MindWorkAI/AI-Studio
1
0 Fork 0
mirror of https://github.com/MindWorkAI/AI-Studio.git synced 2026-10-12 21:13:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into chunk-data

Browse Source 
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.
This commit is contained in:
Thorsten Sommer committed 2026-09-05 21:20:33 +02:00
2 parents d883e9d625 d043fbc8f0
commit fe35630eff
640 files changed
+45059 -4952
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

app/MindWork AI Studio/Provider/LLMProvidersExtensions.cs
+88 -24
View File
@@ -6,7 +6,10 @@ using AIStudio.Provider.Google;
using AIStudio.Provider.Groq;
using AIStudio.Provider.GWDG;
using AIStudio.Provider.Helmholtz;
using AIStudio.Provider.Hetzner;
using AIStudio.Provider.HuggingFace;
using AIStudio.Provider.IONOS;
using AIStudio.Provider.LiteLLM;
using AIStudio.Provider.Mistral;
using AIStudio.Provider.OpenAI;
using AIStudio.Provider.OpenRouter;
@@ -56,11 +59,14 @@ public static class LLMProvidersExtensions
LLMProviders.ALIBABA_CLOUD => "Alibaba Cloud",
LLMProviders.PERPLEXITY => "Perplexity",
LLMProviders.OPEN_ROUTER => "OpenRouter",
LLMProviders.HETZNER => "Hetzner (Experimental)",
LLMProviders.IONOS => "IONOS",
LLMProviders.LITE_LLM => "LiteLLM",
LLMProviders.GROQ => "Groq",
LLMProviders.FIREWORKS => "Fireworks.ai",
LLMProviders.HUGGINGFACE => "Hugging Face",
LLMProviders.SELF_HOSTED => translate ? TB("Self-hosted") : "Self-hosted",
LLMProviders.HELMHOLTZ => "Helmholtz Blablador",
@@ -91,6 +97,9 @@ public static class LLMProvidersExtensions
LLMProviders.ALIBABA_CLOUD => "Alibaba Cloud",
LLMProviders.PERPLEXITY => "Perplexity",
LLMProviders.OPEN_ROUTER => "OpenRouter",
LLMProviders.HETZNER => "Hetzner",
LLMProviders.IONOS => "IONOS",
LLMProviders.LITE_LLM => "LiteLLM",
LLMProviders.GROQ => "Groq",
LLMProviders.FIREWORKS => "Fireworks.ai",
@@ -144,6 +153,23 @@ public static class LLMProvidersExtensions
LLMProviders.OPEN_ROUTER => Confidence.USA_HUB.WithRegion("America, U.S.").WithSources("https://openrouter.ai/privacy", "https://openrouter.ai/terms").WithLevel(settingsManager.GetConfiguredConfidenceLevel(llmProvider)),
LLMProviders.HETZNER => Confidence.GDPR_EXPERIMENTAL_OPEN_SOURCE.WithRegion("Europe, Germany").WithSources(
"https://experiments.hetzner.com/docs/inference",
"https://www.hetzner.com/legal/privacy-policy/",
"https://www.hetzner.com/legal/terms-and-conditions/"
).WithLevel(settingsManager.GetConfiguredConfidenceLevel(llmProvider)),
LLMProviders.IONOS => Confidence.GDPR_NO_TRAINING.WithRegion("Europe, Germany").WithSources(
"https://docs.ionos.com/cloud/ai/ai-model-hub/governance-and-compliance/data-handling",
"https://www.ionos.com/terms-gtc/privacy-policy/"
).WithLevel(settingsManager.GetConfiguredConfidenceLevel(llmProvider)),
// LiteLLM is a gateway the user runs, but it is not a self-hosted LLM: the proxy owner decides
// which downstream providers it routes to, and those are usually cloud services. Self-hosting
// the proxy therefore says nothing about where the data ends up, so we do not claim the trust
// of a self-hosted model here and let the user assign the level themselves.
