--- slug: /add-data-of-api --- # add - Insert data The `add()` method inserts new data into a collection. If a record with the same ID already exists, an error is returned. :::info This API is only available when using a Client. For more information about the Client, see [Client](../50.client.md). ::: ## Prerequisites * You have installed pyseekdb. For more information about how to install pyseekdb, see [Quick Start](../../10.pyseekdb-sdk/10.pyseekdb-sdk-get-started.md). * You have connected to the database. For more information about how to connect to the database, see [Client](../50.client.md). * If you are using seekdb or OceanBase Database in client mode, make sure that the user to which you are connected has the `INSERT` privilege on the table to be operated. For more information about how to view the privileges of the current user, see [View user privileges](https://www.oceanbase.com/docs/common-oceanbase-database-cn-1000000003980135). If you do not have the required privilege, contact the administrator to grant you the privilege. For more information about how to directly grant a privilege, see [Directly grant a privilege](https://www.oceanbase.com/docs/common-oceanbase-database-cn-1000000003980140). ## Request parameters ```python add( ids=ids, embeddings=embeddings, documents=documents, metadatas=metadatas ) ``` |Parameter|Type|Required|Description|Example value| |---|---|---|---|---| |`ids`|string or List[str]|Yes|The ID of the data to be inserted. You can specify a single ID or an array of IDs.|item1| |`embeddings`|List[float] or List[List[float]]|No|The vector or vectors of the data to be inserted. If you specify this parameter, the value of `embedding_function` is ignored. If you do not specify this parameter, you must specify `documents`, and the `collection` must have an `embedding_function`.|[0.1, 0.2, 0.3]| |`documents`|string or List[str]|No|The document or documents to be inserted. If you do not specify `vectors`, `documents` will be converted to vectors using the `embedding_function` of the `collection`.|"This is a document"| |`metadatas`|dict or List[dict]|No|The metadata or metadata list of the data to be inserted. |`{"category": "AI", "score": 95}`| :::info The `embedding_function` associated with the collection is set during `create_collection()` or `get_collection()`. You cannot override it for each operation. ::: ## Request example ```python import pyseekdb from pyseekdb import DefaultEmbeddingFunction, HNSWConfiguration # Create a client client = pyseekdb.Client() collection = client.create_collection( name="my_collection", configuration=HNSWConfiguration(dimension=3, distance='cosine'), embedding_function=None ) # Add single item collection.add( ids="item1", embeddings=[0.1, 0.2, 0.3], documents="This is a document", metadatas={"category": "AI", "score": 95} ) # Add multiple items collection.add( ids=["item4", "item2", "item3"], embeddings=[ [0.1, 0.2, 0.4], [0.4, 0.5, 0.6], [0.7, 0.8, 0.9] ], documents=[ "Document 1", "Document 2", "Document 3" ], metadatas=[ {"category": "AI", "score": 95}, {"category": "ML", "score": 88}, {"category": "DL", "score": 92} ] ) # Add with only embeddings collection.add( ids=["vec1", "vec2"], embeddings=[[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]] ) collection1 = client.create_collection( name="my_collection1" ) # Add with only documents - embeddings auto-generated by embedding_function # Requires: collection must have embedding_function set collection1.add( ids=["doc1", "doc2"], documents=["Text document 1", "Text document 2"], metadatas=[{"tag": "A"}, {"tag": "B"}] ) ``` ## Response parameters None ## References * [Update data](300.update-data-of-api.md) * [Update or insert data](400.upsert-data-of-api.md) * [Delete data](500.delete-data-of-api.md)