fix in comments

Signed-off-by: xieydd <[email protected]>

Author: xieydd

src/vectorchord/getting-started/vectorchord-suite.md

@@ -16,14 +16,17 @@ The suite comprises three key PostgreSQL extensions working in concert:
 
 2. [**VectorChord-bm25:**](https://github.com/tensorchord/VectorChord-bm25) This extension implements the sophisticated BM25 ranking algorithm directly inside PostgreSQL, leveraging efficient Block-WeakAnd algorithms. BM25 is a standard for relevance ranking based on keyword frequency and document characteristics.
 
-3. [**pg\_**](https://github.com/tensorchord/pg_tokenizer.rs)[**tokenizer.rs**](http://tokenizer.rs)[**:**](https://github.com/tensorchord/pg_tokenizer.rs) Provides essential text tokenization capabilities needed for effective full-text search, enabling fine-grained control over how text is processed for full-text search.
+3. [**pg_tokenizer.rs:**](https://github.com/tensorchord/pg_tokenizer.rs) Provides essential text tokenization capabilities needed for effective full-text search, enabling fine-grained control over how text is processed for full-text search.
 
 
 By combining these extensions, you unlock powerful capabilities for building advanced RAG systems entirely within PostgreSQL.
 
 ## How to Use the VectorChord Suite
 
 You can use the `tensorchord/vchord-suite` Docker image to run multiple extensions which are provided by TensorChord. The image is based on the Docker official PostgreSQL image and includes the following extensions:
+- `vchord`
+- `pg_tokenizer` 
+- `vchord_bm25`
 
 ```powershell
 docker run   \           

src/vectorchord/index.md

@@ -4,19 +4,21 @@
 
 - [Overview](/vectorchord/getting-started/overview)
 - [Installation](/vectorchord/getting-started/installation)
+- [VectorChord Suite](/vectorchord/getting-started/vectorchord-suite)
 
 ## Usage
 
 - [Indexing](/vectorchord/usage/indexing)
 - [Indexing with MaxSim Operators](/vectorchord/usage/indexing-with-maxsim-operators)
 - [Search](/vectorchord/usage/search)
-- [Advanced Features](/vectorchord/usage/advanced-features)
 - [Performance Tuning](/vectorchord/usage/performance-tuning)
+- [Advanced Features](/vectorchord/usage/advanced-features)
 
 ## Use Cases
 
 - [Hybrid Search](/vectorchord/use-case/hybrid-search)
 - [ColBERT Rerank](/vectorchord/use-case/colbert-rerank)
+- [ColQwen2 & Modal](/vectorchord/use-case/colqwen2-modal)
 
 ## Admin
 

src/vectorchord/usage/indexing.md

@@ -82,7 +82,7 @@ The following parameters are available:
     - `build.internal.lists = []` means that the vector space is not partitioned.
     - `build.internal.lists = [4096]` means the vector space is divided into $4096$ cells.
     - `build.internal.lists = [4096, 262144]` means the vector space is divided into $4096$ cells, and those cells are further divided into $262144$ smaller cells.
-- Note: The index partitions the vector space into multiple Voronoi cells using centroids, iteratively creating a hierarchical space partition tree. Each leaf node in this tree represents a region with an associated list storing vectors in that region. During insertion, vectors are placed in lists corresponding to their appropriate leaf nodes. For queries, the index optimizes search by excluding lists whose leaf nodes are distant from the query vector, effectively pruning the search space. The `lists` option should be no less than $4 * \sqrt{N}$, where $N$ is the number of vectors in the table. 
+- Note: The index partitions the vector space into multiple Voronoi cells using centroids, iteratively creating a hierarchical space partition tree. Each leaf node in this tree represents a region with an associated list storing vectors in that region. During insertion, vectors are placed in lists corresponding to their appropriate leaf nodes. For queries, the index optimizes search by excluding lists whose leaf nodes are distant from the query vector, effectively pruning the search space. If the length of `lists` is 1,the `lists` option should be no less than $4 * \sqrt{N}$, where $N$ is the number of vectors in the table.
 
 #### `build.internal.spherical_centroids`
 

src/vectorchord/usage/search.md

@@ -28,12 +28,15 @@ SELECT 1 FROM items WHERE category_id = 1 ORDER BY embedding <#> '[0.5,0.5,0.5]'
 #### `vchordrq.probes`
 
 - Description: This GUC parameter `vchordrq.probes` controls how the vector space assists in query pruning. The more probes, the more accurate the search, but also the slower it is.
-- Type: integer
-- Default: `empty`
+- Type: List of integers
+- Default: `[]`
 - Example:
     - `SET vchordrq.probes = 1` means that only one probe is used.
     - `SET vchordrq.probes = 10` means that ten probes are used.
-- Note: The default value is `empty`, which means that only one probe is used. This is the fastest search, but also the least accurate. If you want to improve the accuracy of the search, you can increase the number of probes. However, this will also slow down the search.
+- Note: The default value is an empty list. The length of this option must match the length of `lists`. 
+    - If `lists = []`, then probes must be an empty list.
+    - If `lists = [11, 22]`, then probes can be 2,4 or 4,8, but it must not be an empty list, `3`, `7,8,9`, or `5,5,5,5`.
+
 
 #### `vchordrq.epsilon`