How we're using Gemini Embeddings to build a smarter, community-driven feed on DEV

Ben Halpern — Fri, 22 May 2026 16:27:19 +0000

Big improvements incoming 👋

Finding the right balance for a feed algorithm is historically really hard. If you optimize purely for clicks and comments, you end up with a clickbait echo chamber. But if you just sort by recency, it's a firehose where great discussions disappear in hours.

We've wrestled with this tension at DEV for a long time. We want a feed that feels alive, but actually surfaces high-quality, intellectually stimulating stuff.

So, we're trying something new. We are combining standard community signals—like who you follow and what you react to—with Gemini Embeddings 2 and pgvector.

Here is a look under the hood at how we are putting this together.

1. Keeping things flexible and auditable

Instead of duct-taping API calls all over the codebase, we built a flexible foundation using wrapper classes, mostly centered around Ai::Base and Ai::Embedding.

When a service needs the API, it just passes wrapper: self to the client. This lets Ai::Base look at the calling object, grab its class name, and check its VERSION.

Ai::Base.new(wrapper: self)

This pattern gives us a really clean audit trail via our AiAudit model. Every single time we generate a vector or analyze a trend, we automatically log the model used, the caller's class, payloads, latency, and token counts.

It makes debugging and tracking costs so much easier, without muddying up our core business logic.

2. A more personalized feed

Our main feed is powered by FeedConfig. It compiles custom SQL to score and rank articles for you.

Historically, this was all hardcoded math based on things like tags and whether you follow the author. Now, we've introduced a semantic feedback loop.

As you interact with the platform, we compile a dynamic interest_embedding that represents what you actually care about. We use the pgvector extension in PostgreSQL to inject your interests directly into the SQL query:

(
  CASE
    WHEN articles.semantic_embedding IS NOT NULL
      AND articles.published_at >= :published_since
    THEN (1 - (articles.semantic_embedding <=> :interest_embedding)) * :semantic_similarity_weight
    ELSE 0
  END
)

By using 1 - (embedding <=> user_interest), we get a cosine similarity score. We scale that up and mix it in with standard social signals (like who you follow), post quality, and time decay.

This means a highly relevant post can rise to the top of your feed, but so can a globally trending post from a community member you love. It’s all about balance.

3. What the heck is an embedding anyway? (And why v2 matters)

If you're new to the concept, an embedding is basically taking a piece of content—like an article text—and turning it into a long string of numbers (a vector). These numbers map the content into a "semantic space." If two posts are talking about the exact same conceptual ideas, their numbers will look very similar mathematically, even if they use completely different wording.

We've upgraded this pipeline to use Google's newly released Gemini Embeddings 2 model.

A standard text embedding model only looks at words. But Gemini Embeddings 2 compiles into massive 3,072-dimensional vectors and maps everything into a single, unified semantic space.

Future-proofing for a multi-modal DEV

The coolest part about moving to Embeddings 2 is that it isn't just restricted to text. It natively accepts multimodal inputs—meaning text, code, images, audio, and video.

Right now, we're using it to analyze written DEV posts. But because the underlying math maps everything into the exact same vector space, we are completely future-proofing our infrastructure. As the DEV platform evolves, we can easily feed images, podcast audio, or video posts into the exact same database architecture[.

A user's interest_embedding will be able to effortlessly surface an open-source video tutorial or a technical podcast episode based entirely on conceptual relevance, without us needing to rewrite our feed logic from scratch.

4. Catching nuanced trends 📈

Tags are great for high-level sorting, but they miss the highly specific, timely conversations. If Ruby 3.4 drops, a #ruby tag search won't distinguish between a "Hello World" tutorial and a deep debate about the new parser.

To fix this, we are in the process of building a clustering service powered by TrendDetector.

Every 6 hours, a background job runs a Leader Clustering algorithm in pure Ruby:

Quality first: We only look at recent articles scoring at least 15 points above our homepage minimum.
Clustering: We measure the cosine distance between articles. If a post is close enough (0.15 or less) to an existing cluster, it joins it. If not, it starts a new one.
Labeling: Once a cluster hits 10 or more articles, we ask the Gemini API to label the trend and summarize the core debate.