LLMProviders.LITE_LLM => Confidence.USER_OPERATED_GATEWAY.WithSources("https://docs.litellm.ai/docs/data_security").WithLevel(settingsManager.GetConfiguredConfidenceLevel(llmProvider)),
LLMProviders.SELF_HOSTED => Confidence.SELF_HOSTED.WithLevel(settingsManager.GetConfiguredConfidenceLevel(llmProvider)),
LLMProviders.HELMHOLTZ => Confidence.GDPR_NO_TRAINING.WithRegion("Europe, Germany").WithSources("https://helmholtz.cloud/services/?serviceID=d7d5c597-a2f6-4bd1-b71e-4d6499d98570").WithLevel(settingsManager.GetConfiguredConfidenceLevel(llmProvider)),
@@ -167,7 +193,11 @@ public static class LLMProvidersExtensions
LLMProviders.GOOGLE => true,
LLMProviders.HELMHOLTZ => true,
LLMProviders.ALIBABA_CLOUD => true,
LLMProviders.IONOS => true,
LLMProviders.GWDG => true,
LLMProviders.OPEN_ROUTER => true,
LLMProviders.LITE_LLM => true,
//
// Providers that do not support embeddings:
//
@@ -175,20 +205,26 @@ public static class LLMProvidersExtensions
LLMProviders.ANTHROPIC => false,
LLMProviders.FIREWORKS => false,
LLMProviders.X => false,
LLMProviders.GWDG => false,
LLMProviders.DEEP_SEEK => false,
LLMProviders.HUGGINGFACE => false,
LLMProviders.PERPLEXITY => false,
LLMProviders.OPEN_ROUTER => true,
LLMProviders.HETZNER => false,
//
// Hugging Face serves embeddings, but not through the router endpoint we chat with: that
// one answers "/v1/embeddings" with a plain "Not Found". They have to be asked of one
// inference provider directly, and only some of them answer the OpenAI-compatible form.
// Which ones is decided by HFInferenceProviderExtensions.SupportsEmbeddings.
//
LLMProviders.HUGGINGFACE => true,
//
// Self-hosted providers are treated as a special case anyway.
//
LLMProviders.SELF_HOSTED => true,
_ => false,
};
public static bool ProvideTranscriptionAPI(this LLMProviders llmProvider) => llmProvider switch
{
//
@@ -198,7 +234,10 @@ public static class LLMProvidersExtensions
LLMProviders.MISTRAL => true,
LLMProviders.FIREWORKS => true,
LLMProviders.GWDG => true,
LLMProviders.HELMHOLTZ => true,
LLMProviders.GROQ => true,
LLMProviders.LITE_LLM => true,
//
// Providers that support transcription but provide no OpenAI-compatible API yet:
//
@@ -209,20 +248,26 @@ public static class LLMProvidersExtensions
// Providers that do not support transcription:
//
LLMProviders.OPEN_ROUTER => false,
LLMProviders.GROQ => false,
LLMProviders.HETZNER => false,
LLMProviders.IONOS => false,
LLMProviders.ANTHROPIC => false,
LLMProviders.X => false,
LLMProviders.DEEP_SEEK => false,
LLMProviders.HUGGINGFACE => false,
LLMProviders.PERPLEXITY => false,
LLMProviders.HELMHOLTZ => false,
//
// Hugging Face transcribes audio, but like embeddings, not through the router endpoint we
// chat with: that one answers "/v1/audio/transcriptions" with a plain "Not Found". Only
// some of the inference providers answer the OpenAI-compatible form, which
// HFInferenceProviderExtensions.SupportsTranscription decides.
//
LLMProviders.HUGGINGFACE => true,
//
// Self-hosted providers are treated as a special case anyway.
