Understanding Vector Naming in Typesense
TLDR Koushik was confused by inconsistent vector naming in Typesense documents. Jason clarified that the vector can be named anything, as long as it has a 'num_dim' property.
Aug 03, 2023 (4 months ago)
Koushik
03:23 PM{
"name": "catalogue_items_vectors",
"fields": [
{"name": ".*", "type": "auto"},
{"name": "vec", "type": "float[]", "num_dim": 768}
]
}
now while going through with sample codes https://github.com/typesense/typesense-instantsearch-semantic-search-demo/tree/master
I can see typesense-instantsearch-semantic-search-demo/scripts/vector-generation/main.py
creating vector field like
product['
vectors
'] = sentence_embeddings[0].tolist()I am little confuse which is typesense internally points ?
Jason
04:37 PMNot sure I understand the question. Could you elaborate?
Aug 04, 2023 (4 months ago)
Koushik
08:44 AMBut the second link "main.py" inserting vector field named as "vector".
Koushik
08:45 AMJason
03:56 PMnum_dim
property in the field definition. In the docs we’ve used the name vec
as an example, and in the example we’ve used the word vector
as the field name. You can rename it to any stringJason
03:57 PMembedding
Aug 06, 2023 (4 months ago)
Koushik
07:53 AMTypesense
Indexed 3005 threads (79% resolved)
Similar Threads
Error in Implementing Vector Search
Krish faced an error while implementing vector search. After recreating the collection as suggested by Kishore Nallan, the issue was resolved.
Utilizing Vector Search and Word Embeddings for Comprehensive Search in Typesense
Bill sought clarification on using vector search with multiple word embeddings in Typesense and using them instead of OpenAI's embedding. Kishore Nallan and Jason informed him that their development version 0.25 supports open source embedding models. They also resolved Bill's concerns regarding search performance, language support, and limitations in the search parameters.
Integrating Semantic Search with Typesense
Krish wants to integrate a semantic search functionality with typesense but struggles with the limitations. Kishore Nallan provides resources, clarifications and workarounds to the raised issues.