mixing_the_results.py

# Connect to the semantic-search service and run the query
con = get_victor_connection()
response = con.FindTopKProblems(
    victor_pb2.TopKProblemsRequest(
        query=search_query,
        # In our implementation -1 means "return all matches"
        k=-1,
    ),
)

# Because we're using Cosine Similarity to find closes vectors,
# the resulting distance will always be in the range from -1 to 1.
# This allows us to easily define a confidence threshold and 
# consider anything above this threshold to be a
# "High Confidence Result"

CONFIDENCE_THRESHOLD = 0.65

# A custom scoring function we're goint to pass to ElasticSearch
# More information here: https://www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl-function-score-query.html

scroring_functions = [
    {
        "filter": {"term": {"document_id": match.id}},
        # This function will re-shape elastic search results in a way
        # that those, that scored well in similarity search, will move higher
        "weight": math.pow(
            document_count, match.distance
        )
    } for match in response.matches
]

high_confidence_docs = [
    match.id for match in response.matches
    if match.distance > CONFIDENCE_THRESHOLD
]

elastic_query = {
    'bool': {
        'should': [{
            "match": {
                "title": search_query,
            }
        },
        #
        # You can include any extra fields that you want to
        # query for your documents here
        # ...
        #
        #
        # The "terms" part of the query would ensure that anything that
        # has been found by Victor will always be returned by ElasticSearch
        {
            "terms": {
                "document_id": high_confidence_docs,
                # You can add extra boost to high confidence results
                "boost": 10,
            }
        }]
    }
}

params = {
    'query': {
        "function_score": {
            "query": elastic_query
            "functions": scoring_functions
        }
    }
}

# We use https://github.com/elastic/elasticsearch-dsl-py
# It's a python wrapper around narive ES DSL

from elasticsearch_dsl import Search
from our_project.search import Document

search = Search.from_dict(params)
search = search.index(Document.get_index_name())

search.execute()