Top all-time · #11427
The Sovereign AI Platform for Agents
Company blog · deepset.ai/blog · on HN as antti909aiprogramming
The Sovereign AI Platform for Agents is the company blog at deepset.ai, writing about ai and programming. Since 2021, 7 different Hacker News readers have linked it 9 times. No feed was found, so read it on the site itself.
Too few sampled comments (4) to say how often HN recommends it.?
Why HN links it
HN readers link deepset's pages about Haystack, its open-source framework for NLP search pipelines, and a blog post on building conversational agents. Comments are mostly job postings or mentions of Haystack.
Summarised by Claude from a sample of 4 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Deploy production AI with full control. Build agents and RAG systems using the Haystack Enterprise Platform, trusted by enterprise, defense, and regulated industries.
What Hacker News says?
deepset | Python Engineers, DevOps, Frontend Engineers | Berlin, Remote (CET +/- 2) | https://deepset.ai/ We build Haystack, an Open Source-framework that empowers developers to build NLP-powered search pipelines for various use cases: https://github.com/deepset-ai/haystack On our mission to bring the State-of-the-Art of NLP into every application, we look for different roles to join our team and our journey! If you…
Comment linking /
on “Ask HN: Who is hiring? (April 2021)”Submitted How to make a Rasa chatbot search for answers with Haystack and QA as a story · 4 points
HN discussionThis depends mostly on what kind of search engine you're trying to build. I unfortunately won't be able to point you towards courses, but there are tons of great resources online to help you get started. Search engines are a fairly broad topic, and a lot of it depends on the _type of data_ that you want to build a search engine for. If you're looking towards more traditional, Google/Yahoo-like search, Elasticsearch'…
Comment linking /blog/semantic-search-with-milvus-knowledge-graph-qa-web-crawlers-and-more
on “Ask HN: I want to dive into how to make search engines”Submitted How to Evaluate a Question Answering System as a story · 2 points
HN discussionRe structured data - in theory, yes :) We have to work a bit more in that direction. Here's the first step - querying table data, which could be really helpful for reports, financial data, etc. In regards to the storage backend - it's currently Elasticsearch, OpenSearch, SQL+FAISS/Milvus/Weaviate (when using dense vectors/dense passage retrieval). There is also an in-memory datastore using python primitives for fast…
Comment linking /blog/new-features-in-haystack-v1.0
on “Haystack 1.0 – open-source NLP framework to build NLProc back end applications”Submitted Customizing Retrieval Augmented Generation (RAG) Systems as a story · 1 points
HN discussionWe are hiring at deepset, makers of Haystack | Forward Deployed Engineers | Remote (EU/UK) + hubs: Berlin, Barcelona, London | Full Time * We build AI that companies actually run in production (not demos) * You ship customer-facing LLM apps end-to-end: discovery → build → rollout * You sit at the intersection of product, engineering, and customer teams Interesting problems you’ll work on: * Turning messy workflows +…
Comment linking /careers
on “Ask HN: Who is hiring? (February 2026)”Submitted The Art of Finding as a story · 1 points
HN discussionAlso, with Haystack and a smaller Transformer model to address the long-tail of answers https://github.com/deepset-ai/rasa-haystack (and https://www.deepset.ai/blog/build-smart-conversational-agent... )
Comment linking /blog/build-smart-conversational-agents-with-chatbots-qa
on “RasaGPT: First headless LLM chatbot built on top of Rasa, Langchain and FastAPI”
