mirror of
https://github.com/MindWorkAI/AI-Studio.git
synced 2026-11-04 10:48:23 +00:00
74 lines
3.7 KiB
C#
74 lines
3.7 KiB
C#
using System.Text.Json.Serialization;
|
|
|
|
using AIStudio.Chat;
|
|
using AIStudio.Settings.DataModel;
|
|
using AIStudio.Tools.RAG;
|
|
|
|
namespace AIStudio.Settings;
|
|
|
|
/// <summary>
|
|
/// The common interface for the data sources in DataSources, which classic RAG, Semantic Search and the agents read.
|
|
/// </summary>
|
|
[JsonPolymorphic(TypeDiscriminatorPropertyName = "$type_discriminator")]
|
|
[JsonDerivedType(typeof(DataSourceLocalDirectory), nameof(DataSourceType.LOCAL_DIRECTORY))]
|
|
[JsonDerivedType(typeof(DataSourceLocalFile), nameof(DataSourceType.LOCAL_FILE))]
|
|
[JsonDerivedType(typeof(DataSourceERI_V1), nameof(DataSourceType.ERI_V1))]
|
|
public interface IDataSource : IDataSourceBase
|
|
{
|
|
/// <summary>
|
|
/// The maximum number of matches one retrieval returns. Searched page by page, it is the size of a page.
|
|
/// </summary>
|
|
public ushort MaxMatches { get; init; }
|
|
|
|
/// <summary>
|
|
/// Where a chat may still send data, once content of this data source reached it.
|
|
/// </summary>
|
|
/// <remarks>
|
|
/// Read it through DataSourceOutboundDataExtensions.GetEffectiveOutboundDataRestriction, never
|
|
/// on its own: an organization may demand a stricter level, see
|
|
/// DataSourceSecuritySettings.MinimumOutboundDataRestriction, and so does a data source which only
|
|
/// self-hosted providers may see.
|
|
/// </remarks>
|
|
public OutboundDataRestriction OutboundDataRestriction { get; init; }
|
|
|
|
/// <summary>
|
|
/// The last page which can be retrieved from this data source.
|
|
/// </summary>
|
|
/// <remarks>
|
|
/// By default, as many pages as RetrievalPaging.GetLastPage allows for the page size. A data
|
|
/// source which cannot page that far says so itself. It is a method rather than a property, so
|
|
/// that it never ends up in the settings.
|
|
/// </remarks>
|
|
/// <returns>The number of the last page, which is at least 1.</returns>
|
|
public int GetLastPage() => RetrievalPaging.GetLastPage(this.MaxMatches);
|
|
|
|
/// <summary>
|
|
/// Perform the data retrieval process.
|
|
/// </summary>
|
|
/// <param name="lastUserPrompt">The last user prompt from the chat.</param>
|
|
/// <param name="thread">The chat thread.</param>
|
|
/// <param name="token">The cancellation token.</param>
|
|
/// <returns>The retrieved data context.</returns>
|
|
public Task<IReadOnlyList<IRetrievalContext>> RetrieveDataAsync(IContent lastUserPrompt, ChatThread thread, CancellationToken token = default);
|
|
|
|
/// <summary>
|
|
/// Search the data source for a query of its own, one page at a time.
|
|
/// </summary>
|
|
/// <remarks>
|
|
/// Unlike the retrieval above, the query need not be what the user wrote last: Semantic Search
|
|
/// lets the model work it out from the conversation, and search as often as it takes. The first
|
|
/// page holds what the retrieval above finds for the same text. How the pages are cut is
|
|
/// described in RetrievalPaging.
|
|
///
|
|
/// Since the user did not write the query, the user is not told about problems with it. They
|
|
/// arrive in RetrievalPage.Gaps instead, together with everything else which kept the search
|
|
/// from covering the whole data source.
|
|
/// </remarks>
|
|
/// <param name="query">What to search for.</param>
|
|
/// <param name="page">The page to retrieve, from 1 up to GetLastPage.</param>
|
|
/// <param name="thread">The chat thread.</param>
|
|
/// <param name="token">The cancellation token.</param>
|
|
/// <returns>The retrieved data contexts of this page, whether the next page is worth asking for, and what the search could not cover.</returns>
|
|
/// <exception cref="ArgumentOutOfRangeException">The page is below 1 or beyond the last page.</exception>
|
|
public Task<RetrievalPage> RetrieveDataAsync(string query, int page, ChatThread thread, CancellationToken token = default);
|
|
} |