You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: Documentation/7.0/Raven.Documentation.Pages/ai-integration/vector-search/data-types-for-vector-search.dotnet.markdown
+13-13Lines changed: 13 additions & 13 deletions
Original file line number
Diff line number
Diff line change
@@ -7,13 +7,13 @@
7
7
as outlined below.
8
8
9
9
* Text and numerical data that is not pre-quantized can be further quantized in the generated embeddings.
10
-
Learn more in [Quantization options](../ai-integration/vector-search-using-dynamic-query#quantization-options).
10
+
Learn more in [Quantization options](../../ai-integration/vector-search/vector-search-using-dynamic-query#quantization-options).
11
11
12
12
* In this page:
13
-
*[Supported data types for vector search](../ai-integration/data-types-for-vector-search#supported-data-types-for-vector-search)
* Ensure that all vectors within this field across all documents in the collection are generated by the **same model** and model version and have the **same dimensions**.
42
42
* Consistency in both dimensionality and model source is crucial for meaningful comparisons in the vector space.
43
43
44
-
* In addition to the native types described below, we highly recommended using [RavenVector](../ai-integration/data-types-for-vector-search#ravenvector)
44
+
* In addition to the native types described below, we highly recommended using [RavenVector](../ai-integration/vector-search/data-types-for-vector-search#ravenvector)
45
45
for efficient storage and fast queries when working with numerical embeddings.
46
46
47
47
{CONTENT-FRAME: }
@@ -61,7 +61,7 @@ Use when you prioritize storage efficiency and query speed.
61
61
`byte[] / sbyte[]` - A single pre-quantized embedding vector in the _Int8_ or _Binary_ quantization format.
62
62
`byte[][] / sbyte[][]` - An array of pre-quantized embedding vectors.
63
63
64
-
When storing data in these formats in your documents, you should use [RavenDB’s vector quantizer methods](../ai-integration/vector-search-using-dynamic-query#section-1).
64
+
When storing data in these formats in your documents, you should use [RavenDB’s vector quantizer methods](../../ai-integration/vector-search/vector-search-using-dynamic-query#section-1).
65
65
66
66
{CONTENT-FRAME/}
67
67
{CONTENT-FRAME: }
@@ -106,7 +106,7 @@ When a class property is stored as a `RavenVector`, the vector's content will ap
Copy file name to clipboardExpand all lines: Documentation/7.0/Raven.Documentation.Pages/ai-integration/vector-search/indexing-attachments-for-vector-search.dotnet.markdown
+49-49Lines changed: 49 additions & 49 deletions
Original file line number
Diff line number
Diff line change
@@ -4,18 +4,18 @@
4
4
{NOTE: }
5
5
6
6
* This article explains how to index attachments using a **static-index** to enable vector search on their content.
7
-
Note: Vector search on attachment content is not available when making a [dynamic query](../ai-integration/vector-search-using-dynamic-query).
7
+
Note: Vector search on attachment content is not available when making a [dynamic query](../../ai-integration/vector-search/vector-search-using-dynamic-query).
8
8
9
-
***Prior to this article**, refer to the [Vector search using a static index](../ai-integration/vector-search-using-static-index) article for general knowledge about
9
+
***Prior to this article**, refer to the [Vector search using a static index](../../ai-integration/vector-search/vector-search-using-static-index) article for general knowledge about
*[Indexing ALL attachments](../../ai-integration/vector-search/indexing-attachments-for-vector-search#indexing-all-attachments)
19
19
20
20
{NOTE/}
21
21
@@ -36,7 +36,7 @@
36
36
They are stored as **binary data**, regardless of content type.
37
37
38
38
* Attachments are handled as streams, allowing efficient upload and retrieval.
39
-
Learn more in: [What are attachments](../document-extensions/attachments/what-are-attachments).
39
+
Learn more in: [What are attachments](../../document-extensions/attachments/what-are-attachments).
40
40
41
41
{CONTENT-FRAME/}
42
42
{CONTENT-FRAME: }
@@ -55,7 +55,7 @@ enabling vector search on text or numerical data that is stored in the attachmen
55
55
***Attachments with NUMERICAL data**:
56
56
* While attachments can store any file type, RavenDB does Not generate embeddings from images, videos, or other non-textual content.
57
57
Each attachment must contain a **single** precomputed embedding vector, generated externally.
58
-
* RavenDB indexes the embedding vector from the attachment in and can apply [quantization](../ai-integration/vector-search-using-dynamic-query#quantization-options)
58
+
* RavenDB indexes the embedding vector from the attachment in and can apply [quantization](../../ai-integration/vector-search/vector-search-using-dynamic-query#quantization-options)
59
59
(e.g., index it in _Int8_ format) if this is configured.
60
60
* All embeddings indexed within the same vector-field in the static-index must be vectors of the **same dimension** to ensure consistency in indexing and search.
61
61
They must also be created using the **same model**.
@@ -71,22 +71,22 @@ enabling vector search on text or numerical data that is stored in the attachmen
71
71
This applies to all _Company_ documents that contain an attachment with that name.
from index "Companies/ByVector/FromNumericalAttachment"
132
132
where vector.search(VectorFromAttachment, $queryVector)
@@ -138,23 +138,23 @@ where vector.search(VectorFromAttachment, $queryVector)
138
138
139
139
### JS index
140
140
141
-
* The following is the JavaScript index format equivalent to the [LINQ index](../ai-integration/indexing-attachments-for-vector-search#linq-index) shown above.
141
+
* The following is the JavaScript index format equivalent to the [LINQ index](../../ai-integration/vector-search/indexing-attachments-for-vector-search#linq-index) shown above.
142
142
143
143
* The main difference is that JavaScript indexes do Not support `getContentAsStream()` on attachment objects:
144
144
* Because of this, embedding vectors must be stored in attachments as **Base64-encoded strings**.
145
145
* Use `getContentAsString()` to retrieve the attachment content as a string, as shown in this example.
0 commit comments