elastic / elastic/docs-content

Search use cases section should be a concrete list of use cases and lead users to the correct project type/solution

Open
#8,262 4 comments 1 reaction 0 assignees View on GitHub
Confidence: 0.8 documentation Effort: 1 enhancement Impact: 3 Reach: 4 Team:Developer triaged weeks: 1
Dominant language
No language data
Stars
47
Forks
261
Avg merge
3d 12h
Merged PRs (30d)
116

Description

We now have 2 ES-centric solutions: the Elasticsearch solution, generic, and the Vector Database project type. In the narrative of the verctordb project type, we basically say this is the go-to solution for all vector-friendly use cases, including RAG and others.

Here is an extract from some of our communications:

> Vector Database or Elasticsearch?

> For anyone building applications leveraging vectors, or if the primary workload is semantic search, RAG, or agent retrieval, build on Vector Database. Elasticsearch remains the right choice for customers who need a data platform for multi-signal workloads, general-purpose search, and analytics. Both run the same engine, so either can be adopted at any time.

As such, the pages that we have that present these use cases should not only describe the use case and capabilities we have on our platform for this, but clearly lead users to the optimal path. I for example think of this page https://www.elastic.co/docs/solutions/search/rag that doesn't mention the vectordb project type while talking about a use case that this project type is designed for.

I understand there may be other existing plans with this section, but at this moment I'm mostly thinking about consolidating the vector database story.

Sorry if this duplicates something already in your plans :)

Contributor guide

No contributing guide indexed for this repository

Research direction

Start with the RAG documentation page at https://www.elastic.co/docs/solutions/search/rag and compare its use-case guidance with the Vector Database project type narrative. Update the relevant use-case pages so they describe the capabilities and clearly direct users to the appropriate Elasticsearch or Vector Database path; done means the vector database story is consistently represented.

Written by the indexing model from the issue text.

Assessment

Tech stack
elasticsearch
Domain
documentation
Issue type
Documentation
Difficulty
3/5
Estimated time
1-2 days
Activity status
Active
Clarity
Mostly clear
Newbie friendliness
68/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.