Add tutorial for agentic search #4127

mingshl · 2025-08-20T19:58:15Z

Description

Add tutorial for agentic search

Related Issues

Resolves #[Issue number to be closed when this PR is merged]

Check List

New functionality includes testing.
New functionality has been documented.
API changes companion pull request created.
Commits are signed per the DCO using --signoff.
Public documentation issue/PR created.

By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
For more information on following Developer Certificate of Origin and signing off your commits, please check here.

Signed-off-by: Mingshi Liu <[email protected]>

dhrubo-os · 2025-08-20T20:24:38Z

Approved without reviewing to unblock.

docs/tutorials/agentic_search/agentic_search_llm_generated_type.md

rithin-pullela-aws · 2025-08-20T20:45:33Z

docs/tutorials/agentic_search/agentic_search_llm_generated_type.md

+This is an experimental feature and is not recommended for use in a production environment. For updates on the progress of the feature or if you want to leave feedback, join the discussion on the [OpenSearch forum](https://forum.opensearch.org/).
+{: .warning}
+
+Agentic Search is a new query type proposed in OpenSearch that triggers an agent-driven workflow for query understanding, planning and execution. Instead of hand-crafting DSL, you supply a natural language question and an agent id; the agent executes a Query Planning Toolwith index/mapping introspection, and guide LLMs to produce OpenSearch DSL and run it through agentic query clause and return the search hits based on it.


Nit:
add space at Toolwith
In this part an agent-driven workflow for query understanding, looks like we are suggesting we give an explanation to the query, maybe reword a little?

added space for formatting, and query understanding is terminology in search, check this https://en.wikipedia.org/wiki/Query_understanding

docs/tutorials/agentic_search/agentic_search_llm_generated_type.md

Zhangxunmt · 2025-08-20T20:50:42Z

docs/tutorials/agentic_search/agentic_search_llm_generated_type.md

+     "request_processors": [
+        {
+            "agentic_query_translator": {
+                "agent_id": "your_agent_id"


If this processor takes a model_id and implements the tools logics inside the processor, so we can get rid of the agent steps 4 and 5? We can implement a default agent inside this processor to simplify?

we don't have default agent for now, but we will consider about it

Signed-off-by: Mingshi Liu <[email protected]>

ylwu-amzn · 2025-08-20T20:14:21Z

docs/tutorials/agentic_search/agentic_search_llm_generated_type.md

@@ -0,0 +1,685 @@
+---
+layout: default
+title: Agentic search with a llmGenerated query type


Can we tune the title ?

I would try to open new PR for remaining comments, let's merge for unblocking the release blog.

changed the title in the new PR #4128

please move the discussion to the following PR , thanks

codecov · 2025-08-20T22:04:41Z

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 81.65%. Comparing base (984b13a) to head (798a936).
⚠️ Report is 1 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff            @@
##               main    #4127   +/-   ##
=========================================
  Coverage     81.64%   81.65%           
  Complexity     8830     8830           
=========================================
  Files           761      761           
  Lines         38099    38099           
  Branches       4250     4250           
=========================================
+ Hits          31107    31110    +3     
+ Misses         5166     5163    -3     
  Partials       1826     1826

Flag	Coverage Δ
ml-commons	`81.65% <ø> (+<0.01%)`	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

add tutorial for agentic search

3845d9a

Signed-off-by: Mingshi Liu <[email protected]>

mingshl marked this pull request as ready for review August 20, 2025 19:58

mingshl requested review from b4sjoo, dhrubo-os, jngz-es, model-collapse, rbhavna, ylwu-amzn, zane-neo, Zhangxunmt, austintlee, HenryL27 and xinyual as code owners August 20, 2025 19:58

mingshl temporarily deployed to ml-commons-cicd-env August 20, 2025 19:59 — with GitHub Actions Inactive

dhrubo-os previously approved these changes Aug 20, 2025

View reviewed changes

owaiskazi19 reviewed Aug 20, 2025

View reviewed changes