-
Notifications
You must be signed in to change notification settings - Fork 42
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Create API to implement RAG pattern in IBM Watsonx AI using PineconeDB
- Loading branch information
Showing
1 changed file
with
14 additions
and
0 deletions.
There are no files selected for viewing
14 changes: 14 additions & 0 deletions
14
resources/markdown/resources/API to implement RAG pattern in IBM Watsonx AI using PineconeDB
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,14 @@ | ||
To refer to these instructions while editing the flow, open [the GitHub page](https://github.com/ot4i/app-connect-templates/blob/main/resources/markdown/API%20to%20implement%20RAG%20pattern%20in%20IBM%20Watsonx%20AI%20using%20PineconeDB_instructions.md) (opens in a new window). | ||
|
||
This API takes a question and IBM WatsonX AI uses this question to generate embeddings.These embeddings are used by pineconeDB to do a query. The results generated from this can be used as a prompt to IBM Watsonx AI to get answer to the question. | ||
|
||
## Using the template | ||
|
||
1. Click **Use this template** to start using the template. | ||
1. Click **Operations**, then **Edit flow** for the _Create vectors_ operation. | ||
1. Click on the **IBM Watsonx AI** node, and if you're not already connected, connect to your [IBM Watsonx AI account](https://www.ibm.com/docs/en/app-connect/saas?topic=apps-watsonxai). | ||
1. Click on the **PineconeDB** node , and if you're not already connected, connect to your [PineconeDB account](). | ||
1. Click **Done**. | ||
1. To start the flow, in the banner click **Start flow**. | ||
|
||
Want to see if working? Click **Manage** in the API flow, then follow the instructions on getting started. Once you're in the API portal, use the Try it link and then **Generate** some test data. Replace the value for `file_url` with the URL for the CSV file you want to use. Replace the value for `event_name` with the event name you want to match in your file, and then click **Call operation**. |