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

Add Amazon Bedrock Knowledge base as a RAG Engine (retriever) #427

Merged
merged 50 commits into from
Aug 7, 2024

Conversation

massi-ang
Copy link
Collaborator

Issue #, if available:
Resolves #271

Description of changes:
With this PR we are adding Amazon Bedrock Knowledge Bases as additional RAG Engine (retrievers).

The KB must be already created and available in the same region used by Bedrock. The integration supports both semantic retrieval and hybrid retrieval via the KB retrieve API.

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

@massi-ang massi-ang requested a review from spugachev March 21, 2024 16:15
@massi-ang massi-ang marked this pull request as draft June 25, 2024 14:11
@joysl
Copy link

joysl commented Jun 28, 2024

can I build the chatbot off of this branch?

@massi-ang
Copy link
Collaborator Author

massi-ang commented Jun 30, 2024

@joysl

can I build the chatbot off of this branch?

Yes, you can now use this branch to deploy as it has been synched with main

@joysl
Copy link

joysl commented Jul 1, 2024

@massi-ang Thank you so much, this worked for me

@massi-ang massi-ang requested review from bigadsoleiman and removed request for spugachev July 9, 2024 12:58
@massi-ang massi-ang marked this pull request as ready for review July 9, 2024 12:59
@bigadsoleiman
Copy link
Collaborator

There are few conflicts that needs to be resolved first

Copy link
Collaborator

@charles-marion charles-marion left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Great feature to add.
Added minor comments. Will approved after dev files are removed.

bin/config copy.json Outdated Show resolved Hide resolved
.codecatalyst/workflows/Workflow_81ec.yaml Outdated Show resolved Hide resolved
enterprise: false
enterprise: false,
},
knowledgeBase: {
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

nit: suggestion bedrock or bedrockKnowledgeBase. Other properties name the service.

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Do they? I see aurora, kendra, ...

@charles-marion charles-marion merged commit 0226f4c into main Aug 7, 2024
5 checks passed
lloydclowes pushed a commit to lloydclowes/gen-ai-playground that referenced this pull request Oct 5, 2024
…mples#427)

* feat(kb): initial

* feat(bedrock_kb): initial

* feat(bedrock_kb): knowledge base support

* feat(bedrock_kb): delete workspaces

* feat(bedrock_kb): config

* feat(bedrock_kb): hybrid search

* feat(bedrock_kb): upgrade boto3

* fix(cohere_embeddings): correct set the `input_type`

* feat(kb): add Bedrock KB to the welcome page

* fix(no unused var): correct ignore

* fix: correct enum values

* feat(bedrock_kb): metadata filters

* feat(bedrock_kb): dedup

* feat(llama3): adapter

* feat(bedrock_kb): merge to latest

* chore: updating code to use langchain-community

* feat(bedrock): fix error

* fix(bedrock_kb): magic cli

* fix: correct path to compiled files

* chore: removed wrongly tracked file

* fix: fix review feedback

- remove dev files
- remove console.log
- remove unused code

* fix: remove feature under development

* fix: typescript errors

* fix: ignore code un `dist` to avoid recursive builds

* tests: update test snapshot and fix call order

* test: fix rag tests
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
Status: Done
Development

Successfully merging this pull request may close these issues.

Feature: add Bedrock Knowledge Base as RAG Engine
5 participants