# tPineconeClient Available in... * Cloud Data Fabric * Data Fabric * Qlik Talend Cloud Enterprise Edition * Real-Time Big Data Platform Upserts, queries, fetches, updates, or deletes records in Pinecone index namespaces. Information noteNote: 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: ## tPineconeClient Standard properties These properties are used to configure tPineconeClient running in the Standard Job framework. The Standard tPineconeClient component belongs to the AI family. Information noteNote: This component is a specific version of a dynamic database connector. The properties related to database settings vary depending on your database type selection. For more information about dynamic database connectors, see [DB Generic components](https://help.qlik.com/talend/r/en-US/8.0/components/db-generic/db-generic-component). ## Basic settings | Properties | Description | | --- | --- | | Database | Select the desired database type from the list and click
Apply. | | Property type | Either Built-in or
Repository
.

Built-in: No property data stored centrally.
Repository: Select the repository file in which the properties are stored. The fields that follow are completed automatically using the data retrieved.

| | Schema and Edit Schema | A schema is a row description, it defines the number of fields to be
processed and passed on to the next component. The schema is either
Built-in or stored remotely in the
Repository.

Built-in: You create and store the schema locally for this component only. For more information about a component schema in its Basic settings tab, see Basic settings tab.
Repository: You have already created the schema and stored it in the Repository. You can reuse it in various projects and Job designs. For more information about a component schema in its Basic settings tab, see Basic settings tab.

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

View schema: choose this option to view the schema only.
Change to built-in property: choose this option to change the schema to Built-in for local changes.
Update repository connection: choose this option to change the schema stored in the repository and decide whether to propagate the changes to all the Jobs upon completion.

If you just want to propagate the changes to the current Job, you can select No upon completion and choose this schema metadata again in the Repository Content window.

| | Sync columns | Click this button to retrieve the schema from the preceding
component. | | Guess schema | Click this button to retrieve the schema according to your
settings. | | API Key | Enter the Pinecone API key in this field.

To enter the raw key, click the [...] button next to the
corresponding field to bring out the Enter a new
password dialog box, enter the key in the text field, and click
OK. You can also use a context variable in that
field.

For more information on how to find your Pinecone API Key, see [Authentication](https://docs.pinecone.io/guides/get-started/authentication). | | Host | Enter the IP address of the Pinecone database in this field, or click the
[...] button next to the corresponding field to
retrieve it.

You can also use a context variable in that field. | | Operation | Select the operation you want to perform to the incoming data and data records
in the Pinecone database table:

Upsert: Creates new records and overwrites existing records in the specified index namespace.
Query: Retrieves the IDs of the most similar records in the index, along with their similarity scores. You need to specify the number of results to return in the Top K field, knowing that this number is linked to the number of existing records: if you enter 7 in that field and the database only contains 5 records, you will get 5 records.
Fetch: Fetches records by ID from the specified index namespace.
Update: Updates existing records in the specified index namespace.
Delete: Removes records from the specified index namespace. If you need to apply this action on all the records of the specified namespace, select the Delete all check box that is displayed.
Get index stats: Gets the details of a Pinecone index.

For more information on these data operations, see [Data](https://docs.pinecone.io/guides/data/upsert-data). | | Namespace | Enter the name of the Pinecone index namespace on which you want to apply the
data operations. | ## Advanced settings | Properties | Description | | --- | --- | | tStatCatcher Statistics | Select this check box to gather the Job processing metadata at a Job level
and at each component level. | | Max batch size | Set the maximum number of records allowed in each batch.

For more information on these data operations, see [Upsert limits](https://docs.pinecone.io/guides/data/upsert-data#upsert-limits). | | API version | Specify the version of the Pinecone API to be used in your requests.

For more information on API versioning, see [Specifying an API version](https://docs.pinecone.io/reference/api/versioning#specifying-an-api-version). | | Filter | Specify a filter expression to be used when querying the Pinecone index.

For more information on filter expressions, see [Filter with metadata](https://docs.pinecone.io/guides/data/filter-with-metadata). | ## Global Variables | Variables | Description | | --- | --- | | ERROR\_MESSAGE | ERROR\_MESSAGE: the error message generated by the component when an
error occurs. This is an After variable and it returns a string. | | NB\_LINE | 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. | **Related tasks** * [Indexing phone reviews with embeddings and vector database](https://help.qlik.com/talend/en-US/components/8.0/ai/tembeddingai-tpineconeclient-tmap-indexing-phone-reviews-with-embeddings-and-vector-db "This Job reads phone review text files from a folder, splits the content into smaller chunks for better analysis, generates vector embeddings using Azure OpenAI, and stores them in a Pinecone vector database to enable semantic search.")