#community-help

Hybrid Search Distance Threshold Issue

TLDR 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.

Join the chat

Sep 12, 2023 (2 weeks ago)

Photo of md5-4a81a7211dc7926511b3967d3019e75b

Anish

03:47 PM

👋 When I set a distance threshold like vector_query' : 'embedding:([], distance_threshold:0.30)' it doesn't seem to affect the results of a hybrid search. Some of the results returned have vector distance of 2. How would I set a threshold?

03:48

Anish

03:48 PM

I'm using 'query_by': 'embedding,description'

Photo of md5-8813087cccc512313602b6d9f9ece19f

Jason

03:59 PM

Hmm, that is indeed the way to do it...

03:59

Jason

03:59 PM

I'm not able to reproduce the issue on a test dataset. For eg:

➜  ~ curl -s '' \
-X 'POST' \
--data-binary '
      {
        "searches": [
          {
            "query_by": "embedding",
            "vector_query": "embedding:([], distance_threshold:0.50, k:10)",
            "collection": "hn-comments",
            "q": "cinema"
          }
        ]
      }
' | jq '.results[0].hits[].vector_distance'
0.35301458835601807
0.3530757427215576
0.37170201539993286
0.37984395027160645
0.39115262031555176
0.4030781388282776
0.4054117798805237
0.410835325717926
0.41370344161987305
0.4149748682975769

04:00

Jason

04:00 PM

Could you give me a curl snippet like this that creates a sample collection and documents, and reproduces the issue?

Anish

04:06 PM

Jason So actually it works fine with "query_by": "embedding",, but as soon I add another field there the vector distance isn't respected.

04:07

Anish

04:07 PM

It's difficult to provide a curl snippet with the embeddings and everything, i can try and set up an example

Jason

04:07 PM

Ah I see what you mean. For eg:

➜  ~ curl -s '' \
-X 'POST' \
--data-binary '
      {
        "searches": [
          {
            "query_by": "text,embedding",
            "vector_query": "embedding:([], distance_threshold:0.50, k:10)",
            "collection": "hn-comments",
            "q": "cinema"
          }
        ]
      }
' | jq '.results[0].hits[].vector_distance'
2
2
0.35301458835601807
2
2
0.3530757427215576
2
0.37170201539993286
2
2

04:08

Jason

04:08 PM

In a hybrid search, the vector_distance field is being set to 2 for all the results that are because of keyword search.

04:09

Jason

04:09 PM

Technically vector_distance is only calculated for results that were pulled up from a vector search and distance threshold only applies to vector search.

04:10

Jason

04:10 PM

So the bug here is that we're returning vector_distance: 2 for keyword-matched results, when technically we should not be returning that field at all

Anish

04:11 PM

Is there a way to change the rank fusion formula (like not 0.7 keyword but lower)?

Jason

04:12 PM

Not at the moment... Could you open a feature request GitHub issue for this?

Typesense

Lightning-fast, open source search engine for everyone | Knowledge Base powered by Struct.AI

Indexed 2779 threads (79% resolved)

Join Our Community Manage subscription

Similar Threads

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.

8mo

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.

225

2mo

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.

6mo

Discrepancy in Search Results Between Postman and Python Library

Md raised an issue about differing search results when using Postman and a Python library. Kishore Nallan suggested trying a multi_search request to compare values, and to set a distance threshold on the vector component. The issue was resolved.

1mo

Phrase Search Relevancy and Weights Fix

Jan reported an issue with phrase search relevancy using Typesense Instantsearch Adapter. The problem occurred when searching phrases with double quotes. The team identified the issue to be related to weights and implemented a fix, improving the search results.

111

6mo