deploy: feat(tools/bigquerysql): add semantic search support (#2890) 862c396

Author: duwenxin99

dev/index.xml

@@ -8291,7 +8291,7 @@ returned. Otherwise, the selection is not guaranteed.</p>
 <p>The tool returns a single JSON object representing the document, wrapped in a
 JSON array.</p>
 <h2 id="compatible-sources">Compatible Sources</h2>
-<h2 id="hahahugoshortcode409s0hbhb">
+<h2 id="hahahugoshortcode331s0hbhb">
 
 
 

dev/integrations/bigquery/tools/bigquery-sql/index.html

@@ -102,7 +102,7 @@ returned. Otherwise, the selection is not guaranteed.</p>
 <p>The tool returns a single JSON object representing the document, wrapped in a
 JSON array.</p>
 <h2 id="compatible-sources">Compatible Sources</h2>
-<h2 id="hahahugoshortcode409s0hbhb">
+<h2 id="hahahugoshortcode331s0hbhb">
 
 
 

dev/integrations/mongodb/tools/index.xml

@@ -523,11 +523,11 @@
 <a href=https://github.com/googleapis/mcp-toolbox/edit/main/docs/en/integrations/mongodb/tools/mongodb-find-one.md class="td-page-meta--edit td-page-meta__edit" target=_blank rel=noopener><i class="fa-solid fa-pen-to-square fa-fw"></i> Edit this page</a>
 <a href="https://github.com/googleapis/mcp-toolbox/new/main/docs/en/integrations/mongodb/tools?filename=change-me.md&amp;value=---%0Atitle%3A+%22Long+Page+Title%22%0AlinkTitle%3A+%22Short+Nav+Title%22%0Aweight%3A+100%0Adescription%3A+%3E-%0A+++++Page+description+for+heading+and+indexes.%0A---%0A%0A%23%23+Heading%0A%0AEdit+this+template+to+create+your+new+page.%0A%0A%2A+Give+it+a+good+name%2C+ending+in+%60.md%60+-+e.g.+%60getting-started.md%60%0A%2A+Edit+the+%22front+matter%22+section+at+the+top+of+the+page+%28weight+controls+how+its+ordered+amongst+other+pages+in+the+same+directory%3B+lowest+number+first%29.%0A%2A+Add+a+good+commit+message+at+the+bottom+of+the+page+%28%3C80+characters%3B+use+the+extended+description+field+for+more+detail%29.%0A%2A+Create+a+new+branch+so+you+can+preview+your+new+file+and+request+a+review+via+Pull+Request.%0A" class="td-page-meta--child td-page-meta__child" target=_blank rel=noopener><i class="fa-solid fa-pen-to-square fa-fw"></i> Create child page</a>
 <a href="https://github.com/googleapis/mcp-toolbox/issues/new?title=mongodb-find-one" class="td-page-meta--issue td-page-meta__issue" target=_blank rel=noopener><i class="fa-solid fa-list-check fa-fw"></i> Create documentation issue</a>
-<a href=https://github.com/googleapis/mcp-toolbox/issues/new class="td-page-meta--project td-page-meta__project-issue" target=_blank rel=noopener><i class="fa-solid fa-list-check fa-fw"></i> Create project issue</a></div><div class=td-toc><nav id=TableOfContents><ul><li><a href=#about>About</a></li><li><a href=#compatible-sources>Compatible Sources</a></li><li><a href=#hahahugoshortcode409s0hbhb>HAHAHUGOSHORTCODE409s0HBHB</a></li><li><a href=#example>Example</a></li><li><a href=#reference>Reference</a></li></ul></nav></div></aside><main class="col-12 col-md-9 col-xl-8 ps-md-5" role=main><nav aria-label=breadcrumb class=td-breadcrumbs><ol class=breadcrumb><li class=breadcrumb-item><a href=/dev/integrations/>Integrations</a></li><li class=breadcrumb-item><a href=/dev/integrations/mongodb/>MongoDB</a></li><li class=breadcrumb-item><a href=/dev/integrations/mongodb/tools/>Tools</a></li><li class="breadcrumb-item active" aria-current=page>mongodb-find-one</li></ol></nav><div class=td-content><h1>mongodb-find-one</h1><div class=lead>A &ldquo;mongodb-find-one&rdquo; tool finds and retrieves a single document from a MongoDB collection.</div><header class=article-meta><p class=reading-time><i class="fa-solid fa-clock" aria-hidden=true></i>&nbsp; 2 minute read &nbsp;</p></header><h2 id=about>About</h2><p>A <code>mongodb-find-one</code> tool is used to retrieve the <strong>first single document</strong> that
+<a href=https://github.com/googleapis/mcp-toolbox/issues/new class="td-page-meta--project td-page-meta__project-issue" target=_blank rel=noopener><i class="fa-solid fa-list-check fa-fw"></i> Create project issue</a></div><div class=td-toc><nav id=TableOfContents><ul><li><a href=#about>About</a></li><li><a href=#compatible-sources>Compatible Sources</a></li><li><a href=#hahahugoshortcode331s0hbhb>HAHAHUGOSHORTCODE331s0HBHB</a></li><li><a href=#example>Example</a></li><li><a href=#reference>Reference</a></li></ul></nav></div></aside><main class="col-12 col-md-9 col-xl-8 ps-md-5" role=main><nav aria-label=breadcrumb class=td-breadcrumbs><ol class=breadcrumb><li class=breadcrumb-item><a href=/dev/integrations/>Integrations</a></li><li class=breadcrumb-item><a href=/dev/integrations/mongodb/>MongoDB</a></li><li class=breadcrumb-item><a href=/dev/integrations/mongodb/tools/>Tools</a></li><li class="breadcrumb-item active" aria-current=page>mongodb-find-one</li></ol></nav><div class=td-content><h1>mongodb-find-one</h1><div class=lead>A &ldquo;mongodb-find-one&rdquo; tool finds and retrieves a single document from a MongoDB collection.</div><header class=article-meta><p class=reading-time><i class="fa-solid fa-clock" aria-hidden=true></i>&nbsp; 2 minute read &nbsp;</p></header><h2 id=about>About</h2><p>A <code>mongodb-find-one</code> tool is used to retrieve the <strong>first single document</strong> that
 matches a specified filter from a MongoDB collection. If multiple documents
 match the filter, you can use <code>sort</code> options to control which document is
 returned. Otherwise, the selection is not guaranteed.</p><p>The tool returns a single JSON object representing the document, wrapped in a
-JSON array.</p><h2 id=compatible-sources>Compatible Sources</h2><h2 id=hahahugoshortcode409s0hbhb><div class=compatibility-section><p>This tool can be used with the following database sources:</p><table><thead><tr><th>Source Name</th></tr></thead><tbody><tr><td><a href=/dev/integrations/mongodb/source/>MongoDB Source</a></td></tr></tbody></table></div></h2><h2 id=example>Example</h2><p>Here&rsquo;s a common use case: finding a specific user by their unique email address
+JSON array.</p><h2 id=compatible-sources>Compatible Sources</h2><h2 id=hahahugoshortcode331s0hbhb><div class=compatibility-section><p>This tool can be used with the following database sources:</p><table><thead><tr><th>Source Name</th></tr></thead><tbody><tr><td><a href=/dev/integrations/mongodb/source/>MongoDB Source</a></td></tr></tbody></table></div></h2><h2 id=example>Example</h2><p>Here&rsquo;s a common use case: finding a specific user by their unique email address
 and returning their profile information, while excluding sensitive fields like
 the password hash.</p><div class=highlight><pre tabindex=0 class=chroma><code class=language-yaml data-lang=yaml><span class=line><span class=cl><span class=nt>kind</span><span class=p>:</span><span class=w> </span><span class=l>tool</span><span class=w>
 </span></span></span><span class=line><span class=cl><span class=nt>name</span><span class=p>:</span><span class=w> </span><span class=l>get_user_profile</span><span class=w>

