Ep10: What Are Embeddings + LLM Use Case And Prompt Breaktime Tech Talks podcast

Artwork

Tech News Tech News jmhreif

Player FM - Internet Radio Done Right

Đã thêm cách đây bốn mươi ba tuần

Nội dung được cung cấp bởi jmhreif. Tất cả nội dung podcast bao gồm các tập, đồ họa và mô tả podcast đều được jmhreif hoặc đối tác nền tảng podcast của họ tải lên và cung cấp trực tiếp. Nếu bạn cho rằng ai đó đang sử dụng tác phẩm có bản quyền của bạn mà không có sự cho phép của bạn, bạn có thể làm theo quy trình được nêu ở đây https://vi.player.fm/legal.

O

Obscurities

Obscurities podcast artwork

Obscurities podcast artwork

1
The Lead Masks Mystery: Death on Vintém Hill 5:58

cách đây 26 ngày trước5:58

5:58

In 1966, two Brazilian men were found dead on Vintém Hill under bizarre circumstances that continue to perplex investigators and conspiracy theorists alike. Lying side by side, their bodies were discovered wearing matching lead masks—shields with no eyeholes—alongside cryptic notes. Were they victims of a cult ritual, a failed experiment, or something even more otherworldly? See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info .…

Breaktime Tech Talks « »
Ep10: What are embeddings + LLM use case and prompt

cách đây khoảng một năm trước 7:35

Chia sẻ

MP3•Trang chủ episode

Nội dung được cung cấp bởi jmhreif. Tất cả nội dung podcast bao gồm các tập, đồ họa và mô tả podcast đều được jmhreif hoặc đối tác nền tảng podcast của họ tải lên và cung cấp trực tiếp. Nếu bạn cho rằng ai đó đang sử dụng tác phẩm có bản quyền của bạn mà không có sự cho phép của bạn, bạn có thể làm theo quy trình được nêu ở đây https://vi.player.fm/legal.

With the amount of new information, sometimes it’s hard to review earlier concepts. In this episode, we explain what an embedding is and talk about aligning your prompt with your use case for improving LLM answers (example app code repository).

… continue reading

39 tập

#Tech #News #Tech News #jmhreif

Artwork

Ep10: What are embeddings + LLM use case and prompt

Breaktime Tech Talks

published cách đây khoảng một năm trước

Chia sẻ

MP3•Trang chủ episode

Nội dung được cung cấp bởi jmhreif. Tất cả nội dung podcast bao gồm các tập, đồ họa và mô tả podcast đều được jmhreif hoặc đối tác nền tảng podcast của họ tải lên và cung cấp trực tiếp. Nếu bạn cho rằng ai đó đang sử dụng tác phẩm có bản quyền của bạn mà không có sự cho phép của bạn, bạn có thể làm theo quy trình được nêu ở đây https://vi.player.fm/legal.

With the amount of new information, sometimes it’s hard to review earlier concepts. In this episode, we explain what an embedding is and talk about aligning your prompt with your use case for improving LLM answers (example app code repository).

… continue reading

39 tập

#Tech #News #Tech News #jmhreif

Tất cả các tập

×

1
Ep39: Why embedding models should match + Advice for starting a blog 13:36

cách đây 6 ngày trước13:36

13:36

In this podcast episode, hear about my hands-on experience ( code repository on Github ) understanding the importance of using the same embedding models for both creating and searching vector embeddings in databases and how mismatched models can lead to poor search results. I also pull highlights from an article with advice for those interested in blogging , and how it particularly relates to my own approach to tech blogging.…

1
Ep38: Spring AI Debugging + How to Contribute to Open Source 13:25

cách đây 20 ngày trước13:25

13:25

In this episode, I continue my journey with vector databases, integrating Pinecone , Neo4j , and Spring AI . While making some progress, I also encountered hurdles, such as evolving APIs and the unique architecture of vector stores. Next, I share insights from an article on contributing to open-source projects , how it can accelerate your career and enhance both your technical and soft skills. From picking the right project to building credibility within the community, it's a series of steps that gets better with time and practice!…

1
Ep37: Vector Database Frustration + Microsoft LazyGraphRAG 12:22

cách đây 27 ngày trước12:22

12:22

In this episode, I discuss my challenges exploring vector databases for an upcoming demo. From what is a vector database to integration issues, hear how I tried a few different approaches with limited success and discover the surprising one with the most promise. I also explore Microsoft's "Lazy Graph RAG" approach, which seems to trade one challenge for another but could be valuable in certain cases.…

1
Ep36: What is a Developer Advocate + Balancing Digital Consumption 11:27

cách đây 6 weeks trước11:27

11:27

This week, I explored the Javalin Java framework and project decisions I'm trying to make. I also answer: What exactly does a Developer Advocate/Evangelist/Devrel do? Finally, I reflect on an article on balancing digital consumption with actual productivity.

