Search
// vespa

End-to-End Vespa Neural Search Tutorial

In this tutorial, we will dive into the world of Vespa, a highly scalable and distributed search engine. We will explore how Vespa leverages neural networks to enhance search capabilities, improve relevance, and enable advanced natural language processing techniques. Join us as we uncover the exciting possibilities of neural search with Vespa.

Recorded

coming soon

If you are not able to attend public training, this is the best option for you. You will be able to take the course at your own pace and rhythm and learn whenever it fits your schedule and mood.

  • Top expert trainers
  • Q&A by e-mail
  • Certificate of Attendance

Private

ask for quote

If you are looking for intensive sessions tailored to your (or your team’s) experience, then private training is your perfect choice!

  • In presence or Online
  • Tailored Training
  • Top Expert Trainers
  • Certificate of Attendance

Recorded

coming soon

If you are not able to attend public training, this is the best option for you. You will be able to take the course at your own pace and rhythm and learn whenever it fits your schedule and mood.

  • Top expert trainers
  • Q&A by e-mail
  • Certificate of Attendance

Public classroom

£ 250,00

SCHEDULE

19th Jun 2024

3:00 – 7:00 PM GMT+1

  • Live on Zoom
  • Top expert trainers
  • Certificate of Attendance
By Purchasing the training You Accept our Training’s Terms and Conditions

Private

ask for quote

If you are looking for intensive sessions tailored to your (or your team’s) experience, then private training is your perfect choice!

  • In presence or Online
  • Tailored Training
  • Top Expert Trainers
  • Certificate of Attendance

Based on experience with leading companies including

Based on experience with leading companies including

universal
BBC
Alfresco
I recently took the course on Apache Solr Neural Search and I must say it was really good. Alessandro and Ilaria were very knowledgeable and presented the material in a clear and concise manner. They went over the contents at a reasonable pace giving enough time for questions at the end of each section. The training was extremely helpful in understanding the concepts and implementation of vector-based search in Solr.
I highly recommend this course to anyone looking to avail of Solr neural search capabilities to improve search experience.
Ahmad Abdelghany
Software Development Manager @ Shutterstock

PREREQUISITES

• Basic understanding of Search Engines

• Basic understanding of Neural Search principles

• Familiarity with Vespa

WHAT YOU WILL LEARN

• How to Prepare suitable documents

• How to export a suitable neural model and use it in Vespa

• How to configure Vespa for Neural Search

• How to run Nearest Neighbor queries, combining them with filters and textual search

INTENDED AUDIENCE

• Data scientists
• Software Engineers
• Developers

Your Trainers

Alessandro Benedetti

APACHE LUCENE/SOLR COMMITTER
APACHE SOLR PMC MEMBER

Alessandro has been involved in designing and developing search-relevant solutions from 2010.
Over the years he has worked on various projects, with various open source technologies aiming to build search solutions able to satisfy the user information needs, often integrating such solutions with machine learning and artificial intelligence technologies.

Anna Ruggero

R&D Search Software Engineer, her focus is on the integration of Information Retrieval systems with advanced Machine Learning, Natural Language Processing and Data Mining algorithms. She likes to find new solutions that integrate her work as a Search Consultant with the latest Academia studies.

The schedule

The training session is meticulously structured for optimal comprehension and retention. 

It commences with a comprehensive 1-hour theory session, followed by a brief 15-minute test to assess understanding. Subsequently, participants engage in a 45-minute Q&A segment, fostering interactive learning and clarification of concepts. The training then resumes with another 1-hour theory module, another 15-minute evaluation test, and concludes with a final 45-minute Q&A session to consolidate knowledge and address any remaining queries.

3:00-4:00 theory session
4:00-4:15 test
4:15-5:00 Q&A segment

5:00-6:00 theory session
6:00-6:15 test
6:15-7:00 Q&A segment

Topics

1. BRIEF OVERVIEW

The training begins by providing participants with a foundational understanding of Vespa and Neural Search. This introductory module offers insights into the significance, applications, and fundamental concepts underlying Vespa and Neural Search, setting the stage for deeper exploration.

2. PREPARE DOCUMENTS

In this section, learn how to create documents that align with Vespa’s required format. A Python script with real examples will be shown to participants.

3. EXPORT THE NEURAL MODEL

Explore the management aspects of language models through their lifecycle. Currently, Vespa supports models in ONNX XGBoost and LightGBM format. In this section, participants will learn how to export a HuggingFace model to be loaded in Vespa with step-by-step code examples.

4. CONFIGURE VESPA (SERVICES + SCHEMA)

In this section, learn how to configure Vespa to use an embedding model both at index and query time. Explore the steps to define and configure the vector field within your Vespa schema. Gain practical insights into optimizing the indexing process to efficiently store and manage vector data. Lay the foundation for leveraging vector fields in neural search applications within Vespa.

5. Index documents

Discover how to index documents into Vespa’s neural search index. Follow a step-by-step guide to ingest and store documents within the Vespa index, ensuring efficient retrieval and search capabilities. Learn best practices for optimizing indexing performance and maintaining data integrity. Gain practical experience in seamlessly integrating document indexing with Vespa’s neural search functionality.

6. Neural Search Queries
Unlock the full potential of Vespa’s neural search capabilities in this comprehensive section. Explore advanced search techniques, including:
  • Exact Nearest Neighbor Search
  • Approximate Nearest Neighbor Search
  • Approximate Nearest Neighbor with query filter
  • Multi-vector Approximate Nearest Neighbor Search
  • Multiple Nearest Neighbor Search Operators in the Same Query
  • Hybrid Sparse and Dense Retrieval Methods
  • Normalized Hybrid Search
  • Approximate Nearest Neighbor for Re-ranking
Gain practical insights into optimizing search performance and enhancing search relevance through innovative approaches. Develop proficiency in harnessing Vespa’s neural search features to deliver superior search experiences.

FAQ

The training session is conducted online via Zoom for live participation. However, for those who may not be able to attend in real-time or prefer to learn at their own pace, we are working on a recorded version. This allows participants to access the content online and review it at their convenience.

Absolutely! Everyone is welcome to participate in this training. Please note that there are specific prerequisites listed nearby, so be sure to check those before inviting others to ensure they meet the requirements.

The ‘The End-to-End Vespa Neural Search Tutorial’ training session has a duration of 4 hours. This includes a 2-hour theory session, a 30-minute test, followed by a 1.5-hour Q&A segment.

Yes, absolutely! You will have the opportunity to ask any questions you may have at the end of the test module.

Your teachers will be:
  – Alessandro Benedetti, Apache Lucene/Solr committer and Apache Solr PMC member.

Yes, indeed! At the conclusion of the training, you will receive a certificate of attendance via email.

Yes, we do offer corporate training sessions. Feel free to reach out to us, and we’ll be happy to discuss the best options tailored for you and your team!

    Feel free to contact us

    Your email address will not be published. Required fields are marked *