Top all-time · #3362
Haystack
Company blog · haystack.deepset.ai/blogaiprogramming
Haystack is the company blog at haystack.deepset.ai, writing about ai and programming. Since 2021, 22 different Hacker News readers have linked it 40 times, most often “Haystack: Open-Source AI Framework for Production Ready Agents, RAG”. It is still writing: the last post was on 2026-10-07, and you can follow it by feed.
Too few sampled comments (21) to say how often HN recommends it.?
Why HN links it
HN readers link the Haystack site for its tutorials, docs and benchmarks on the deepset LLM framework, mainly as pointers to retrieval and pipeline examples. Many comments are about its name clashing with other projects.
Summarised by Claude from a sample of 21 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Create agentic, context engineered AI systems using Haystack’s modular and customizable building blocks, built for real-world, production-ready applications.
Most-linked posts?
- Haystack: Open-Source AI Framework for Production Ready Agents, RAG12 people · 12 mentions · first linked 2022-12-01
- /tutorials/22_pipeline_with_promptnode2 people · 3 mentions · first linked 2023-05-08
- /tutorials2 people · 2 mentions · first linked 2023-06-21
- /2 people · 2 mentions · first linked 2023-05-05
What Hacker News says?
I thought it was https://haystack.deepset.ai
Comment linking /
on “Show HN: Haystack – an IDE for exploring and editing code on an infinite canvas”Submitted Haystack 2.0 – compound LLM pipelines are here as a story · 11 points
HN discussionNamespace conflict, and yes it does matter. Just as "mamba" was an anaconda package manager re-implementation before it got commandeered by the LLM research crowd, now Haystack is being stolen away from Deepset: https://github.com/deepset-ai/haystack https://haystack.deepset.ai/
Comment linking /
on “Show HN: Haystack – an IDE for exploring and editing code on an infinite canvas”Submitted Haystack 3.0: Agents with hooks, skills, and built-in introspection as a story · 3 points
HN discussionDid you really have to pick the same name as the Haystack open source AI framework? https://haystack.deepset.ai/ https://github.com/deepset-ai/haystack It's a very active project and it's confusing to have two projects with the same name. Besides, I don't understand why you'd give a "2D digital whiteboard that automatically draws connections between code as you navigate and edit files" the name haystack.
Comment linking /
on “Launch HN: Haystack (YC S24) – Visualize and edit code on an infinite canvas”Submitted Evaluating different LLM-based approaches to text-to-SQL as a story · 3 points
HN discussionI immediately thought this was an update by Deepset and their Haystack framework. https://haystack.deepset.ai/ Just FYI.
Comment linking /
on “Show HN: Haystack – Review pull requests like you wrote them yourself”Submitted Haystack 1.18: Share and use LLM prompts with PromptHub as a story · 3 points
HN discussionIndeed this tutorial on Haystack is a good one as an example: https://haystack.deepset.ai/tutorials/22_pipeline_with_promp... It combines a retrieval step followed by a prompt layer which inserts the relevant context into the prompt. You can however change the 'retrieval step' with something that uses a proper embedding model and OpenAI also provides those if you want to. I tend to use lighter (cheaper) OSS models f…
Comment linking /tutorials/22_pipeline_with_promptnode
on “Anthropic - Introducing 100K Token Context Windows, Around 75,000 Words”Submitted Haystack: Open-Source AI Framework for Production Ready Agents, RAG as a story · 2 points
HN discussionYes, you can use a local embeddings model like gtr-t5-xl alongside retriever augmentation. This can point you in the right direction: https://haystack.deepset.ai/tutorials/22_pipeline_with_promp...
Comment linking /tutorials/22_pipeline_with_promptnode
on “Anthropic - Introducing 100K Token Context Windows, Around 75,000 Words”Submitted Improving retrieval with automated metadata extraction as a story · 2 points
HN discussionI was confused for a bit but there is no relation to https://haystack.deepset.ai/
Comment linking /
on “Haystack DB – 10x faster than FAISS with binary embeddings by default”Submitted Show HN: Scale Haystack Pipelines Seamlessly with Ray Serve as a story · 2 points
HN discussionThis should get you started: https://haystack.deepset.ai/tutorials/22_pipeline_with_promp...
Comment linking /tutorials/22_pipeline_with_promptnode
on “It looks like GPT-4-32k is rolling out”Submitted What's the difference between generative and extractive models as a story · 2 points
HN discussionthis and other different end-to-end architectures are offered in deepset/haystack, one of the best and quite mature frameworks to work with LLMs (pre-GPT craze) and do augmented retrieval, etc. I do feel the article presents old concepts as "emerging". if you are curious about building something quickly, you can jump into one of the tutorials https://haystack.deepset.ai/tutorials Over a weekend I've used deepset/hay…
Comment linking /tutorials
on “Emerging Architectures for LLM Applications”Submitted Introducing Agents in Haystack: Make LLMs resolve complex tasks as a story · 2 points
HN discussionYep, you want a GPU for many of the models. However, then subsecond queries are easy to achieve. See benchmarks: https://haystack.deepset.ai/benchmarks/latest
Comment linking /benchmarks/latest
on “Semantic Search for FAQs with Haystack”Submitted New multimodal Gemini embeddings from Google (videos and PDFs supported) as a story · 1 points
HN discussionthere is an alternative that is production-grade - deepset haystack https://haystack.deepset.ai/ p.s. i am contributor so there could be bias
Comment linking /
on “Langchain Is Pointless”Submitted Custom Rag Pipelines to Summarize Latest Hacker News Posts with Haystack 2.0 as a story · 1 points
HN discussionI used Haystack due to the readily available colab notebook[1] for their tutorials. I wanted to feed my own text corpus to it, and that was the fastest way available. Langchain docs are helpful, and it would be even better if you published an end-to-end notebook using a popular dataset. Definitely looking forward to try langchain as I dive deeper into this. 1. https://haystack.deepset.ai/blog/how-to-build-a-semantic…
Comment linking /blog/how-to-build-a-semantic-search-engine-in-python
on “Large language models are having their Stable Diffusion moment”Submitted Show HN: Memory Enables Conversational Agents in Haystack as a story · 1 points
HN discussionWebsite: https://haystack.deepset.ai/ Documentation: https://docs.haystack.deepset.ai/docs
Comment linking /
on “Build with LLMs for production with Haystack – has 10k stars on GitHub”Submitted Show HN: The beginner's guide to LLM prompting as a story · 1 points
HN discussionYes, Haystack is Apache 2.0 :) https://haystack.deepset.ai
Comment linking /
on “Re-implementing LangChain in 100 lines of code”Submitted Generative vs. Extractive Language Models as a story · 1 points
HN discussionActually Haystack is very focused on RAG lately, just have a look at the latest blog articles: https://haystack.deepset.ai/blog (Disclaimer: I am a Haystack maintainer)
Comment linking /blog
on “Show HN: Neum AI – Open-source large-scale RAG framework”Submitted Show HN: What are prompt injections and how to prevent as a story · 1 points
HN discussion
