Skip to content

Background service for chunking and embedding data - #756

Open
PaulKoudelka wants to merge 52 commits into
MindWorkAI:mainfrom
PaulKoudelka:chunk-data
Open

Background service for chunking and embedding data#756
PaulKoudelka wants to merge 52 commits into
MindWorkAI:mainfrom
PaulKoudelka:chunk-data

Conversation

@PaulKoudelka

Copy link
Copy Markdown
Contributor

No description provided.

@PaulKoudelka

Copy link
Copy Markdown
Contributor Author

Still in progress

@SommerEngineering SommerEngineering left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

Thanks 🙂

Comment thread app/MindWork AI Studio/Settings/DataModel/DataSourceERI_V1.cs Outdated
Comment thread app/MindWork AI Studio/Settings/DataModel/Data.cs Outdated
Comment thread app/MindWork AI Studio/Pages/Information.razor Outdated
Comment thread app/MindWork AI Studio/MindWork AI Studio.csproj Outdated
Comment thread app/MindWork AI Studio/MindWork AI Studio.csproj Outdated
Comment thread app/MindWork AI Studio/Tools/Databases/DatabaseRole.cs Outdated
Comment thread app/MindWork AI Studio/Tools/Databases/EmbeddingState/EmbeddingStateClient.cs Outdated
Comment thread app/MindWork AI Studio/Tools/Databases/IndexStore/IndexStoreClient.cs Outdated
Comment on lines 42 to 44
case ContentStreamDocumentMetadata:
case ContentStreamImageMetadata:
return sseEvent.Content;

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

We are rejecting all metadata, which we could use for RAG, e.g., page numbers. We should change this!

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