diff --git a/README.md b/README.md index 1adcfdfe3cba4c7ba29907320eddc054f3189475..e1499bbdd84e05887c955cb8d419be0138ade90b 100644 --- a/README.md +++ b/README.md @@ -37,6 +37,11 @@ This script performs the following actions: * After the vector store is set up, the script retrieves and displays the store's endpoint for immediate use. ### Step 3: Vectorizing the PDF Files + +Before starting vectorizing, please go to AWS bedrock service and request the following models: +* Titan Embedding v1 +* Claude v2 + After setting up the S3 bucket and Vector DB, we could process PDF files to generate and store embeddings in the vector database. Run: