tidbcloud: Add auto embedding docs

TOC-tidb-cloud.md

@@ -216,8 +216,8 @@
     - [TiKV Follower Read](/follower-read.md)
     - [Coprocessor Cache](/coprocessor-cache.md)
     - Garbage Collection (GC)
-       - [Overview](/garbage-collection-overview.md)
-       - [Configuration](/garbage-collection-configuration.md)
+      - [Overview](/garbage-collection-overview.md)
+      - [Configuration](/garbage-collection-configuration.md)
     - [Tune TiFlash Performance](/tiflash/tune-tiflash-performance.md)
   - Optimize Resource Allocation
     - Resource Manager
@@ -258,6 +258,15 @@
   - Get Started
     - [Get Started with SQL](/vector-search/vector-search-get-started-using-sql.md)
     - [Get Started with Python](/vector-search/vector-search-get-started-using-python.md)
+  - Auto Embedding
+    - [Overview](/tidb-cloud/vector-search-auto-embedding-overview.md)
+    - [Amazon Titan Embeddings](/tidb-cloud/vector-search-auto-embedding-amazon-titan.md)
+    - [Cohere Embeddings](/tidb-cloud/vector-search-auto-embedding-cohere.md)
+    - [Jina AI Embeddings](/tidb-cloud/vector-search-auto-embedding-jina-ai.md)
+    - [OpenAI Embeddings](/tidb-cloud/vector-search-auto-embedding-openai.md)
+    - [Gemini Embeddings](/tidb-cloud/vector-search-auto-embedding-gemini.md)
+    - [HuggingFace Embeddings](/tidb-cloud/vector-search-auto-embedding-huggingface.md)
+    - [NVIDIA NIM Embeddings](/tidb-cloud/vector-search-auto-embedding-nvidia-nim.md)
   - Integrations
     - [Overview](/vector-search/vector-search-integration-overview.md)
     - AI Frameworks
@@ -326,8 +335,8 @@
     - [Connect via VPC Peering](/tidb-cloud/set-up-vpc-peering-connections.md)
     - [TLS Connections to TiDB Cloud Dedicated](/tidb-cloud/tidb-cloud-tls-connect-to-dedicated.md)
   - Data Access Control
-      - [Encryption at Rest Using Customer-Managed Encryption Keys](/tidb-cloud/tidb-cloud-encrypt-cmek.md)
-      - [User-Controlled Log Redaction](/tidb-cloud/tidb-cloud-log-redaction.md)
+    - [Encryption at Rest Using Customer-Managed Encryption Keys](/tidb-cloud/tidb-cloud-encrypt-cmek.md)
+    - [User-Controlled Log Redaction](/tidb-cloud/tidb-cloud-log-redaction.md)
   - Database Access Control
     - [Configure Cluster Password Settings](/tidb-cloud/configure-security-settings.md)
   - Audit Management
@@ -673,8 +682,8 @@
   - [Use UUIDs](/best-practices/uuid.md)
   - [TiDB Accelerated Table Creation](/accelerated-table-creation.md)
   - [Schema Cache](/schema-cache.md)
-- API Reference ![BETA](/media/tidb-cloud/blank_transparent_placeholder.png)   
-  - [Overview](/tidb-cloud/api-overview.md) 
+- API Reference ![BETA](/media/tidb-cloud/blank_transparent_placeholder.png)
+  - [Overview](/tidb-cloud/api-overview.md)
   - v1beta1
     - [TiDB Cloud Starter and Essential](https://docs.pingcap.com/tidbcloud/api/v1beta1/serverless)
     - [TiDB Cloud Dedicated](https://docs.pingcap.com/tidbcloud/api/v1beta1/dedicated)
@@ -692,8 +701,8 @@
     - [TSO](/tso.md)
   - Storage Engines
     - TiKV
-        - [TiKV Overview](/tikv-overview.md)
-        - [RocksDB Overview](/storage-engine/rocksdb-overview.md)
+      - [TiKV Overview](/tikv-overview.md)
+      - [RocksDB Overview](/storage-engine/rocksdb-overview.md)
     - TiFlash
       - [TiFlash Overview](/tiflash/tiflash-overview.md)
       - [Spill to Disk](/tiflash/tiflash-spill-disk.md)

tidb-cloud/vector-search-auto-embedding-amazon-titan.md

@@ -0,0 +1,139 @@
+---
+title: Amazon Titan Embeddings
+summary: Learn how to use Amazon Titan embedding models in TiDB Cloud.
+aliases: ["/tidb/stable/vector-search-auto-embedding-amazon-titan"]
+---
+
+# Amazon Titan Embeddings
+
+## Available Models
+
+TiDB Cloud provides the following [Amazon Titan embedding model](https://docs.aws.amazon.com/bedrock/latest/userguide/titan-embedding-models.html) natively. No API key required.
+
+**Amazon Titan Text Embedding V2 model**
+
+- Name: `tidbcloud_free/amazon/titan-embed-text-v2`
+- Dimensions: 1024 (default), 512, 256
+- Distance Metric: Cosine / L2
+- Languages – English (100+ languages in preview)
+- Supported use cases – RAG, document search, reranking, classification, etc.
+- Max input text tokens: 8,192
+- Max input text characters: 50,000
+- Price: Free
+- Hosted by TiDB Cloud: ✅
+- Bring Your Own Key: ❌
+
+For more details, see [its official documentation](https://docs.aws.amazon.com/bedrock/latest/userguide/titan-embedding-models.html).
+
+## Availability
+
+This feature is currently available in these regions and offerings:
+
+- Starter: AWS Frankfurt (eu-central-1)
+- Starter: AWS Oregon (us-west-2)
+- Starter: AWS N. Virginia (us-east-1)
+
+## SQL Usage Example
+
+```sql
+CREATE TABLE sample (
+  `id`        INT,
+  `content`   TEXT,
+  `embedding` VECTOR(1024) GENERATED ALWAYS AS (EMBED_TEXT(
+                "tidbcloud_free/amazon/titan-embed-text-v2",
+                `content`
+              )) STORED
+);
+
+
+INSERT INTO sample
+    (`id`, `content`)
+VALUES
+    (1, "Java: Object-oriented language for cross-platform development."),
+    (2, "Java coffee: Bold Indonesian beans with low acidity."),
+    (3, "Java island: Densely populated, home to Jakarta."),
+    (4, "Java's syntax is used in Android apps."),
+    (5, "Dark roast Java beans enhance espresso blends.");
+
+
+SELECT `id`, `content` FROM sample
+ORDER BY
+  VEC_EMBED_COSINE_DISTANCE(
+    embedding,
+    "How to start learning Java programming?"
+  )
+LIMIT 2;
+```
+
+Result:
+
+```
++------+----------------------------------------------------------------+
+| id   | content                                                        |
++------+----------------------------------------------------------------+
+|    1 | Java: Object-oriented language for cross-platform development. |
+|    4 | Java's syntax is used in Android apps.                         |
++------+----------------------------------------------------------------+
+```
+
+## Options
+
+You can specify additional options via the `additional_json_options` parameter of the `EMBED_TEXT()` function.
+
+- `normalize` – (optional) Flag indicating whether or not to normalize the output embedding. Defaults to true.
+- `dimensions` – (optional) The number of dimensions the output embedding should have. The following values are accepted: 1024 (default), 512, 256.
+
+**Example: Use alternative dimensions via `dimensions`**
+
+```sql
+CREATE TABLE sample (
+  `id`        INT,
+  `content`   TEXT,
+  `embedding` VECTOR(512) GENERATED ALWAYS AS (EMBED_TEXT(
+                "tidbcloud_free/amazon/titan-embed-text-v2",
+                `content`,
+                '{"dimensions": 512}'
+              )) STORED
+);
+
+
+INSERT INTO sample
+    (`id`, `content`)
+VALUES
+    (1, "Java: Object-oriented language for cross-platform development."),
+    (2, "Java coffee: Bold Indonesian beans with low acidity."),
+    (3, "Java island: Densely populated, home to Jakarta."),
+    (4, "Java's syntax is used in Android apps."),
+    (5, "Dark roast Java beans enhance espresso blends.");
+
+
+SELECT `id`, `content` FROM sample
+ORDER BY
+  VEC_EMBED_COSINE_DISTANCE(
+    embedding,
+    "How to start learning Java programming?"
+  )
+LIMIT 2;
+```
+
+Result:
+
+```
++------+----------------------------------------------------------------+
+| id   | content                                                        |
++------+----------------------------------------------------------------+
+|    1 | Java: Object-oriented language for cross-platform development. |
+|    4 | Java's syntax is used in Android apps.                         |
++------+----------------------------------------------------------------+
+```
+
+## Python Usage Example
+
+See [PyTiDB Documentation](https://pingcap.github.io/ai/guides/auto-embedding/).
+
+## See Also
+
+- [Auto Embedding Overview](/tidb-cloud/vector-search-auto-embedding-overview.md)
+- [Vector Search](/vector-search/vector-search-overview.md)
+- [Vector Functions and Operators](/vector-search/vector-search-functions-and-operators.md)
+- [Hybrid Search](/tidb-cloud/vector-search-hybrid-search.md)