//
LLMProviders.SELF_HOSTED => true,
_ => false,
};
@@ -233,7 +278,7 @@ public static class LLMProvidersExtensions
/// <returns>The provider instance.</returns>
public static IProvider CreateProvider(this AIStudio.Settings.Provider providerSettings)
{
return providerSettings.UsedLLMProvider.CreateProvider(providerSettings.InstanceName, providerSettings.Host, providerSettings.Hostname, providerSettings.Model, providerSettings.HFInferenceProvider, providerSettings.Id, providerSettings.AdditionalJsonApiParameters, tokenizerPath: providerSettings.TokenizerPath, providerSettings.IsEnterpriseConfiguration);
return providerSettings.UsedLLMProvider.CreateProvider(providerSettings.InstanceName, providerSettings.Host, providerSettings.Hostname, providerSettings.HFInferenceProvider, providerSettings.Id, providerSettings.AdditionalJsonApiParameters, providerSettings.IsEnterpriseConfiguration, capabilityOverrides: providerSettings.CapabilityOverrides, tokenizerPath: providerSettings.TokenizerPath);
}
/// <summary>
@@ -243,7 +288,7 @@ public static class LLMProvidersExtensions
/// <returns>The provider instance.</returns>
public static IProvider CreateProvider(this EmbeddingProvider embeddingProviderSettings)
{
return embeddingProviderSettings.UsedLLMProvider.CreateProvider(embeddingProviderSettings.Name, embeddingProviderSettings.Host, embeddingProviderSettings.Hostname, embeddingProviderSettings.Model, HFInferenceProvider.NONE, configuredProviderId: embeddingProviderSettings.Id, tokenizerPath: embeddingProviderSettings.TokenizerPath, isEnterpriseConfiguration: embeddingProviderSettings.IsEnterpriseConfiguration);
return embeddingProviderSettings.UsedLLMProvider.CreateProvider(embeddingProviderSettings.Name, embeddingProviderSettings.Host, embeddingProviderSettings.Hostname, embeddingProviderSettings.HFInferenceProvider, configuredProviderId: embeddingProviderSettings.Id, isEnterpriseConfiguration: embeddingProviderSettings.IsEnterpriseConfiguration, hfEndpointKind: HFEndpointKind.EMBEDDING, tokenizerPath: embeddingProviderSettings.TokenizerPath);
}
/// <summary>
@@ -253,14 +298,14 @@ public static class LLMProvidersExtensions
/// <returns>The provider instance.</returns>
public static IProvider CreateProvider(this TranscriptionProvider transcriptionProviderSettings)
{
return transcriptionProviderSettings.UsedLLMProvider.CreateProvider(transcriptionProviderSettings.Name, transcriptionProviderSettings.Host, transcriptionProviderSettings.Hostname, transcriptionProviderSettings.Model, HFInferenceProvider.NONE, configuredProviderId: transcriptionProviderSettings.Id, tokenizerPath: string.Empty, isEnterpriseConfiguration: transcriptionProviderSettings.IsEnterpriseConfiguration);
return transcriptionProviderSettings.UsedLLMProvider.CreateProvider(transcriptionProviderSettings.Name, transcriptionProviderSettings.Host, transcriptionProviderSettings.Hostname, transcriptionProviderSettings.HFInferenceProvider, configuredProviderId: transcriptionProviderSettings.Id, isEnterpriseConfiguration: transcriptionProviderSettings.IsEnterpriseConfiguration, hfEndpointKind: HFEndpointKind.TRANSCRIPTION);
}
private static IProvider CreateProvider(this LLMProviders provider, string instanceName, Host host, string hostname, Model model, HFInferenceProvider inferenceProvider, string configuredProviderId = "", string expertProviderApiParameter = "", string tokenizerPath = "", bool isEnterpriseConfiguration = false)
