fix dead links and reword

rithin-pullela-aws · rithin-pullela-aws · commit 7aa8c519359d · 2025-09-30T15:31:01.000-07:00
Signed-off-by: rithin-pullela-aws &lt;rithinp@amazon.com&gt;
diff --git a/_query-dsl/specialized/agentic.md b/_query-dsl/specialized/agentic.md
@@ -48,10 +48,10 @@ When executed, the agentic search request performs the following steps:
 3. The generated DSL query is executed as a search request in OpenSearch.
 4. Returns the search results based on the generated query.
 
-For a complete example, see [Agentic search]({{site.url}}{{site.baseurl}}/vector-search/ai-search/agentic-search/).
+For a complete example, see [Agentic search]({{site.url}}{{site.baseurl}}/vector-search/ai-search/agentic-search/index/).
 
 ## Next steps
 
-- Learn how to set up agentic search in [Agentic search]({{site.url}}{{site.baseurl}}/vector-search/ai-search/agentic-search/).
+- Learn how to set up agentic search in [Agentic search]({{site.url}}{{site.baseurl}}/vector-search/ai-search/agentic-search/index/).
 - Learn about configuring agents in [Agents]({{site.url}}{{site.baseurl}}/ml-commons-plugin/agents-tools/agents/).
 - Learn about the [QueryPlanningTool]({{site.url}}{{site.baseurl}}/ml-commons-plugin/agents-tools/tools/query-planning-tool/).
diff --git a/_search-plugins/search-pipelines/agentic-context-processor.md b/_search-plugins/search-pipelines/agentic-context-processor.md
@@ -98,6 +98,6 @@ The response contains the steps taken by the agent to translate the query, the m
 
 ## Related pages
 
-- [Agentic search queries]({{site.url}}{{site.baseurl}}/vector-search/ai-search/agentic-search)
+- [Agentic search queries]({{site.url}}{{site.baseurl}}/vector-search/ai-search/agentic-search/index/)
 - [Agents]({{site.url}}{{site.baseurl}}/ml-commons-plugin/agents-tools/agents/index/)
 - [Agentic query translator processor]({{site.url}}{{site.baseurl}}/search-plugins/search-pipelines/agentic-query-translator-processor/)
diff --git a/_search-plugins/search-pipelines/agentic-query-translator-processor.md b/_search-plugins/search-pipelines/agentic-query-translator-processor.md
@@ -127,6 +127,6 @@ The response contains the matching documents:
 
 ## Related pages
 
-- [Agentic search queries]({{site.url}}{{site.baseurl}}/vector-search/ai-search/agentic-search)
+- [Agentic search queries]({{site.url}}{{site.baseurl}}/vector-search/ai-search/agentic-search/index/)
 - [Agents]({{site.url}}{{site.baseurl}}/ml-commons-plugin/agents-tools/agents/index/)
 - [Agentic context processor]({{site.url}}{{site.baseurl}}/search-plugins/search-pipelines/agentic-context-processor/)
diff --git a/_vector-search/ai-search/agentic-search/agent-converse.md b/_vector-search/ai-search/agentic-search/agent-converse.md
@@ -13,7 +13,7 @@ Enable monitoring and conversation continuation using the `agentic_context` resp
 
 ## Prerequisites
 
-- An agent is registered and configured as descrived in [Agent customization]({{site.url}}{{site.baseurl}}/vector-search/ai-search/agentic-search/agent-customization/#complete-agent-configuration)
+- An agent is registered and configured as described in [Agent customization]({{site.url}}{{site.baseurl}}/vector-search/ai-search/agentic-search/agent-customization/)
 - The agent includes the QueryPlanningTool
 
 ## Setup: Create Search Pipeline
@@ -91,8 +91,8 @@ GET /_search?search_pipeline=agentic-pipeline
 
 ### Prerequisites: Register Models
 
-1. **[Register a model for the Agent]({{site.url}}{{site.baseurl}}/vector-search/ai-search/agentic-search/#step-4-create-a-model-for-conversational-agent)** - This model will be used by the conversational agent for reasoning and tool orchestration
-2. **[Register a model for Query Planning Tool]({{site.url}}{{site.baseurl}}/vector-search/ai-search/agentic-search/#step-3-create-a-model-for-query-planning-tool)** - This model will be used specifically by the QueryPlanningTool to generate OpenSearch DSL queries
+1. **[Register a model for the Agent]({{site.url}}{{site.baseurl}}/vector-search/ai-search/agentic-search/index/#step-4-create-a-model-for-conversational-agent)** - This model will be used by the conversational agent for reasoning and tool orchestration
+2. **[Register a model for Query Planning Tool]({{site.url}}{{site.baseurl}}/vector-search/ai-search/agentic-search/index/#step-3-create-a-model-for-query-planning-tool)** - This model will be used specifically by the QueryPlanningTool to generate OpenSearch DSL queries
 
 ### 1. Create product index
 
diff --git a/_vector-search/ai-search/agentic-search/agent-customization.md b/_vector-search/ai-search/agentic-search/agent-customization.md
@@ -118,19 +118,17 @@ POST /_plugins/_ml/connectors/_create
 
 ## Tool orchestration
 
-### Essential tools for intelligent search
-
-#### QueryPlanningTool (Required)
+### QueryPlanningTool (Required)
 
 The [`QueryPlanningTool`]({{site.url}}{{site.baseurl}}/ml-commons-plugin/agents-tools/tools/query-planning-tool/) is mandatory for agentic search functionality. It translates natural language queries into OpenSearch DSL.
 
