How to use IBM App Connect with Pinecone Vector Database
Pinecone Vector Database is a purpose-built platform for indexing and searching dense vectors. It supports use cases like semantic search, recommendation systems, and AI-powered data analysis.
App Connect
Enterprise as a Service connector-
Local
connector in containers (Continuous Delivery release) 13.0.2.0-r1 or later
Supported product and API versions
To find out which product and API versions this connector supports, see Detailed System Requirements on the IBM Support page.
Connecting to Pinecone Vector Database
Complete the connection fields that you see in the App Connect Designer page or flow editor. If necessary, work with your Pinecone Vector Database administrator to obtain these values.
- The Server URL is the URL for the API server that makes runtime calls.
- The API key is the API key that is used to access Pinecone Vector Database.
- Set Allow self-signed certificates to be true or false. Set the property to true if you want to be able to accept self-signed certificates that are trusted and used only in a nonproduction environment. The default is false.
- The Override server URL is required if you want to connect to an endpoint
in a private network by using the private network client, or to override the server URL. Specify an
override value for the host and port for the connector in the format
<http or https>://<host_name>:<port>. If you are not using the private network client or do not require an override, don't complete this field. - Private network connection: Select the name of a private network
connection that App Connect uses to connect to your private
network. This list is populated with the names of private network connections that are created from
the
Private network connections
page in the Designer instance. You see this field only if a switch server is configured for this Designer instance. For more information, see Connecting to a private network from App Connect Designer. (In App Connect Designer 12.0.10.0-r1 or earlier instances that include this field, the display name is shown as Agent name.)
To obtain the connection values for Pinecone Vector Database, see Obtaining connection values for Pinecone Vector Database.
To connect to a Pinecone Vector Database endpoint from the App Connect Designer Applications and APIs page for the first time, expand Pinecone Vector Database, then click Connect.
Before you use the account that is created in App Connect in a flow, rename the account to something meaningful that helps you to identify it. To rename the account on the Applications and APIs page, select the account, open its options menu (⋮), then click Rename Account.
General Considerations
Before you use App Connect Designer with Pinecone Vector Database, take note of the following considerations:
- You can see lists of the trigger events and actions that are available
on the Applications and APIs page of the App Connect Designer.
For some applications, the events and actions depend on the environment and whether the connector supports configurable events and dynamic discovery of actions. If the application supports configurable events, you see a Show more configurable events link under the events list. If the application supports dynamic discovery of actions, you see a Show more link under the actions list.
- If you are using multiple accounts for an application, the set of fields that is displayed when you select an action for that application can vary for different accounts. In the flow editor, some applications always provide a curated set of static fields for an action. Other applications use dynamic discovery to retrieve the set of fields that are configured on the instance that you are connected to. For example, if you have two accounts for two instances of an application, the first account might use settings that are ready for immediate use. However, the second account might be configured with extra custom fields.
Events and Actions
Pinecone Vector Database events
These events are for changes in this application that trigger a flow to start completing the actions in the flow.
Pinecone Vector Database actions
Your flow completes these actions on this application.
| Object | Action | Description |
|---|---|---|
| Indexes | Create index | This operation deploys a Pinecone index |
| Retrieve all indexes | This operation returns a list of all indexes in a project | |
| Retrieve index details by name | Retrieves a description of an index | |
| Delete index | This operation deletes an existing index | |
| Vectors | Retrieve vectors | This operation looks up and returns vectors, by ID and from a single namespace |
| Retrieve vector IDs | The retrieve operation lists the IDs of vectors in a single namespace of a serverless index | |
| Query vectors | This operation searches a namespace by using a query vector. It retrieves the IDs of the most similar items in a namespace, along with their similarity scores. | |
| Update or create vector | This operation writes vectors into a namespace. If a new value is updated or created for an existing vector ID, it overwrites the previous value. | |
| Update vector | This operation updates a vector in a namespace. If a value is included, it overwrites the previous value. | |
| Delete vectors | This operation deletes vectors, by ID, from a single namespace |
Examples
Use templates to quickly create flows for Pinecone Vector Database
Learn how to use App Connect templates to quickly create flows that complete actions in Pinecone Vector Database. For example, go to the Discover page and search for Pinecone Vector Database.
Use IBM® App Connect to build flows that integrate with Pinecone Vector Database.
The following blog post describes how to implement a RAG pattern by querying a vector in Pinecone Vector Database and by using the embeddings that IBM watsonx.ai generates. The article also describes how to use the results to generate text by using IBM watsonx.ai. Click Read the blog to go to the blog.