Improve technical accuracy and completeness of index_options documentation

Addresses feedback from issue #3804 by clarifying parameter references
and expanding quantization strategy documentation.

Changes:
- Add explicit int4_hnsw documentation with 8x memory reduction guidance
- Fix parameter reference: "model_settings.index_options" → "index_options"
- Clarify that index_options is configured directly on the semantic_text field
- Improve consistency across cross-references in dense-vector.md and knn.md

These refinements ensure users have accurate information about configuring
vector quantization strategies for semantic search.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

Author: ctindel

solutions/search/semantic-search/semantic-search-semantic-text.md

@@ -201,7 +201,7 @@ serverless: unavailable
 
 1. Use DiskBBQ for disk-based vector storage with minimal memory requirements. Available in Elasticsearch 9.2+. This option stores compressed vectors on disk, reducing RAM usage to as little as 100 MB while maintaining query latencies around 15ms.
 
-Other quantization options include `int8_hnsw` and `int4_hnsw`:
+Other quantization options include `int8_hnsw` (8-bit integer quantization) and `int4_hnsw` (4-bit integer quantization):
 
 ```console
 PUT semantic-embeddings-int8
@@ -222,7 +222,7 @@ PUT semantic-embeddings-int8
 }
 ```
 
-1. Use 8-bit integer quantization for 4x memory reduction with high accuracy retention.
+1. Use 8-bit integer quantization for 4x memory reduction with high accuracy retention. For 4-bit quantization, use `"type": "int4_hnsw"` instead, which provides 8x memory reduction.
 
 For HNSW-specific tuning parameters like `m` and `ef_construction`, you can include them in the `index_options`:
 

solutions/search/vector/dense-vector.md

@@ -48,5 +48,5 @@ Better Binary Quantization (BBQ) is an advanced vector quantization technique fo
 Learn more about how BBQ works, supported algorithms, and configuration examples in the [Better Binary Quantization (BBQ) documentation](https://www.elastic.co/docs/reference/elasticsearch/index-settings/bbq).
 
 ::::{tip}
-When using the [`semantic_text` field type](../semantic-search/semantic-search-semantic-text.md), you can configure BBQ and other quantization options through the `model_settings.index_options` parameter. See [Optimizing vector storage with `index_options`](../semantic-search/semantic-search-semantic-text.md#semantic-text-index-options) for examples of using `bbq_hnsw`, `int8_hnsw`, and other quantization strategies with semantic text fields.
+When using the [`semantic_text` field type](../semantic-search/semantic-search-semantic-text.md), you can configure BBQ and other quantization options through the `index_options` parameter. See [Optimizing vector storage with `index_options`](../semantic-search/semantic-search-semantic-text.md#semantic-text-index-options) for examples of using `bbq_hnsw`, `int8_hnsw`, and other quantization strategies with semantic text fields.
 ::::

solutions/search/vector/knn.md

@@ -137,7 +137,7 @@ For approximate kNN, {{es}} stores dense vector values per segment as an [HNSW g
 In addition to search-time parameters, HNSW exposes index-time settings that balance graph build cost, search speed, and accuracy. When defining your `dense_vector` mapping, use [`index_options`](elasticsearch://reference/elasticsearch/mapping-reference/dense-vector.md#dense-vector-index-options) to set these parameters.
 
 ::::{tip}
-When using the [`semantic_text` field type](../semantic-search/semantic-search-semantic-text.md) with dense vector embeddings, you can also configure `index_options` through the `model_settings` parameter. See [Optimizing vector storage with `index_options`](../semantic-search/semantic-search-semantic-text.md#semantic-text-index-options) for examples.
+When using the [`semantic_text` field type](../semantic-search/semantic-search-semantic-text.md) with dense vector embeddings, you can also configure `index_options` directly on the field. See [Optimizing vector storage with `index_options`](../semantic-search/semantic-search-semantic-text.md#semantic-text-index-options) for examples.
 ::::
 
 ```console