Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Support Structured and Multi-Modal Response Types in Bedrock Retriever #317

Open
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

000-000-000-000-000
Copy link

Purpose

Adds support for structured and multi-modal retrieval by updating the Bedrock retriever response parsing logic

Detailed Changes

  1. Modularize retrieval logic in Bedrock retriever to separate a/ request creation b/ response parsing c/ search result to document conversion
  2. Make the retrieval config clearly optional + make it clear that it can be either a dictionary or a Python object
  3. Add TEXT, IMAGE, and ROW parsing for search results
  4. Introduce broader testing regime to test more cases across all of the different output types

Testing

  1. Added and executed new unit tests
  2. Installed and ran manual local tests on a few existing Knowledge Bases

…rock retriever + modularize some of the retrieval code
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants