Blog
Notes from the team
Engineering deep dives, release notes and talks from Starlight Search, the team behind Pulsar and EmbedAnything.
- EmbedAnything update
Sonam Pankaj4 min read
Release Notes 0.7
0.7 is all about making deployment easy and integrations to data sources. Including Prebuilt Docker Image,SearchR1 example to improve context for Agents and AWS S3 bucket Integration.
[Read post]- EmbedAnything update
Sonam Pankaj6 min read
Beyond EmbedAnything: A Year of Growth Beyond Expectations!!
Reflecting on EmbedAnything: A Year Later A year ago, I shared the story behind EmbedAnything—how we built and scaled an embedding infrastructure that has since been loved by developers at Microsoft, Meta, Tencent, AWS…
[Read post]- EmbedAnything update
Sonam Pankaj3 min read
Memory Leak Explained!
Vector Streaming is popular for its low latency and high modularity features. But the best of it all is the memory leak that we are trying to bring it but haven’t been able to click with the audience yet. Why we named…
[Read post]- EmbedAnything update
Sonam Pankaj3 min read
How to Configure TextEmbedConfig in EmbedAnything
After presenting at Google, PyCon DE, Berlin Buzzwords, and GDG Berlin, I was surprised by how many people approached me with questions about writing configurations, chunk sizes, and batch sizes for EmbedAnything. Since…
[Read post]- EmbedAnything update
Sonam Pankaj2 min read
Release Notes 6.0
Super Excited to share the latest development in our library, which essentially giving you more embedding choices -- Cohere and siglip, new chunking method-- late chunking and more crates that facilitates amazing…
[Read post]- EmbedAnything update
Sonam Pankaj3 min read
Easy MCP integration to our agentic framework; LUMO
Building a Server with Lumo: A Step-by-Step Guide to MCP Integration Lumo, a powerful Rust-based agent, offers seamless integration with MCPs (Modular Control Protocols) and remarkable flexibility in implementation…
[Read post]- EmbedAnything update
Sonam Pankaj2 min read
Easy Observability to our agentic framework; LUMO
In the rapidly evolving landscape of AI agents, particularly those employing Large Language Models (LLMs), observability and tracing have emerged as fundamental requirements rather than optional features. As agents…
[Read post]- EmbedAnything update
Sonam Pankaj5 min read
PyCon Germany
The 2025 PyCon DE event highlighted a growing but cautious interest in AI agents among the Python community. While agent technology received significant attention, many speakers and attendees expressed skepticism about…
[Read post]- EmbedAnything update
Sonam Pankaj & Akshay Ballal4 min read
How to write adapters for your vector database.
We have received multiple requests to add different vector database for our vector streaming. So We have decided to put a detailed guide for different vector databases out there. We are happy to accept pull-request.
[Read post]- EmbedAnything update
Sonam Pankaj & Akshay Ballal5 min read
In-and-Out of domain query with EmbedAnything and SmolAgent
When working with domain-specific queries, we often struggle with the challenge of balancing in-domain and out-of-domain requests. But not anymore! With embedanything, you can leverage fine-tuned, domain-focused models…
[Read post]- EmbedAnything update
Sonam Pankaj1 min read
version 0.5
We are thrilled to share that EmbedAnything version 0.5 is out now and comprise of insane development like support for ModernBert and ReRanker models. Along with Ingestion pipeline support for DocX, and HTML let’s get…
[Read post]- EmbedAnything update
Sonam Pankaj & Akshay Ballal7 min read
Optimize VLM Tokens with EmbedAnything x ColPali
ColPali, a late-interaction vision model, leverages this power to enable text searches within images. This means you can pinpoint the exact pages in a PDF containing relevant text, even if the text exists only as part…
[Read post]- EmbedAnything update
Sonam Pankaj4 min read
The path ahead of EmbedAnything
In March, we set out to build a local file search app. We aimed to create a tool that would make file searching faster, more innovative, and more efficient. However, we quickly hit a roadblock: no high-performance…
[Read post]- EmbedAnything update
Akshay Ballal & Sonam Pankaj7 min read
About Embed Anything
EmbedAnything is an open-source Rust/Python framework that lets you generate vector embeddings for any data (text, images, audio) with minimal code. It's blazing fast, memory-efficient, and can handle massive datasets…
[Read post]- EmbedAnything update
Sonam Pankaj5 min read
Gemini as a Research Agent: Fusion Deep Research for Intelligent Information Retrieval
In today's data-saturated world, effective research isn't just about accessing information—it's about finding the right information efficiently. Let's explore how Gemini can function as a sophisticated research agent…
[Read post]- EmbedAnything update
Akshay Ballal & Sonam Pankaj4 min read
Vector Streaming
Introducing vector streaming in EmbedAnything, a feature designed to optimize large-scale document embedding. By enabling asynchronous chunking and embedding using Rust’s concurrency, it reduces memory usage and speeds…
[Read post]
Put Pulsar to work.
Start free on Pulsar Cloud, or book 30 minutes with us to see how it would run in your own environment.