Speed | Accuracy | Memory Usage |
---|---|---|
Fast | Good | Medium |
Speed | Accuracy | Memory Usage |
---|---|---|
Medium | Highest | High |
Speed | Accuracy | Memory Usage |
---|---|---|
Fast | Good | Low |
filters
parameter in query operations supports MongoDB-style operators:
$eq
: Equality ({"category": "research"}
)$ne
: Not equal ({"status": {"$ne": "draft"}}
)$gt
: Greater than ({"score": {"$gt": 0.8}}
)$gte
: Greater than or equal ({"year": {"$gte": 2020}}
)$lt
: Less than ({"price": {"$lt": 100}}
)$lte
: Less than or equal ({"rating": {"$lte": 4.5}}
)$in
: In array ({"tag": {"$in": ["ai", "ml"]}}
)$nin
: Not in array ({"category": {"$nin": ["spam", "deleted"]}}
)$and
: Logical AND ({"$and": [{"a": 1}, {"b": 2}]}
)$or
: Logical OR ({"$or": [{"x": 1}, {"y": 2}]}
)include
parameter:
vector
: The vector data itselfcontents
: Text or binary content associated with the vectormetadata
: Structured metadata objectdistance
: Similarity distance (query operations only)cosine
: Cosine similarity (recommended for normalized vectors)euclidean
: Euclidean distance (L2 norm)squared_euclidean
: Squared Euclidean distance (faster than euclidean)