-#### Additional tools
+### Additional tools
 
 You can add any tools from the [ML Commons Tools documentation]({{site.url}}{{site.baseurl}}/ml-commons-plugin/agents-tools/tools/index/) to enhance your agent's capabilities. 
 
 The conversational agent will automatically select and orchestrate the appropriate tools based on the query context.
 
-**Complete agent configuration:** {#complete-agent-configuration}
+#### Complete agent configuration
 
 ```json
 POST /_plugins/_ml/agents/_register
diff --git a/_vector-search/ai-search/agentic-search/flow-agent.md b/_vector-search/ai-search/agentic-search/flow-agent.md
@@ -98,7 +98,7 @@ GET products-index/_search?search_pipeline=agentic-pipeline
 **Key differences for flow agents:**
 - **Must specify index name**: Unlike conversational agents, you must include the index name in the URL path
 - **No memory_id**: Flow agents don't support conversation memory, so you cannot use `memory_id` parameter
-- **Simplified response**: No `agent_steps_summary` or detailed reasoning in the response
+- **Limited response details**: No `agent_steps_summary` or detailed reasoning in the response
 
 **Example response:**
 ```json
diff --git a/_vector-search/ai-search/agentic-search/neural-search.md b/_vector-search/ai-search/agentic-search/neural-search.md
@@ -141,8 +141,8 @@ POST /_bulk
 
 Register two models as described in the [Agentic Search setup]({{site.url}}{{site.baseurl}}/vector-search/ai-search/agentic-search/index/):
 
-1. **[Register a model for the Agent]({{site.url}}{{site.baseurl}}/vector-search/ai-search/agentic-search/#step-4-create-a-model-for-conversational-agent)**
-2. **[Register a model for Query Planning Tool]({{site.url}}{{site.baseurl}}/vector-search/ai-search/agentic-search/#step-3-create-a-model-for-query-planning-tool)**
+1. **[Register a model for the Agent]({{site.url}}{{site.baseurl}}/vector-search/ai-search/agentic-search/index/#step-4-create-a-model-for-conversational-agent)**
+2. **[Register a model for Query Planning Tool]({{site.url}}{{site.baseurl}}/vector-search/ai-search/agentic-search/index/#step-3-create-a-model-for-query-planning-tool)**
 
 ### Step 6: Create Agent with Embedding Model ID
 
diff --git a/_vector-search/ai-search/agentic-search/search-templates.md b/_vector-search/ai-search/agentic-search/search-templates.md
@@ -157,7 +157,7 @@ POST /_scripts/store_sum_skus
             "m": {
               "bucket_script": {
                 "buckets_path": { "x": "i>f>q" },
-                "script": { "source": "params.x >= {{min}}{{^min}}10{{/min}} ? 1 : 0" }
+                "script": { "source": "{% raw %}params.x >= {{min}}{{^min}}10{{/min}} ? 1 : 0{% endraw %}" }
               }
             }
           }
@@ -170,14 +170,12 @@ POST /_scripts/store_sum_skus
 ```
 {% include copy-curl.html %}
 
-### Step 5: Register Query Planner Tool with Search Templates
+### Step 5: Register Agent with Query Planner Tool (with Search Templates)
 
 Refer to these to register query planner model and the agent model:
 
 - [Create a model for Query Planning tool]({{site.url}}{{site.baseurl}}/vector-search/ai-search/agentic-search/index/#step-3-create-a-model-for-query-planning-tool)
 - [Create a Model for Conversational Agent]({{site.url}}{{site.baseurl}}/vector-search/ai-search/agentic-search/index/#step-4-create-a-model-for-conversational-agent)
-- [Create an Agent]({{site.url}}{{site.baseurl}}/vector-search/ai-search/agentic-search/index/#step-5-create-an-agent)
-- [Create a search pipeline]({{site.url}}{{site.baseurl}}/vector-search/ai-search/agentic-search/index/#step-6-create-a-search-pipeline)
 
 ```json
 {
@@ -296,16 +294,7 @@ POST /stores/_search?search_pipeline=my_pipeline
 }
 ```
 
-This error demonstrates that the LLM struggled to generate a valid query for this complex scenario. The failure occurred because:
-
-- The query involves nested aggregations with multiple SKUs
-- Complex filtering logic across inventory arrays
-- Script-based calculations with type handling
-
-LLMs often encounter issues with:
-- Incorrect `_source` iteration patterns
-- Misuse of `doc` values in scripts
-- Type mismatches causing runtime `script_exception` errors
+This error demonstrates that the LLM struggled to generate a valid query for this complex scenario. The failure occurred because the query involves advanced features like scripts and complex aggregations that are difficult for LLMs to generate correctly.
 
 Let's now demonstrate how search templates solve this problem:
 
