Nice... it's cool to see how different companies are putting together best fit solutions. I'm also glad that they at least started out with off the shelf apps instead of jumping to something like a bespoke solution early on. Quickwit[1] looks interesting, found via Tantivity reference. Kind of like ES w/ Lucene. 1. https://github.com/quickwit-oss/quickwit. - Source: Hacker News / about 1 year ago

Https://github.com/quickwit-oss/quickwit to_tsvector in PG never worked well for my use cases SELECT * FROM dump WHERE to_tsvector('english'::regconfig, hh_fullname) @@ to_tsquery('english'::regconfig, 'query'); Wish them to succeed. Will automatically upvote any post Tantivy as keyword. - Source: Hacker News / about 2 years ago

We tested S3 Express for our search engine quickwit[0] a couple of weeks ago. While this was really satisfying on the performance side, we were a bit disappointed by the price, and I mostly agree with the article on this matter. I can see some very specific use cases where the pricing should be OK but currently, I would say most of our users should just stay on the classic S3 and add some local SSD caching if they... - Source: Hacker News / over 2 years ago

Quickwit (https://quickwit.io/) | Paris, France | Onsite and remote (based in Europe) | Full-time The company is fully remote but we also have a small office in Paris. We prefer candidates based in Europe but can make exceptions for the right profiles. - Senior Software Engineer 80-110k€ + 0.25-1% equity based on experience.

    We’re looking for a senior software engineer to contribute to...

- Source: Hacker News / almost 3 years ago

- Another nice comment seen on HN « it seems to be very easy to run, not very IO intensive, and running fine on a single node with modest hardware with >2 billion log rows. It has a really cool dynamic schema feature too.» [9] Fun fact: at least 4 users are using Garage[10] as the object storage, this OSS project looks really promising and made the HN front page a few months ago[11], we really cherish the OSS for... - Source: Hacker News / about 3 years ago

If you build on the JVM and want to use Qdrant, the official client is io.qdrant:client — and it's built for Java. Every call returns a ListenableFuture, requests are assembled with protobuf builders, and it drags a gRPC/Netty stack onto your classpath. From Kotlin, that means fighting the language:. - Source: dev.to / 20 days ago

The stack runs on Qdrant for vector storage, Ollama for local embeddings, and optional Neo4j for a knowledge graph that I added later. I also set it up to route different operations to the best LLM for each task. It provides eleven tools for your Claude Code instance to manage long-term memory operations, and your memories data never leaves your machine. - Source: dev.to / 6 months ago

Qdrant: Open-source vector database optimized for hybrid search and easy integration with ML workflows. - Source: dev.to / 9 months ago

Yes, Java SDKs are critical. But you don't need to rebuild entire orchestration engines just to write agents in Java. The ecosystem already has platforms solving the hard problems: memory (Zep, Mem0, LangMem), tools (specialized platforms), vectors (Pinecone, Weaviate, Qdrant), observability (LangSmith, Helicone, Langfuse). Integrate, don't rebuild. - Source: dev.to / 9 months ago

James Allsopp adds, "LangChain or LlamaIndex for managing LLM workflows, especially if you're adding vector search or documents." These tools handle multi-step processes, essential for complex apps. - Source: dev.to / 12 months ago