Background service for chunking and embedding data - #756
Open
PaulKoudelka wants to merge 31 commits into
Open
Conversation
Contributor
Author
|
Still in progress |
SommerEngineering
requested changes
Aug 4, 2026
| public DataSourceSecurity SecurityPolicy { get; init; } = DataSourceSecurity.NOT_SPECIFIED; | ||
|
|
||
| /// <inheritdoc /> | ||
| public ConfidenceLevel ComplianceLevel { get; init; } = ConfidenceLevel.UNKNOWN; |
Member
There was a problem hiding this comment.
Let's please call the setting confidence level everywhere. Especially in the config plugin.
|
|
||
| public DataAgentRetrievalContextValidation AgentRetrievalContextValidation { get; init; } = new(); | ||
|
|
||
| public DataDataSourceIndexing DataSourceIndexing { get; init; } = new(); |
Member
There was a problem hiding this comment.
Please move this into the app settings.
| } | ||
|
|
||
| <ThirdPartyComponent Name="Qdrant Edge" Developer="Andrey Vasnetsov, Tim Visée, Arnaud Gourlay, Luis Cossío, Ivan Pleshkov, Roman Titov, xzfc, JojiiOfficial & Open Source Community" LicenseName="Apache-2.0" LicenseUrl="https://github.com/qdrant/qdrant/blob/master/LICENSE" RepositoryUrl="https://github.com/qdrant/qdrant" UseCase="@T("Qdrant Edge is an embedded vector database and vector similarity search engine. We use it to realize local RAG—retrieval-augmented generation—within AI Studio. Thanks for the effort and great work that has been and is being put into Qdrant.")"/> | ||
| <ThirdPartyComponent Name="SQLite" Developer="SQLite developers & Open Source Community" LicenseName="Public Domain" LicenseUrl="https://www.sqlite.org/copyright.html" RepositoryUrl="https://www.sqlite.org/src/" UseCase="@T("SQLite stores local RAG indexing metadata, searchable chunk text, and the file fingerprints used to decide whether local files need to be indexed again, without requiring a separate database server or a system SQLite installation.")"/> |
Member
There was a problem hiding this comment.
Please mention the developers by name, thank you.
| <PackageReference Include="MudBlazor" Version="8.15.0" /> | ||
| <PackageReference Include="MudBlazor.Markdown" Version="8.11.0" /> | ||
| <PackageReference Include="ReverseMarkdown" Version="5.0.0" /> | ||
| <PackageReference Include="SQLitePCLRaw.bundle_e_sqlite3" Version="2.1.10" /> |
Member
There was a problem hiding this comment.
We should use the newest 3.x release
| <ItemGroup> | ||
| <PackageReference Include="CodeBeam.MudBlazor.Extensions" Version="8.3.0" /> | ||
| <PackageReference Include="HtmlAgilityPack" Version="1.12.4" /> | ||
| <PackageReference Include="Microsoft.Data.Sqlite.Core" Version="9.0.9" /> |
Member
There was a problem hiding this comment.
I assume there is a 9.0.18 version?
| public enum DatabaseRole | ||
| { | ||
| VECTOR_STORE, | ||
| EMBEDDING_STATE, |
Member
There was a problem hiding this comment.
Rename to e.g., INDEX_STORE or something like that.
|
|
||
| namespace AIStudio.Tools.Databases.EmbeddingState; | ||
|
|
||
| public abstract class EmbeddingStateClient(string name, string path) : DatabaseClient(name, path) |
Member
There was a problem hiding this comment.
Should be renamed according to DataBaseRole.
| public abstract Task DeleteDataSourceAsync(string dataSourceId, CancellationToken token); | ||
| } | ||
|
|
||
| public sealed record EmbeddingStateFile( |
Member
There was a problem hiding this comment.
Please move all individual data classes into their own files.
|
|
||
| namespace AIStudio.Tools.Databases.EmbeddingState; | ||
|
|
||
| public sealed class SqliteEmbeddingStateClientImplementation( |
Member
There was a problem hiding this comment.
Please re-format lines like this, so we use the typical screen width (~170 chars).
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
No description provided.