🧪 Tools: experiment with different use cases

deepset-ai / haystack

:mag: AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.

https://haystack.deepset.ai

Apache License 2.0

16.94k stars 1.85k forks source link

🧪 Tools: experiment with different use cases #8281

Closed anakin87 closed 3 weeks ago

anakin87 commented 1 month ago

Now that the main building blocks are in place, we should play with different use cases

Goals:

figure out if all the components fit together well
understand if the UX is optimal
see if integrating components in a Pipeline is smooth (when it makes sense to do that, unsure about conversational scenarios)

anakin87 commented 4 weeks ago

WIP: https://www.notion.so/deepsetai/Tools-use-cases-WIP-358a2ccae52f49e38dccda713031925d?pvs=12

anakin87 commented 3 weeks ago

Unpolished notes in the aforementioned Notion page.

The work done on this topic resulted in the notebook of https://github.com/deepset-ai/haystack-experimental/pull/71.