https://typesense.org logo
Join Slack
Powered by
I have got a problem where using postman I get dif...
# community-help
m
I have got a problem where using postman I get different results for hybrid search and using python library it returns different results. typesense==0.16.0 (python client)
k
Can you please post a small reproduceable example?
m
I am just getting the IDs for sequentially fetching from DB using django queryset 
search_parameters1 = {
'q': remove_trailing_whitespace(search),
'query_by': 'embedding,title,job_responsibility,skills,industry,location,type,division,company',
'include_fields': 'id',
'per_page': 250,
'page': 1,
'sort_by': '_vector_distance:desc'
}
res = client.collections['alljobsupdated'].documents.search(search_parameters1)
newlist = [x['document']['id'] for x in res['hits']]
print(newlist)
Here the sequence and list are different than fetching directly from postman like {server}/collections/alljobsupdated/documents/search?q=laravel&query_by=embedding,title,job_responsibility,skills,industry,location,type,division,company&sort_by=_vector_distance:desc&include_fields=id&page=250
k
Can you try a multi_search request with both python client and with postman and compare those values? I wonder if there is some url encoding issue because of the GET params
Multi search uses POST so we can rule that out
m
okay thanks bhai, I will try it
it is working now but sometimes returns irrelevant data , do we need to remove stop words before inserting on typesense ?
k
Irrelevant data can happen because of semantic search.
m
is there any possibilities to tweak the fusion mechanism dynamically?
k
Can you try setting a distance threshold on the vector component:
Copy code
vector_query=embedding:([], distance_threshold:0.30)
In the snippet above, 
embedding
is the name of the vector field. Try adding the above to your queries to see if it helps.
m
thank you for the support
Open in Slack
PreviousNext
Powered by