Skip to content
Nappai Documentation

Amazon Bedrock Embeddings

This component helps Nappai understand the meaning of your text data. It translates text into numbers that computers can easily work with, making it easier for Nappai to perform tasks like searching, comparing, and organizing information.

Relationship with Amazon Bedrock

This component uses Amazon Bedrock, a powerful service from Amazon Web Services (AWS), to generate these numerical text representations. It leverages Amazon’s advanced AI models to create high-quality embeddings.

Inputs

  • Model Id: Choose the specific Amazon Bedrock model you want to use to create the embeddings. A default model is provided, but you can select others if needed.
  • Credential: This is your access key to use Amazon Bedrock. Nappai will securely store this information. (Advanced users only)
  • Endpoint URL: (Advanced users only) This input is for advanced users who need to specify a custom endpoint for Amazon Bedrock. Leave this blank unless you have specific instructions from your administrator.

Outputs

The component produces Embeddings, which are numerical representations of your text. These embeddings are then used by other Nappai components to perform tasks like finding similar pieces of text or organizing information based on meaning. You won’t directly interact with the embeddings themselves; other components will use them behind the scenes.

Usage Example

Imagine you have a large collection of customer reviews. You can use this component to create embeddings for each review. Then, you can use another Nappai component (like a vector database) to quickly find reviews that are similar in meaning, allowing you to identify common themes or issues.

Templates

[List of templates where the component can be seen and its configuration - This section requires information not provided in the prompt]

  • Semantic Text Splitter: This component breaks down large texts into smaller, more manageable chunks before creating embeddings. This is useful for very long pieces of text.
  • Couchbase, Upstash, Chroma DB, Weaviate, Vectara, Redis, PGVector, FAISS, Astra DB, Qdrant, Pinecone, MongoDB Atlas, Milvus, Supabase, Cassandra, Text Embedder: These components are vector databases or other tools that can store and search the embeddings created by this component, allowing you to find similar pieces of text or information.

Tips and Best Practices

  • Start with the default Model Id unless you have a specific reason to choose a different one.
  • Contact your administrator if you need help configuring the advanced settings (Endpoint URL and Credential).

Security Considerations

Your Amazon Bedrock credentials are securely stored and managed by Nappai. Do not share these credentials with anyone. If you suspect unauthorized access, contact your administrator immediately.