Troubleshooting Vector Search Setup in Typesense
TLDR Gio encountered issues setting up vector search using Typesense. Jason provided guidance and eventually offered to help via a call.
1
Feb 27, 2023 (9 months ago)
Gio
11:26 AM1. I’ve embedded a plain text using OpenAI.
2. I’ve created a collection by pasting the embedded list of vectors inside FIELD parameter.
3. When I go to search tab it only searches inside document title.
Have in mind I’m a nocode developer (Bubble io to be specific). So I’m trying to set this up correctly to then integrate Typesense to my app.
Guys could you please point me to right direction? I’m really desperate. I need to make this work… Jason
Gio
04:54 PMJason
06:53 PMJason
06:54 PMvector_query
parameterGio
07:06 PMGio
07:07 PMGio
07:07 PMJason
07:07 PMJason
07:08 PMGio
07:08 PMGio
07:08 PMJason
07:09 PMvector_query=vec:([0.96826, 0.94, 0.39557, 0.306488], k:100)
Jason
07:09 PMGio
07:11 PMJason
07:11 PMGio
07:12 PMGio
07:13 PMJason
07:16 PM1
Typesense
Indexed 3005 threads (79% resolved)
Similar Threads
Issues with Search UI for Vector Search
WL is building a search UI for vector search and having issues with syntax, while Jason provides context on the issue.
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.
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.
Hybrid Search Distance Threshold Issue
Anish has an issue with search results not respecting the vector distance threshold when using hybrid search. Jason explains additional fields cause `vector_distance` to only apply to vector search results and suggests opening a feature request on GitHub.