1
Ep35: Vector Databases + Building Effective Agents 8:53

cách đây 7 weeks trước8:53

8:53

In this episode, there are two topics I'm looking forward to diving deeper into: vector databases and AI agents. I'm particularly interested in understanding how vector databases work, how they work with data, and their role in AI applications. Then I share my thoughts on Anthropic’s article about Building AI Agents , which discusses their varying definitions—from simple workflows to fully autonomous systems—and provides practical examples. The article highlights the importance of starting simple, adding complexity only as needed.…

1
Ep34: Outlines and Iterating + Lessons from Grace Hopper 13:21

cách đây 8 weeks trước13:21

13:21

In this podcast episode, hear my process of preparing for an upcoming conference with insights on how outlines enhance presentations and blog posts, as well as code and architecture. Also discuss how constant improvement is key with an online course as an example. Finally, I highlight a historical read on cryptography , and share reflections from Grace Hopper's 1982 lecture on data, hardware, and software , drawing connections between her insights and modern challenges in technology.…

1
Ep33: Cypher DSL examples + Crowd-source AI hacking 8:58

cách đây 9 weeks trước8:58

8:58

In this episode, I share recent blog posts. The first is about tackling challenges with GitHub repositories , offering solutions on syncing forks and using git rebasing, diffs, and pruning. Next, I created examples with Cypher DSL , providing beginner-friendly details to help users get started. Additionally, I started prepping for the Devnexus conference , where I'll be delivering my first keynote. I also read an article about an intriguing AI testing project where a user successfully manipulated an AI to break its rules and win a $50,000 prize, illustrating the potential challenges AI systems face in handling sensitive tasks.…

1
Ep32: Official CLI + Bread Code Framework 10:32

cách đây 10 weeks trước10:32

10:32

In this episode, I’m following up on a few things I’ve mentioned before. I dive into some updates on the Aura CLI (the official product version). I also explored the Neo4j GenAI Java library a bit more, including a connection hiccup I ran into with Neo4j Desktop. Then, I get into my experience with the Cypher DSL library and how Cypher fits into the retrieval part of RAG systems. Finally, I take a fun detour into an interesting article about a GitHub repository that combines coding and sourdough baking . It’s a cool reminder that the skills we learn in coding can apply to all sorts of other areas, even in the kitchen!…

1
Ep31: Database CLI + Containerization Refcard 9:31

cách đây 11 weeks trước9:31

9:31

In this episode, hear updates on a few projects, including Neo4j's new Aura CLI and NeoConverse . Plus, the promised blog post from last week's episode on Spring Data Neo4j entity updates . Shout-out to the JAXJUG and TampaJUG groups. If you're not involved with a tech group, there are options! Finally, a review of the DZone RefCard on Java containerization with its clear guidance on Docker containers, native builds, and deployment, making complex concepts more accessible for developers.…

1
Ep30: SDN update entity + Knowledge Graph ebook 9:06

cách đây 12 weeks trước9:06

9:06

Dive into my latest experiences with Spring Data Neo4j, specifically exploring new methods for updating nodes. After revisiting my 2023 blog post on this topic, I share insights on custom Cypher queries and projections . I also discuss the challenges of finding good examples for update operations. In addition, Neo4j announced the release of The Developer's Guide: How to Build a Knowledge Graph , a new ebook I co-authored. Hear my challenges of writing the book, including finding the right dataset for graph queries, working through product updates during the writing process, and the complexities of collaborating across different perspectives. Stay tuned for future updates, as we continue to refine this ever-evolving resource.…

1
Ep29: Neo4j GenAI plugin + How-To for Technical Content 10:16

cách đây 13 weeks trước10:16

10:16

In this episode, dive into a few exciting areas I've been exploring, including generative AI and graph technologies. I worked with Neo4j’s generative AI plugin for an experiment, and it wasn't all smooth sailing. Next, my highlights from an article in the Descript community on how to expand your educational YouTube audience —especially applied for those creating technical content. Key tips include thinking like a viewer to ask great questions, tweaking video intros to keep people engaged, and channeling viewer interests to strengthen connections.…

1
Ep28: 2024 Recap, 2025 Look-Ahead + Always Be Launching 12:32

cách đây 15 weeks trước12:32

12:32

Take a moment to reflect on 2024, exploring highlights in AI advancements, personal growth, and professional achievements, along with exciting 2025 goals. Then delve into an article that discusses marketing strategies but aligns well with developer advocacy.

1
Ep27: Lexical vs Semantic Search + Downside of Vector Databases 8:54

cách đây 16 weeks trước8:54

8:54

Explore the distinction between lexical and semantic search technologies, the growing use of vector databases , and the potential challenges and solutions that may arise as these technologies mature.

1
Ep26: Git Troubles + Dungeons & Dragons Graph 11:43

cách đây 18 weeks trước11:43

11:43

Git issues, finally resetting local branch , cherry-picking , and cleaning up . Then a fun graph presentation - Dungeons, Dragons, and Graph Databases .

1
Ep25: Github Actions + AI Coding Assistant 8:56

cách đây 19 weeks trước8:56

8:56

In this episode, hear some positive tech experiences from the week: the upgrade from GitHub Actions ( upload/download artifact ) to v4 through a 3rd party repo , and the new AI coding assistant feature in IntelliJ IDEA.

Chào mừng bạn đến với Player FM!

Player FM đang quét trang web để tìm các podcast chất lượng cao cho bạn thưởng thức ngay bây giờ. Đây là ứng dụng podcast tốt nhất và hoạt động trên Android, iPhone và web. Đăng ký để đồng bộ các theo dõi trên tất cả thiết bị.

Nghe hơn 500 chủ đề

Hướng dẫn sử dụng nhanh

Podcast hàng đầu

Tạp chí thể thao

Tạp chí kinh tế

KBS WORLD Radio Tiếng Hàn qua phim ảnh

Vietnamese News - NHK WORLD RADIO JAPAN

Tạp chí tiêu điểm

The Present Writer

Podcasts – Life Abroad Podcast

Nghe chương trình này trong khi bạn khám phá