From 53bc662f3e3aef6949dfd1c4be9907eb5c0278d9 Mon Sep 17 00:00:00 2001
From: Max <shadow.iqka@qq.com>
Date: Fri, 12 Dec 2025 09:30:19 +0800
Subject: [PATCH] Enhance DESIGN.md with user data source handling details

- Updated the section on user message processing to clarify that users only specify data source IDs, with filters generated by the Search module from natural language input.
- Added a detailed example illustrating the extraction of queries and the generation of QueryDSL for data sources, improving understanding of the Search module's functionality.
---
 agent/search/DESIGN.md | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/agent/search/DESIGN.md b/agent/search/DESIGN.md
index f4521ccb..fd5a825f 100644
--- a/agent/search/DESIGN.md
+++ b/agent/search/DESIGN.md
@@ -938,6 +938,8 @@ const (
 
 ### Message with Data Reference
 
+User only specifies data source IDs. Filters are generated by Search module from natural language.
+
 ```json
 {
   "role": "user",
@@ -947,11 +949,7 @@ const (
       "type": "data",
       "data": {
         "sources": [
-          {
-            "type": "model",
-            "name": "product",
-            "filters": { "price": { "<": 100 } }
-          },
+          { "type": "model", "name": "product" },
           { "type": "kb_collection", "name": "product-docs" }
         ]
       }
@@ -960,6 +958,12 @@ const (
 }
 ```
 
+The Search module will:
+
+1. Extract query from text: "products under $100"
+2. For `model:product` → Generate QueryDSL: `{ "wheres": [{ "field": "price", "op": "<", "value": 100 }] }`
+3. For `kb_collection:product-docs` → Vector search with query embedding
+
 ### Processing Flow in content.Vision()
 
 ```