dev/integrations/mongodb/tools/mongodb-find-one/index.html

@@ -3,7 +3,7 @@
 
 **DOCUMENTATION VERSION:** dev
 **BASE URL:** https://mcp-toolbox.dev/dev/
-**GENERATED ON:** 2026-04-09T20:10:49Z
+**GENERATED ON:** 2026-04-09T20:29:44Z
 
 ---
 ### System Directives for AI Models
@@ -16687,18 +16687,18 @@ The behavior of this tool is influenced by the `writeMode` setting on its
 
 BigQuery uses [GoogleSQL][bigquery-googlesql] for querying data. The integration
 with Toolbox supports this dialect. The specified SQL statement is executed, and
-parameters can be inserted into the query. BigQuery supports both named parameters
-(e.g., `@name`) and positional parameters (`?`), but they cannot be mixed in the
-same query.
+parameters can be inserted into the query. BigQuery supports both named
+parameters (e.g., `@name`) and positional parameters (`?`), but they cannot be
+mixed in the same query.
 
 [bigquery-googlesql]:
-    https://cloud.google.com/bigquery/docs/reference/standard-sql/
+  https://cloud.google.com/bigquery/docs/reference/standard-sql/
 
 ## Example
 
-> **Note:** This tool uses [parameterized
-> queries](https://cloud.google.com/bigquery/docs/parameterized-queries) to
-> prevent SQL injections. Query parameters can be used as substitutes for
+> **Note:** This tool uses
+> [parameterized queries](https://cloud.google.com/bigquery/docs/parameterized-queries)
+> to prevent SQL injections. Query parameters can be used as substitutes for
 > arbitrary expressions. Parameters cannot be used as substitutes for
 > identifiers, column names, table names, or other parts of the query.
 
