# tMilvusInput Retrieves records from a collection in the Milvus database and transfers them to the following component. This component is not shipped with your Talend Studio by default. You need to install it using the Feature Manager. For more information, see [Installing features using the Feature Manager](https://help.qlik.com/talend/r/en-US/8.0/studio-user-guide/install-features-to-talend-studio). For a quick introduction on using this component in your Job, see the following video: ## tMilvusInput Standard properties These properties are used to configure tMilvusInput running in the Standard Job framework. The Standard tMilvusInput component belongs to the Databases family. ## Basic settings | Properties | Description | | --- | --- | | Use existing connection | Select this check box and in the Component
List drop-down list, select the desired connection component to
reuse the connection details you already defined. | | Schema and Edit Schema | A schema is a row description. It defines the number of fields
(columns) to be processed and passed on to the next component. When you create a Spark
Job, avoid the reserved word line when naming the
fields.

Click Edit
schema to make changes to the schema. If the current schema is of the Repository type, three options are available:

| | Collection | Enter the name of the collection in the Milvus database, or click the
[...] button next to the corresponding field to fetch
the available collections and select the desired one. | | Operation | Select the type of operation you want to perform on the collection data:



If you are using dynamic fields to specify the collection, note that the
QUERY mode will have a normal output, while the SEARCH mode will generate a new
column called $meta with all the dynamic fields in
it. | | Query vector | This component supports vector search capabilities, you can use this option
to specify the query condition using the queryVector
property. This query vector should be a JSON array, or array of an array, like
[1,0,1,0,1] and
[[1,0,1],[1,0,1],[0,1,1]].

For more
information on vector searches in Milvus, see the corresponding [Milvus documentation](https://milvus.io/docs/single-vector-search.md#Overview).

This field is available
only when you have selected SEARCH from
the Operation drop-down
list. | | Filter | Enter a query to filter on specific records in the collection data.

For
example, type in id < 50 to retrieve the
records whose id is lower than 50
from the collection specified in the Collection field. | | Limit and
Offset |

For more information on these two parameters, see the corresponding [Milvus documentation](https://milvus.io/docs/single-vector-search.md#Use-Limit-and-Offset). | ## Advanced settings | Properties | Description | | --- | --- | | tStatCatcher Statistics | Select this check box to collect the log data at the component
level. | | Partition | Select this check box to read data in partitions.

Enter the name, in
double quotation marks, of the partition column or columns of the Milvus table
you want to read data from, or click the [...] button
next to the corresponding field to select the desired ones.

If you need
to list several values, separate them with a comma. | | Load collection into memory | Select this check box to load the selected collection into memory when
executing the Job. | ## Global Variables | Variables | Description | | --- | --- | | Global Variables | NB\_LINE: the number
of rows read by an input component or transferred to an output component. This is an
After variable and it returns an integer.


ERROR\_MESSAGE: the error message generated by the
component when an error occurs. This is an After variable and it returns a string. This
variable functions only if the Die on error checkbox is
cleared, if the component has this checkbox.

A Flow variable functions during the execution of a component
while an After variable functions after the execution of the component.

To fill up a field or expression with a variable, press Ctrl+Space to access the variable list and choose the variable to use from
it.

For more information about variables, see [Using contexts and variables](https://help.qlik.com/talend/r/en-US/8.0/studio-user-guide/contexts-and-variables). | ## Usage | Usage guidance | Description | | --- | --- | | **Usage rule** | | **Related tasks** * [Querying Milvus collections using vector embeddings](https://help.qlik.com/talend/en-US/components/8.0/milvus/tmilvus-components-storing-and-retrieving-product-embeddings-standard-component "The following Job demonstrates how to connect to a Milvus vector database, insert product embeddings, and retrieve similar products using vector similarity search.")