We store all of this in TrendMembership, which lets us sort articles in the UI based on how close they are to the core topic.

All of this can be tracked via our open source codebase Forem:

forem / forem

For empowering community 🌱

Forem 🌱

For Empowering Community

Welcome to the Forem codebase, the platform that powers dev.to. We are so excited to have you. With your help, we can build out Forem’s usability, scalability, and stability to better serve our communities.

What is Forem?

Forem is open source software for building communities. Communities for your peers, customers, fanbases, families, friends, and any other time and space where people need to come together to be part of a collective See our announcement post for a high-level overview of what Forem is.

dev.to (or just DEV) is hosted by Forem. It is a community of software developers who write articles, take part in discussions, and build their professional profiles. We value supportive and constructive dialogue in the pursuit of great code and career growth for all members. The ecosystem spans from beginner to advanced developers, and all are welcome to find their place…

View on GitHub

5. Putting the community first ❤️

Human curation, both from the broader community and our editorial perspective, is still the backbone of the system.

We are using Gemini Embeddings to amplify what the community is already doing. It’s about mixing the raw utility of vector search with the human spirit of developer-voted scores and relationships.

We want DEV to be the best place on the internet to share code and talk about software. We think this is a big step in that direction.

What do you think? Let me know in the comments.

Happy coding!

Definitely looking forward to using Antigravity 2.0

Ben Halpern — Tue, 19 May 2026 17:27:33 +0000

Meme Monday

Ben Halpern — Mon, 18 May 2026 12:47:35 +0000

Meme Monday!

Today's cover image comes from the last thread.

DEV is an inclusive space! Humor in poor taste will be downvoted by mods.

Meme Monday

Ben Halpern — Mon, 11 May 2026 10:06:48 +0000

Meme Monday!

Today's cover image comes from the last thread.

DEV is an inclusive space! Humor in poor taste will be downvoted by mods.

Meme Monday

Ben Halpern — Mon, 04 May 2026 12:44:01 +0000

Meme Monday!

Today's cover image comes from the last thread.

DEV is an inclusive space! Humor in poor taste will be downvoted by mods.

me_irl

Ben Halpern — Fri, 01 May 2026 22:58:54 +0000

My LLM assistant's new buzzword is starting responses with "be completely candid". Very grating.

Ben Halpern — Fri, 01 May 2026 15:53:12 +0000

https://github.blog/news-insights/company-news/an-update-on-github-availability/

Ben Halpern — Tue, 28 Apr 2026 21:18:01 +0000

An update on GitHub availability - The GitHub Blog

Here’s what we’ve done—and what we’re still doing—to improve our availability and reliability.

github.blog

Meme Monday

Ben Halpern — Mon, 27 Apr 2026 13:11:07 +0000

Meme Monday!

Today's cover image comes from the last thread.

DEV is an inclusive space! Humor in poor taste will be downvoted by mods.

This is pretty exciting! https://github.com/matz/spinel

Ben Halpern — Fri, 24 Apr 2026 14:39:33 +0000

GitHub - matz/spinel · GitHub

Contribute to matz/spinel development by creating an account on GitHub.

github.com

Forem Core: Ben Halpern

How we're using Gemini Embeddings to build a smarter, community-driven feed on DEV

1. Keeping things flexible and auditable

2. A more personalized feed

3. What the heck is an embedding anyway? (And why v2 matters)

Future-proofing for a multi-modal DEV

4. Catching nuanced trends 📈

forem / forem

For empowering community 🌱

Forem 🌱

What is Forem?

5. Putting the community first ❤️

Pretty normal

I Used to Get Excited About New Tools Now I Feel Tired.

Definitely looking forward to using Antigravity 2.0

Meme Monday

Meme Monday

Meme Monday

me_irl

My LLM assistant's new buzzword is starting responses with "be completely candid". Very grating.

Same for me at the moment

I don't want to give Claude SSH access to my home server

https://github.blog/news-insights/company-news/an-update-on-github-availability/

An update on GitHub availability - The GitHub Blog

Meme Monday

This is pretty exciting! https://github.com/matz/spinel

GitHub - matz/spinel · GitHub