private static IProvider CreateProvider(this LLMProviders provider, string instanceName, Host host, string hostname, HFInferenceProvider inferenceProvider, string configuredProviderId = "", string expertProviderApiParameter = "", bool isEnterpriseConfiguration = false, HFEndpointKind hfEndpointKind = HFEndpointKind.CHAT, ProviderCapabilityOverrides? capabilityOverrides = null, string tokenizerPath = "")
{
try
{
return provider switch
IProvider providerInstance = provider switch
{
LLMProviders.OPEN_AI => new ProviderOpenAI { InstanceName = instanceName, ConfiguredProviderId = configuredProviderId, AdditionalJsonApiParameters = expertProviderApiParameter, TokenizerPath = tokenizerPath, IsEnterpriseConfiguration = isEnterpriseConfiguration },
LLMProviders.ANTHROPIC => new ProviderAnthropic { InstanceName = instanceName, ConfiguredProviderId = configuredProviderId, AdditionalJsonApiParameters = expertProviderApiParameter, TokenizerPath = tokenizerPath, IsEnterpriseConfiguration = isEnterpriseConfiguration },
@@ -271,10 +316,13 @@ public static class LLMProvidersExtensions
LLMProviders.ALIBABA_CLOUD => new ProviderAlibabaCloud { InstanceName = instanceName, ConfiguredProviderId = configuredProviderId, AdditionalJsonApiParameters = expertProviderApiParameter, TokenizerPath = tokenizerPath, IsEnterpriseConfiguration = isEnterpriseConfiguration },
LLMProviders.PERPLEXITY => new ProviderPerplexity { InstanceName = instanceName, ConfiguredProviderId = configuredProviderId, AdditionalJsonApiParameters = expertProviderApiParameter, TokenizerPath = tokenizerPath, IsEnterpriseConfiguration = isEnterpriseConfiguration },
LLMProviders.OPEN_ROUTER => new ProviderOpenRouter { InstanceName = instanceName, ConfiguredProviderId = configuredProviderId, AdditionalJsonApiParameters = expertProviderApiParameter, TokenizerPath = tokenizerPath, IsEnterpriseConfiguration = isEnterpriseConfiguration },
LLMProviders.HETZNER => new ProviderHetzner { InstanceName = instanceName, ConfiguredProviderId = configuredProviderId, AdditionalJsonApiParameters = expertProviderApiParameter, TokenizerPath = tokenizerPath, IsEnterpriseConfiguration = isEnterpriseConfiguration },
LLMProviders.IONOS => new ProviderIONOS { InstanceName = instanceName, ConfiguredProviderId = configuredProviderId, AdditionalJsonApiParameters = expertProviderApiParameter, TokenizerPath = tokenizerPath, IsEnterpriseConfiguration = isEnterpriseConfiguration },
LLMProviders.LITE_LLM => new ProviderLiteLLM(hostname) { InstanceName = instanceName, ConfiguredProviderId = configuredProviderId, AdditionalJsonApiParameters = expertProviderApiParameter, TokenizerPath = tokenizerPath, IsEnterpriseConfiguration = isEnterpriseConfiguration },
LLMProviders.GROQ => new ProviderGroq { InstanceName = instanceName, ConfiguredProviderId = configuredProviderId, AdditionalJsonApiParameters = expertProviderApiParameter, TokenizerPath = tokenizerPath, IsEnterpriseConfiguration = isEnterpriseConfiguration },
LLMProviders.FIREWORKS => new ProviderFireworks { InstanceName = instanceName, ConfiguredProviderId = configuredProviderId, AdditionalJsonApiParameters = expertProviderApiParameter, TokenizerPath = tokenizerPath, IsEnterpriseConfiguration = isEnterpriseConfiguration },
LLMProviders.HUGGINGFACE => new ProviderHuggingFace(inferenceProvider, model) { InstanceName = instanceName, ConfiguredProviderId = configuredProviderId, AdditionalJsonApiParameters = expertProviderApiParameter, TokenizerPath = tokenizerPath, IsEnterpriseConfiguration = isEnterpriseConfiguration },
