Haystack Blog
haystack.deepset.ai · Company blog · on HN since 2021
The blog of deepset's Haystack, an open source framework for building LLM pipelines, RAG, and AI agents.
What HN saysHN commenters mention it mostly because another project shares the Haystack name, which they say causes confusion and a namespace conflict with this active framework.
22HN people shared it
16linked it in comments
18stories submitted
39story points
4 months agolast shared
2021people per year2026
Most-shared posts
- 1Haystack: Open-Source AI Framework for Production Ready Agents, RAG14 people · 4 points · first shared 2022 · 1 comments on HN
- 2Blog2 people · first shared 2023
- 3Tutorials2 people · first shared 2023
- 422 pipeline with promptnode2 people · first shared 2023
- 5Haystack 2.0 – compound LLM pipelines are here1 people · 11 points · first shared 2024 · 4 comments on HN
- 6Evaluating different LLM-based approaches to text-to-SQL1 people · 3 points · first shared 2024 · discussion on HN
- 7What's the difference between generative and extractive models1 people · 3 points · first shared 2023 · discussion on HN
- 8Haystack 1.18: Share and use LLM prompts with PromptHub1 people · 3 points · first shared 2023 · discussion on HN
- 9Haystack 3.0: Agents with hooks, skills, and built-in introspection1 people · 3 points · first shared 2026 · discussion on HN
- 10Improving retrieval with automated metadata extraction1 people · 2 points · first shared 2024 · discussion on HN
- 11Show HN: Scale Haystack Pipelines Seamlessly with Ray Serve1 people · 2 points · first shared 2023 · discussion on HN
- 12Introducing Agents in Haystack: Make LLMs resolve complex tasks1 people · 2 points · first shared 2023 · discussion on HN
- 13Show HN: How to Prevent Prompt Injections1 people · 2 points · first shared 2023 · discussion on HN
- 14Show HN: Memory Enables Conversational Agents in Haystack1 people · 1 points · first shared 2023 · discussion on HN
- 15Custom Rag Pipelines to Summarize Latest Hacker News Posts with Haystack 2.01 people · 1 points · first shared 2023 · discussion on HN
What HN people wrote when they linked it
luplex · 2026-05-19
Haystack is a popular Framework for building AI agents: https://haystack.deepset.ai/
joloooo · 2025-09-11
I immediately thought this was an update by Deepset and their Haystack framework. https://haystack.deepset.ai/
Just FYI.
Tepix · 2024-09-25
Did 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.
Der_Einzige · 2024-07-25
Namespace 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/
barefeg · 2024-04-29
I was confused for a bit but there is no relation to https://haystack.deepset.ai/
FranklinMaillot · 2023-11-01
I haven't tried any of them but there's semantic-kernel and autogen by Microsoft, and Haystack.
https://github.com/microsoft/semantic-kernel
https://github.com/microsoft/autogen
https://haystack.deepset.ai/
bilgeyucel · 2023-07-17
Website: https://haystack.deepset.ai/
Documentation: https://docs.haystack.deepset.ai/docs
stan_kirdey · 2023-07-08
there is an alternative that is production-grade - deepset haystack https://haystack.deepset.ai/
p.s. i am contributor so there could be bias
tuanacelik · 2023-05-12
Indeed this tutorial on Haystack is a good one as an example: https://haystack.deepset.ai/tutorials/22_pipeline_with_promptnode
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 for this step though. PS: There's some functionality in the PromptNode to make sure you don't exceed prompt limit.
xatalytic · 2023-01-05
I’ll shoot you a line. As it happens I just came across Haystack (6.5k stars on GitHub) which looks like an awesome stack for this class of work.
https://haystack.deepset.ai/
ukuina · 2024-07-26
I thought it was https://haystack.deepset.ai
aantti · 2023-05-05
Yes, Haystack is Apache 2.0 :) https://haystack.deepset.ai
zansara · 2023-11-22
Actually 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)
antti909 · 2023-04-04
Thanks for the spotlight :) We've spent quite a lot of time working on the Agents lately, and it's definitely a big focus. Couple of extra points to reflect on some of the comments here. It's quite straightforward to build a hybrid NLP backend with Haystack combining either hosted LLM (e.g., OpenAI or Cohere), or local, smaller Transformer models, or both. Agents add another level of control on top of that, as described in the article and in the comments. This provides more flexibility wrt bridging it to the relevant data and extract/generate accurate non-hallucinatory answers. Join our Discord too :) https://haystack.deepset.ai/community
bishes · 2023-03-12
I 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-search-engine…
tholor · 2021-09-03
Yep, 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