Docs confusing on using haystack-ai vs. farm-haystack

[pramodatre]

This is probably a very trivial issue and maybe I'm not looking at the right place. I could not work though the Agent examples in the docs by just installing haystack-ai which I believe is a newer version and the future development work happen here. I noticed that I have to use farm-haystack for using Agent as shown in this tutorial: https://haystack.deepset.ai/tutorials/24_building_chat_app

Here are some thoughts that will help someone like me:

1. Clarify the roles of haystack-ai and farm-haystack on the documentation landing page.
2. Release new work only in haystack-ai so that users don't have to use two dependencies that are incompatible.

I'm kind of stuck as I want to use Agent workflows and it's features but I cannot install farm-haystack into my project as I have already done development using haystack-ai.

Any suggestions to deal with these issues will be very helpful!

Thanks a lot in advance!

[julian-risch]

Hello @pramodatre Thank you for your feedback! I will check how we can update the documentation landing page and the tutorials to clarify that Haystack version 2.x, which is the haystack-ai package, is the way to go. The other package, farm-haystack, is Haystack version 1.x. They are not supposed to be used together and we strongly recommend to use Haystack 2.x only going forward.
Haystack 1.26 is the final minor release for Haystack 1.x and although we will continue to release bug fixes for this version, we will neither be adding nor removing any functionalities. Instead, we focus our efforts on Haystack 2.x. Haystack 1.26 will reach its end-of-life on March 11, 2025.
For your project, I suggest that you have a look at Agents with Haystack 2.x. For example, this cookbook: https://github.com/deepset-ai/haystack-cookbook/blob/main/notebooks/conversational_rag_using_memory.ipynb
and also our experimental features around tool calling https://colab.research.google.com/github/deepset-ai/haystack-cookbook/blob/main/notebooks/tools_support.ipynb
You can find a list of all experimental features here: https://github.com/deepset-ai/haystack-experimental?tab=readme-ov-file#active-experiments
We'd be very interested to hear your feedback on these features! Please let us know if Haystack is missing any particular features for your use cases. Thank you!

[pramodatre]

Thank you for your prompt reply and pointing in the right direction!
I'm also looking for standard Agent implementation like ReAct -- is there such an implementation in Haystack version 2.x like the one that I see in version 1.x? I want to confirm before building such well-known agents from the abstractions that are provided in Haystack.

[vblagoje]

@pramodatre ReAct is relatively easy in Haystack - have a look at https://github.com/vblagoje/notebooks/blob/main/haystack2x-demos/ReAct_Haystack.ipynb
Let us know if you have any questions 🙏

[pramodatre]

Thanks a lot for sharing this! Very helpful!