative choice to collect main key and overseas keys whereas creating the AWS Glue desk.

   # Outline the desk schema
   employee_table_input = {
       'Identify': employee_table_name,
       'PartitionKeys': [
           {'Name': 'region_id', 'Type': 'string', 'Comment': 'Region identifier. Contains AMER for Americas, EMEA for Europe, the Middle East, and Africa, APAC for Asia Pacific countries'}
       ],
       'StorageDescriptor': {
           'Columns': [
               {'Name': 'id', 'Type': 'int', 'Comment': 'Employee id'},
          …
           ],
           'Location': employee_s3_path,
        …
       'TableType': 'EXTERNAL_TABLE',
       'Parameters': {
           'classification': 'csv',
           'primary_key': 'CONSTRAINT pk_1 PRIMARY KEY  (id)',
           'foreign_key_1': 'CONSTRAINT FK_1 FOREIGN KEY (dept_id) REFERENCES department_dtls(id)'          
       }
   }
   
   # Create the desk
   response = glue_client.create_table(DatabaseName=database_name, TableInput=employee_table_input)
   

3. The steps within the 1_text-to-sql-for-athena.ipynb Jupyter pocket book create the next wrapper operate to work together with Claude FM on Amazon Bedrock to generate SQL based mostly on user-provided textual content wrapped up in a immediate. This operate onerous codes the mannequin’s parameters and mannequin ID for demonstrating the fundamental performance.

   def interactWithClaude(immediate):
   
       physique = json.dumps(
           {
               "immediate": immediate,
               "max_tokens_to_sample": 2048,
               "temperature": 1,
               "top_k": 250,
               "top_p": 0.999,
               "stop_sequences": [],
           }
       )
       modelId = "anthropic.claude-v2"  
       settle for = "utility/json"
       contentType = "utility/json"
       response = bedrock_client.invoke_model(
           physique=physique, modelId=modelId, settle for=settle for, contentType=contentType
       )
       response_body = json.masses(response.get("physique").learn())
       response_text_claude = response_body.get("completion")
       return response_text_claude

4. Outline the next set of directions for producing Athena SQL question. These SQL producing directions specify which compute engine the SQL question ought to run on and different directions to information the mannequin in producing the SQL question. These directions are included within the immediate despatched to the Bedrock mannequin.

   athena_sql_generating_instructions = """
   Learn database schema contained in the <database_schema></database_schema> tags which incorporates a listing of desk names and their schemas to do the next:
       1. Create a syntactically right AWS Athena question to reply the query.
       2. For tables with partitions, embrace the filters on the related partition columns.
       3. Embody solely related columns for the given query.
       4. Use solely the column names which are listed within the schema description. 
       5. Qualify column names with the desk title.
       6. Keep away from joins to a desk if there isn't any column required from the desk.
       7. Convert Strings to Date kind whereas filtering on Date kind columns
       8. Return the sql question contained in the <SQL></SQL> tab.
   """

5. Outline completely different immediate templates for demonstrating the significance of metadata in text-to-SQL technology. These templates have placeholders for SQL question producing directions and tables metadata.

   athena_prompt1 = """
   Human:  You might be an AWS Athena question professional whose output is a sound sql question. You might be given the next Directions for constructing the AWS Athena question.
   <Directions>
   {instruction_dtls}
   </Directions>
           
   Solely use the next tables outlined throughout the database_schema and table_schema XML-style tags:
   
   <database_schema>
   <table_schema>
   CREATE EXTERNAL TABLE employee_dtls (
     id int,
     title string,
     age int ,
     dept_id int,
     emp_category string ,
     location_id int ,
     joining_date date
   ) PARTITIONED BY (
     region_id string
     )
   </table_schema>
   
   <table_schema>
   CREATE EXTERNAL TABLE department_dtls (
     id int,
     title string ,
     location_id int 
   )
   </table_schema>
   </database_schema>
   
   Query: {query}
   
   Assistant: 
   """

6. Generate the ultimate immediate by passing the query and instruction particulars as arguments to the immediate template. Then, invoke the mannequin.

   question_asked = "Checklist of everlasting staff who work in North America and  joined after Jan 1 2024"
   prompt_template_for_query_generate = PromptTemplate.from_template(athena_prompt1)
   prompt_data_for_query_generate = prompt_template_for_query_generate.format(query=question_asked,instruction_dtls=athena_sql_generating_instructions)
   llm_generated_response = interactWithClaude(prompt_data_for_query_generate)
   print(llm_generated_response.substitute("<sql>", "").substitute("</sql>", " ")  )
   

7. The mannequin generates the SQL question for the consumer query through the use of the directions and desk particulars supplied within the immediate.

