Implement RAG #92
Open
Implement RAG #92
Conversation
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
It's not robust. Just minimum work to produces embeddings.
Implemented version for LLM and sentence transformer Also implemented a basic test UI in the knowledge base page just for testing
Adapter for Langchain still needs to be implemented...
Knowledge base should allow the user to add files/folders to a knowledge base so that it can be used in llm
WIP. Still need to figure out correct way of dealing with this. Perhaps a provider instead?
The knowledge groups are not separated for RAG yet. It basically pulls all embeddings regardless of group.
However, its rough, it assumes a hardcoded path to an embedder Looks like state is not well done thus it doesnt know when it's done. Just a lot of problems to fix before release but a working prototype.
Still need to be able to remove the documents?
Removed the loader selector and allow the user to toggle files to upload instead DropArea can take multiple files/directories
Use a stream to deal with updates for objectBox This looks like a good pattern for the tree too
This removes need for much of the provider
This center wrap was also around the child which would screw with the content of the child
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #92 +/- ##
==========================================
- Coverage 36.22% 30.75% -5.47%
==========================================
Files 43 58 +15
Lines 1858 2286 +428
==========================================
+ Hits 673 703 +30
- Misses 1185 1583 +398
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. |
Was missing some ui for the empty states
There is a function for it, but it adds the dot. Since it's a simple problem I'd rather have this solution than having to remove the dot.
RHeckerIntel
requested review from
ArendJanKramer,
ActiveChooN and
AlexanderBarabanov
as code owners
Own pdf decoder is a bit more work to do deal with edge cases and does not within time schedule now
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Implementation of RAG!
Features:
Knowledge base:
Text generation with temporary file:
Text generation using existing knowledge base:
