mirror of
https://github.com/MindWorkAI/AI-Studio.git
synced 2026-09-29 20:23:38 +00:00
Resolved 29 conflicting files. The notable decisions: Confidence: main's tool-calling gate (RequiredProviderConfidence) and this branch's local-RAG gate (DataConfidenceLevel) turned out to be the same rule on the same axis, so they are now one field. Both tool results and data sources raise it through RequireProviderConfidence(). The gate checks the level strictly and no longer exempts providers trusted by configuration: TrustedProviderIds is documented as applying to data-source security checks only, and organizations set confidence through DataConfidence .CustomConfidenceScheme instead. The security axis (DataSecurity, ERI, IsTrustedForDataSourceSecurityChecks) is unchanged. Provider creation: main's CreateProvider signature won (hfEndpointKind, capabilityOverrides, no model parameter); tokenizerPath was added to it and is set for every provider, including the new Hetzner, IONOS and LiteLLM. Provider and EmbeddingProvider combine the record parameters, Lua parsing and Lua serialization of both sides. File types: main's hierarchy (ODT leaf, WORD parent, PowerPoint without the legacy .ppt, TABULAR instead of DELIMITED_TABLE) plus this branch's SPREADSHEET parent with ODS and the xlsm/xlsb/xla/xlam extensions, which the runtime already reads. Both sides had added a conflicting HTML filter; the reading family keeps the name, and the export path uses a narrow HTML_DOCUMENT, following the existing LATEX/TEX split. Runtime: main's file_data.rs is the base, including the prompt-injection sanitizer and the extraction routes. Token counting and chunk segmentation moved into take_released, so they act on the text the filter has released rather than on text it is still holding. A failed count is logged and left out instead of ending the extraction, because the app counts such a segment itself. Data sources: the participating-provider checks of this branch are kept, and main's GetAllowedDataSources overload now builds on them. DirectChatService resolves the launched chat's data source options before the check, so filter and chat see the same options. .NET and Rust both build clean; I18N regenerated to 4060 keys.
97 lines
4.5 KiB
C#
97 lines
4.5 KiB
C#
using System.Text;
|
|
|
|
using AIStudio.Agents;
|
|
using AIStudio.Chat;
|
|
using AIStudio.Provider;
|
|
using AIStudio.Settings;
|
|
using AIStudio.Tools.PluginSystem;
|
|
|
|
namespace AIStudio.Tools.RAG.AugmentationProcesses;
|
|
|
|
public sealed class AugmentationOne : IAugmentationProcess
|
|
{
|
|
private static readonly ILogger<AugmentationOne> LOGGER = Program.LOGGER_FACTORY.CreateLogger<AugmentationOne>();
|
|
|
|
private static string TB(string fallbackEN) => I18N.I.T(fallbackEN, typeof(AugmentationOne).Namespace, nameof(AugmentationOne));
|
|
|
|
#region Implementation of IAugmentationProcess
|
|
|
|
/// <inheritdoc />
|
|
public string TechnicalName => "AugmentationOne";
|
|
|
|
/// <inheritdoc />
|
|
public string UIName => TB("Standard augmentation process");
|
|
|
|
/// <inheritdoc />
|
|
public string Description => TB("This is the standard augmentation process, which uses all retrieval contexts to augment the chat thread.");
|
|
|
|
/// <inheritdoc />
|
|
public async Task<ChatThread> ProcessAsync(IProvider provider, IContent lastUserPrompt, ChatThread chatThread, IReadOnlyList<IRetrievalContext> retrievalContexts, CancellationToken token = default)
|
|
{
|
|
var settings = Program.SERVICE_PROVIDER.GetService<SettingsManager>()!;
|
|
|
|
if(retrievalContexts.Count == 0)
|
|
{
|
|
LOGGER.LogWarning("No retrieval contexts were issued. Skipping the augmentation process.");
|
|
return chatThread;
|
|
}
|
|
|
|
var numTotalRetrievalContexts = retrievalContexts.Count;
|
|
|
|
// Want the user to validate all retrieval contexts?
|
|
if (settings.ConfigurationData.AgentRetrievalContextValidation.EnableRetrievalContextValidation && chatThread.DataSourceOptions.AutomaticValidation)
|
|
{
|
|
// Let's get the validation agent & set up its provider:
|
|
var validationAgent = Program.SERVICE_PROVIDER.GetService<AgentRetrievalContextValidation>()!;
|
|
if (validationAgent.SetLLMProvider(provider, chatThread.DataSecurity, chatThread.RequiredProviderConfidence))
|
|
{
|
|
try
|
|
{
|
|
// Let's validate all retrieval contexts:
|
|
var validationResults = await validationAgent.ValidateRetrievalContextsAsync(lastUserPrompt, chatThread, retrievalContexts, token);
|
|
if (validationResults.Count == 0)
|
|
LOGGER.LogWarning("Retrieval context validation returned no results. Continuing augmentation with all retrieved contexts.");
|
|
else
|
|
{
|
|
//
|
|
// Now, filter the retrieval contexts to the most relevant ones:
|
|
//
|
|
var targetWindow = validationResults.DetermineTargetWindow(TargetWindowStrategy.TOP10_BETTER_THAN_GUESSING);
|
|
var threshold = validationResults.GetConfidenceThreshold(targetWindow);
|
|
|
|
// Filter the retrieval contexts:
|
|
retrievalContexts = validationResults.Where(x => x.RetrievalContext is not null && x.Confidence >= threshold).Select(x => x.RetrievalContext!).ToList();
|
|
}
|
|
}
|
|
catch (OperationCanceledException) when (token.IsCancellationRequested)
|
|
{
|
|
throw;
|
|
}
|
|
catch (Exception exception)
|
|
{
|
|
LOGGER.LogError(exception, "Retrieval context validation failed. Continuing augmentation with all retrieved contexts.");
|
|
}
|
|
}
|
|
else
|
|
LOGGER.LogWarning("Skipping retrieval context validation because no sufficiently trusted validation agent provider is available. Continuing augmentation with all retrieved contexts.");
|
|
}
|
|
|
|
LOGGER.LogInformation($"Starting the augmentation process over {retrievalContexts.Count:###,###,###,###} of {numTotalRetrievalContexts:###,###,###,###} retrieved contexts.");
|
|
|
|
//
|
|
// We build a huge prompt from all retrieval contexts:
|
|
//
|
|
var sb = new StringBuilder();
|
|
sb.AppendLine("The following useful information will help you in processing the user prompt:");
|
|
sb.AppendLine();
|
|
|
|
// Let's convert all retrieval contexts to Markdown:
|
|
await retrievalContexts.AsMarkdown(sb, token);
|
|
|
|
// Add the augmented data to the chat thread:
|
|
chatThread.AugmentedData = sb.ToString();
|
|
return chatThread;
|
|
}
|
|
|
|
#endregion
|
|
} |