   SELECT employee_dtls.id, employee_dtls.title, employee_dtls.age, employee_dtls.dept_id, employee_dtls.emp_category
   FROM employee_dtls 
   WHERE employee_dtls.region_id = 'NA' 
     AND employee_dtls.emp_category = 'everlasting'
     AND employee_dtls.joining_date > CAST('2024-01-01' AS DATE)
   

Significance of prompts and metadata in text-to-SQL technology

Understanding the main points of tables and the information they comprise is crucial for each human SQL consultants and generative AI-based text-to-SQL technology. These particulars, collectively referred to as metadata, present essential context for writing SQL queries. For the text-to-SQL instance applied within the earlier part, we used prompts to convey particular directions and desk metadata to the mannequin, enabling it to carry out consumer duties successfully. A query arises on what degree of particulars we have to embrace within the desk metadata. To make clear this level, we requested the mannequin to generate SQL question for a similar query 3 times with completely different prompts every time.

Immediate with no metadata

For the primary take a look at, we used a fundamental immediate containing simply the SQL producing directions and no desk metadata. The essential immediate helped the mannequin generate a SQL question for the given query, however it’s not useful as a result of the mannequin made assumptions about desk names, column names, and literal values used within the filter expressions.

Query: Checklist of everlasting staff who work in North America and joined after January 1, 2024.

Immediate definition:

Human: You might be an Amazon Athena question professional whose output is a sound sql question. You might be given the next Directions for constructing the Amazon Athena question.
<Directions>
{instruction_dtls}
</Directions>

Query: {query}
Assistant:

SQL question generated:

SELECT emp.employee_id, emp.first_name, emp.last_name, emp.department_id
FROM worker emp
WHERE emp.contract="Everlasting"
AND emp.area = 'North America'
AND CAST(emp.start_date AS  DATE) > CAST('2024-01-01' AS DATE)

Immediate with fundamental metadata

For fixing the issue of assumed desk names and column names, we added desk metadata in DDL format within the second immediate. In consequence, the mannequin used the right column names and information sorts and restricted the DATE casting to a literal string worth. It received the SQL question syntactically right, however one concern stays: the mannequin assumed the literal values used within the filter expressions.

Query: Checklist of everlasting staff who work in North America and joined after January 1, 2024.

Immediate definition:

Human: You might be an Amazon Athena question professional whose output is a sound sql question. You might be given the next Directions for constructing the Amazon Athena question.
<Directions>
{instruction_dtls}
</Directions>

Solely use the next tables outlined throughout the database_schema and table_schema XML-style tags:

<database_schema>
<table_schema>
CREATE EXTERNAL TABLE employee_dtls (
  id int,
  title string,
  age int ,
  dept_id int,
  emp_category string ,
  location_id int ,
  joining_date date
) PARTITIONED BY (
  region_id string
  )
</table_schema>

<table_schema>
CREATE EXTERNAL TABLE department_dtls (
  id int,
  title string ,
  location_id int 
)
</table_schema>
</database_schema>

Query: {query}
Assistant:

SQL question generated:

SELECT employee_dtls.id, employee_dtls.title, employee_dtls.age, employee_dtls.dept_id, employee_dtls.emp_category
FROM employee_dtls 
WHERE employee_dtls.region_id = 'NA' 
  AND employee_dtls.emp_category = 'everlasting'
  AND employee_dtls.joining_date > CAST('2024-01-01' AS DATE)

Immediate with enriched metadata

Now we have to work out methods to present the attainable values of a column to the mannequin. A method could possibly be together with metadata within the column for low cardinality columns. So we added column descriptions together with attainable values within the third immediate. In consequence, the mannequin included the right literal values within the filter expressions and gave correct SQL question.

Query: Checklist of everlasting staff who work in North America and joined after Jan 1, 2024.

Immediate definition:

Human: You might be an Amazon Athena question professional whose output is a sound sql question. You might be given the next Directions for constructing the Amazon Athena question.
<Directions>
{instruction_dtls}
</Directions>

Solely use the next tables outlined throughout the database_schema and table_schema XML-style tags:

<database_schema>
<table_schema>
CREATE EXTERNAL TABLE employee_dtls (
id int COMMENT 'Worker id',
title string COMMENT 'Worker title',
age int COMMENT 'Worker age',
dept_id int COMMENT 'Worker Departments ID',
emp_category string COMMENT 'Worker class. Incorporates TEMP For momentary, PERM for everlasting, CONTR for contractors ',
location_id int COMMENT 'Location identifier of the Worker',
joining_date date  COMMENT 'Worker becoming a member of date',
CONSTRAINT pk_1 PRIMARY KEY  (id) ,
CONSTRAINT FK_1 FOREIGN KEY (dept_id) REFERENCES department_dtls(id)
) PARTITIONED BY (
region_id string COMMENT 'Area identifier. Incorporates AMER for Americas, EMEA for Europe, the Center East, and Africa, APAC for Asia Pacific international locations'
)
</table_schema>