LLMProviders.HUGGINGFACE => new ProviderHuggingFace(inferenceProvider, hfEndpointKind) { InstanceName = instanceName, ConfiguredProviderId = configuredProviderId, AdditionalJsonApiParameters = expertProviderApiParameter, TokenizerPath = tokenizerPath, IsEnterpriseConfiguration = isEnterpriseConfiguration },
LLMProviders.SELF_HOSTED => new ProviderSelfHosted(host, hostname) { InstanceName = instanceName, ConfiguredProviderId = configuredProviderId, AdditionalJsonApiParameters = expertProviderApiParameter, TokenizerPath = tokenizerPath, IsEnterpriseConfiguration = isEnterpriseConfiguration },
@@ -283,6 +331,11 @@ public static class LLMProvidersExtensions
_ => new NoProvider(),
};
if (providerInstance is BaseProvider baseProvider)
baseProvider.CapabilityOverrides = capabilityOverrides;
return providerInstance;
}
catch (Exception e)
{
@@ -302,6 +355,8 @@ public static class LLMProvidersExtensions
LLMProviders.ALIBABA_CLOUD => "https://account.alibabacloud.com/register/intl_register.htm",
LLMProviders.PERPLEXITY => "https://www.perplexity.ai/account/api",
LLMProviders.OPEN_ROUTER => "https://openrouter.ai/keys",
LLMProviders.HETZNER => "https://experiments.hetzner.com",
LLMProviders.IONOS => "https://cloud.ionos.com/compute/sign-up",
LLMProviders.GROQ => "https://console.groq.com/",
LLMProviders.FIREWORKS => "https://fireworks.ai/login",
@@ -327,6 +382,8 @@ public static class LLMProvidersExtensions
LLMProviders.PERPLEXITY => "https://www.perplexity.ai/account/api/",
LLMProviders.OPEN_ROUTER => "https://openrouter.ai/activity",
LLMProviders.HUGGINGFACE => "https://huggingface.co/settings/billing",
LLMProviders.HETZNER => "https://experiments.hetzner.com",
LLMProviders.IONOS => "https://dcd.ionos.com/latest/?page=dcd-ai-model-hub",
_ => string.Empty,
};
@@ -345,6 +402,8 @@ public static class LLMProvidersExtensions
LLMProviders.PERPLEXITY => true,
LLMProviders.OPEN_ROUTER => true,
LLMProviders.HUGGINGFACE => true,
LLMProviders.HETZNER => true,
LLMProviders.IONOS => true,
_ => false,
};
@@ -352,14 +411,13 @@ public static class LLMProvidersExtensions
public static string GetModelsOverviewURL(this LLMProviders provider, HFInferenceProvider inferenceProvider) => provider switch
{
LLMProviders.FIREWORKS => "https://fireworks.ai/models?show=Serverless",
LLMProviders.HUGGINGFACE => $"https://huggingface.co/models?inference_provider={inferenceProvider.EndpointsId()}",
LLMProviders.HUGGINGFACE => $"https://huggingface.co/models?inference_provider={inferenceProvider.CatalogFilter()}",
_ => string.Empty,
};
public static bool IsLLMModelProvidedManually(this LLMProviders provider) => provider switch
{
LLMProviders.FIREWORKS => true,
LLMProviders.HUGGINGFACE => true,
_ => false,
};
@@ -408,6 +466,7 @@ public static class LLMProvidersExtensions
public static bool IsHostnameNeeded(this LLMProviders provider) => provider switch
{
LLMProviders.SELF_HOSTED => true,
LLMProviders.LITE_LLM => true,
_ => false,
};
@@ -422,15 +481,18 @@ public static class LLMProvidersExtensions
LLMProviders.ALIBABA_CLOUD => true,
LLMProviders.PERPLEXITY => true,
LLMProviders.OPEN_ROUTER => true,
LLMProviders.HETZNER => true,
LLMProviders.IONOS => true,
LLMProviders.LITE_LLM => true,
LLMProviders.GROQ => true,
LLMProviders.FIREWORKS => true,
LLMProviders.HELMHOLTZ => true,
LLMProviders.GWDG => true,
LLMProviders.HUGGINGFACE => true,
LLMProviders.SELF_HOSTED => host is (Host.OLLAMA or Host.VLLM),
_ => false,
};
@@ -445,6 +507,8 @@ public static class LLMProvidersExtensions
LLMProviders.ALIBABA_CLOUD => true,
LLMProviders.PERPLEXITY => true,
LLMProviders.OPEN_ROUTER => true,
LLMProviders.HETZNER => true,
LLMProviders.IONOS => true,
LLMProviders.GROQ => true,
LLMProviders.FIREWORKS => true,