SemanticSearchIndex
represents a semantic search index object.
Details and Options
- SemanticSearchIndex represents a corpus of documents that can be searched by semantic similarity.
- Indexes are usually created by CreateSemanticSearchIndex.
- Index properties can be accessed via SemanticSearchIndex[…]["prop"].
- The following properties are supported:
-
"Database" vector database backing the index "DocumentCount" number of documents stored in the index "Embeddings" vector embeddings of the entries "FeatureExtractor" how features are extracted from text segments "ID" index ID "ItemCount" number of segments stored in the index "Items" stored segments "Label" item labels "Location" where the database is stored "TagKeys" keys of the tag association "Tags" tags associated with each entry "Tokenizer" how the text segment is split into tokens {prop1,…} a list of properties - The following options can be specified:
-
OverwriteTarget Automatic whether to overwrite an existing location GeneratedAssetLocation $GeneratedAssetLocation where to save the database
Examples
open allclose allBasic Examples (2)
Scope (4)
Extract a list of index properties:
Use the index to perform a search operation:
Store a SemanticSearchIndex in a file:
Options (1)
GeneratedAssetLocation (1)
Wolfram Research (2024), SemanticSearchIndex, Wolfram Language function, https://reference.wolfram.com/language/ref/SemanticSearchIndex.html.
Text
Wolfram Research (2024), SemanticSearchIndex, Wolfram Language function, https://reference.wolfram.com/language/ref/SemanticSearchIndex.html.
CMS
Wolfram Language. 2024. "SemanticSearchIndex." Wolfram Language & System Documentation Center. Wolfram Research. https://reference.wolfram.com/language/ref/SemanticSearchIndex.html.
APA
Wolfram Language. (2024). SemanticSearchIndex. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/SemanticSearchIndex.html