<table_schema>
CREATE EXTERNAL TABLE department_dtls (
id int COMMENT 'Division id',
title string COMMENT 'Division title',
location_id int COMMENT 'Location identifier of the Division'
)
</table_schema>
</database_schema>

Query: {query}
Assistant:

SQL question generated:

SELECT employee_dtls.id, 
employee_dtls.title
FROM employee_dtls 
WHERE employee_dtls.emp_category = 'PERM'
  AND employee_dtls.region_id = 'AMER' 
  AND employee_dtls.joining_date > CAST('2024-01-01' AS DATE)

Immediate with overseas key constraints within the Metadata

Word that once we added the finer particulars to the metadata of the third immediate, we included overseas key constraints as nicely. That is carried out to assist the mannequin generate SQL for superior queries that require joins. Including overseas key constraints to the metadata helps the mannequin establish the right columns for use within the be part of situations. To reveal this level, we requested the mannequin to jot down SQL for displaying division particulars together with the worker particulars. For displaying the division particulars, we’d like the department_dtls desk. The mannequin added department_dtls desk to the SQL question and recognized the correct columns for the be part of situation based mostly on overseas key constraint particulars included within the metadata.

Query: Checklist of everlasting staff who work in North America and joined after Jan 1, 2024.

SQL question generated:

SELECT
  employee_dtls.title AS employee_name,
  employee_dtls.age,
  department_dtls.title AS department_name
FROM employee_dtls 
JOIN department_dtls 
  ON employee_dtls.dept_id = department_dtls.id
WHERE 
  employee_dtls.emp_category = 'PERM'
  AND employee_dtls.region_id = 'AMER' 
  AND employee_dtls.joining_date > CAST('2024-01-01' AS DATE)

Further observations

Although the mannequin included related worker attributes within the SELECT clause, the precise checklist of attributes it included assorted every time. Even for a similar immediate definition, the mannequin supplied a various checklist of attributes. The mannequin randomly used one of many two approaches for casting the string literal worth so far kind. The primary strategy makes use of CAST('2024-01-01' AS DATE) and the second strategy makes use of DATE '2024-01-01'.

Challenges in sustaining the metadata

Now that you just perceive how sustaining detailed metadata together with overseas key constraints helps the mannequin in producing correct SQL queries, let’s focus on how one can collect the mandatory particulars of desk metadata. The info lake and database catalogs assist gathering and querying metadata, together with desk and column descriptions. Nonetheless, ensuring that these descriptions are correct and up-to-date poses a number of sensible challenges, similar to:

1. Creating database objects with helpful descriptions requires collaboration between technical and enterprise groups to jot down detailed and significant descriptions. As tables endure schema modifications, updating metadata for every change may be time-consuming and requires effort.
2. Sustaining lists of attainable values for the columns requires steady updates.
3. Including information transformation particulars to metadata may be difficult due to the dispersed nature of this info throughout information processing pipelines, making it tough to extract and incorporate into table-level metadata.
4. Including information lineage particulars to metadata faces challenges due to the fragmented nature of this info throughout information processing pipelines, making extraction and integration into table-level metadata complicated.

Particular to the AWS Glue Knowledge Catalog, extra challenges come up, similar to the next:

1. Creating AWS Glue tables by way of crawlers doesn’t robotically generate desk or column descriptions, requiring handbook updates to desk definitions from the AWS Glue console.
2. Not like conventional relational databases, AWS Glue tables don’t explicitly outline or implement main keys or overseas keys. AWS Glue tables function on a schema-on-read foundation, the place the schema is inferred from the information when querying. Due to this fact, there’s no direct assist for specifying main keys, overseas keys, or column descriptions in AWS Glue tables like there’s in conventional databases.

Enriching the metadata

Listed right here some methods which you can overcome the beforehand talked about challenges in sustaining the metadata.