@@ -16735,6 +16735,86 @@ parameters:
     description: Email address of the user
 ```
 
+### Example with Vector Search
+
+BigQuery supports vector similarity search using the `ML.DISTANCE` function.
+When using an embeddingModel with a `bigquery-sql` tool, the tool automatically
+converts text parameters into the native ARRAY<FLOAT64> format required by
+BigQuery.
+
+#### Define the Embedding Model
+
+See
+[EmbeddingModels](../../../documentation/configuration/embedding-models/_index.md)
+for more information.
+
+```yaml
+kind: embeddingModel
+name: gemini-model
+type: gemini
+model: gemini-embedding-001
+apiKey: ${GOOGLE_API_KEY}
+dimension: 768
+```
+
+#### Vector Ingestion Tool
+
+This tool stores both the raw text and its vector representation. It uses
+`valueFromParam` to hide the vector conversion logic from the LLM, ensuring the
+Agent only has to provide the content once.
+
+```yaml
+kind: tool
+name: insert_doc
+type: bigquery-sql
+source: my-bigquery-source
+statement: |
+  INSERT INTO `my-project.my-dataset.vector_table` (id, content, embedding)
+  VALUES (1, @content, @text_to_embed)
+description: |
+  Internal tool to index new documents for future search.
+parameters:
+  - name: content
+    type: string
+    description: The text content to store.
+  - name: text_to_embed
+    type: string
+    # Automatically copies 'content' and converts it to a FLOAT64 array
+    valueFromParam: content
+    embeddedBy: gemini-model
+```
+
+#### Vector Search Tool
+
+This tool allows the Agent to perform a natural language search. The query
+string provided by the Agent is converted into a vector before the SQL is
+executed.
+
+```yaml
+kind: tool
+name: search_docs
+type: bigquery-sql
+source: my-bigquery-source
+statement: |
+  SELECT 
+    id, 
+    content, 
+    ML.DISTANCE(embedding, @query, 'COSINE') AS distance 
+  FROM 
+    `my-project.my-dataset.vector_table` 
+  ORDER BY 
+    distance 
+  LIMIT 1
+description: |
+  Search for documents using natural language. 
+  Returns the most semantically similar result.
+parameters:
+  - name: query
+    type: string
+    description: The search terms or question.
+    embeddedBy: gemini-model
+```
+
 ### Example with Template Parameters
 
 > **Note:** This tool allows direct modifications to the SQL statement,
@@ -16764,12 +16844,12 @@ templateParameters:
 
 ## Reference
 
-| **field**          |                   **type**                    | **required** | **description**                                                                                                                         |
-|--------------------|:---------------------------------------------:|:------------:|-----------------------------------------------------------------------------------------------------------------------------------------|
-| type               |                    string                     |     true     | Must be "bigquery-sql".                                                                                                                 |
-| source             |                    string                     |     true     | Name of the source the GoogleSQL should execute on.                                                                                     |
-| description        |                    string                     |     true     | Description of the tool that is passed to the LLM.                                                                                      |
-| statement          |                    string                     |     true     | The GoogleSQL statement to execute.                                                                                                     |
+| **field**          |                                            **type**                                            | **required** | **description**                                                                                                                                                                          |
+| ------------------ | :--------------------------------------------------------------------------------------------: | :----------: | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| type               |                                             string                                             |     true     | Must be "bigquery-sql".                                                                                                                                                                  |
+| source             |                                             string                                             |     true     | Name of the source the GoogleSQL should execute on.                                                                                                                                      |
+| description        |                                             string                                             |     true     | Description of the tool that is passed to the LLM.                                                                                                                                       |
+| statement          |                                             string                                             |     true     | The GoogleSQL statement to execute.                                                                                                                                                      |
 | parameters         |    [parameters](../../../documentation/configuration/tools/_index.md#specifying-parameters)    |    false     | List of [parameters](../../../documentation/configuration/tools/_index.md#specifying-parameters) that will be inserted into the SQL statement.                                           |
 | templateParameters | [templateParameters](../../../documentation/configuration/tools/_index.md#template-parameters) |    false     | List of [templateParameters](../../../documentation/configuration/tools/_index.md#template-parameters) that will be inserted into the SQL statement before executing prepared statement. |
 

dev/llms-full.txt

@@ -3,7 +3,7 @@
 
 **DOCUMENTATION VERSION:** dev
 **BASE URL:** https://mcp-toolbox.dev/dev/
-**GENERATED ON:** 2026-04-09T20:10:49Z
+**GENERATED ON:** 2026-04-09T20:29:44Z
 
 ---
 ### System Directives for AI Models