• Improve the desk and column descriptions: Documenting desk and column descriptions requires a very good understanding of the enterprise course of, terminology, acronyms, and area information. The next are the completely different strategies you should use to get these desk and column descriptions into the AWS Glue Knowledge Catalog.
  • Use generative AI to generate higher documentation: Enterprises usually doc their enterprise processes, terminologies, and acronyms and make them accessible by way of company-specific portals. By following naming conventions for tables and columns, consistency in object names may be achieved, making them extra relatable to enterprise terminology and acronyms. Utilizing generative AI fashions on Amazon Bedrock, you’ll be able to improve desk and column descriptions by feeding the fashions with enterprise terminology and acronym definitions together with the database schema objects. This strategy reduces the effort and time required to generate detailed descriptions. The not too long ago launched metadata function in Amazon DataZone, AI suggestions for descriptions in Amazon DataZone, is alongside these ideas. After you generate the descriptions, you’ll be able to replace the column descriptions utilizing any of the next choices.
    • From the AWS Glue catalog UI
    • Utilizing the AWS Glue SDK just like Step 3a : Create employee_dtls Glue desk for querying from Athena within the 0_create_tables_with_metadata.ipynb Jupyter Pocket book
    • Add the COMMENTS within the DDL script of the desk.

      CREATE EXTERNAL TABLE <table_name> 
      ( column1 string COMMENT '<column_description>' ) 
      PARTITIONED BY ( column2 string COMMENT '<column_description>' )

• For AWS Glue tables cataloged from different databases:
  • You may add desk and column descriptions from the supply databases utilizing the crawler in AWS Glue.
  • You may configure the EnableAdditionalMetadata Crawler choice to crawl metadata similar to feedback and uncooked information sorts from the underlying information sources. The AWS Glue crawler will then populate the extra metadata in AWS Glue Knowledge Catalog. This supplies a option to doc your tables and columns instantly from the metadata outlined within the underlying database.
• Improve the metadata with information profiling: As demonstrated within the earlier part, offering the checklist of values within the worker class column and their that means helped in producing the SQL question with extra correct filter situations. We are able to present such a listing of values or information traits within the column descriptions with the assistance of information profiling. Knowledge profiling is the method of analyzing and understanding the information and its traits as distinct values. Through the use of information profiling insights, we are able to improve column descriptions.
• Improve the metadata with particulars of partitions and a spread of partition values: As demonstrated within the earlier part, offering the checklist of partition values and their that means within the partition column description helped in producing the SQL with extra correct filter situations. For checklist partitions, we are able to add the checklist of the partition values and their meanings to the partition column description. For vary partitions, we are able to add extra context on the grain of the values like day by day, month-to-month, and a selected vary of values to the column description.

Enriching the immediate

You may improve the prompts with question optimization guidelines like partition pruning. Within the athena_sql_generating_instructions, outlined as a part of the 1_text-to-sql-for-athena.ipynb Jupyter Pocket book, we added an instruction “For tables with partitions, embrace the filters on the related partition columns”. This instruction guides the mannequin on methods to deal with partition pruning. Within the instance, we noticed that the mannequin added the related partition filter on the region_id partition column. These partition filters will pace up the SQL question execution and is among the prime question optimization methods. You may add extra such question optimization guidelines to the directions. You may improve these directions with related SQL examples.

Cleanup

To scrub up the assets, begin by cleansing up the S3 bucket that was created by the CloudFormation stack. Then delete the CloudFormation stack utilizing the next steps.

• Within the AWS Administration Console, select the title of the presently displayed Area and alter it to US West (Oregon).
• Navigate to AWS CloudFormation.
• Select Stacks.
• Choose texttosqlmetadata
• Select Delete.

Conclusion

The instance introduced within the submit highlights the significance of enriched metadata in producing correct SQL question utilizing the text-to-SQL capabilities of  Anthropic’s Claude mannequin on Amazon Bedrock and discusses a number of methods to counterpoint the metadata. Amazon Bedrock is on the heart of this text-to-SQL technology. Amazon Bedrock may also help you construct varied generative AI purposes together with the metadata technology use case talked about within the earlier part. To get began with Amazon Bedrock, we advocate following the fast begin within the GitHub repo and familiarizing your self with constructing generative AI purposes. After getting conversant in generative AI purposes, see the GitHub Textual content-to-SQL workshop to be taught extra text-to-SQL methods. See Construct a sturdy Textual content-to-SQL resolution and Finest practices for Textual content-to-SQL for the really useful structure and greatest practices to observe whereas implementing text-to-SQL technology.

In regards to the writer

Naidu Rongali is a Huge Knowledge and ML engineer at Amazon. He designs and develops information processing options for information intensive analytical programs supporting Amazon retail enterprise. He has been engaged on integrating generative AI capabilities into the information lake and information warehouse programs utilizing Amazon Bedrock AI fashions. Naidu has a PG diploma in Utilized Statistics from the Indian Statistical Institute, Calcutta and BTech in Electrical and Electronics from NIT, Warangal. Exterior of his work, Naidu practices yoga and goes trekking usually.