feat: implement semantic search, knowledge unit extraction, and visualization components

This commit is contained in:
2026-05-03 15:59:30 +02:00
parent 94ecc7a404
commit 1f187b5125
24 changed files with 844 additions and 21 deletions
@@ -0,0 +1,41 @@
using System.ComponentModel.DataAnnotations;
using System.ComponentModel.DataAnnotations.Schema;
using NexusReader.Domain.Enums;
namespace NexusReader.Domain.Entities;
public class KnowledgeUnit
{
[Key]
[MaxLength(128)]
public string Id { get; set; } = string.Empty; // Hash(Source + Content + Version)
[Required]
[MaxLength(128)]
public string SourceId { get; set; } = string.Empty;
[Required]
[MaxLength(50)]
public string Version { get; set; } = "1.0";
[Required]
public KnowledgeUnitType Type { get; set; }
[Required]
public string Content { get; set; } = string.Empty;
public string? MetadataJson { get; set; } // e.g. { "page": 1, "path": "Chapter 1 > Intro" }
[Required]
[MaxLength(128)]
public string TenantId { get; set; } = string.Empty;
[Column(TypeName = "vector(768)")] // Default for text-embedding-004
public float[]? Vector { get; set; }
public DateTime CreatedAt { get; set; } = DateTime.UtcNow;
// Relationships
public ICollection<KnowledgeUnitLink> OutgoingLinks { get; set; } = new List<KnowledgeUnitLink>();
public ICollection<KnowledgeUnitLink> IncomingLinks { get; set; } = new List<KnowledgeUnitLink>();
}
@@ -0,0 +1,28 @@
using System.ComponentModel.DataAnnotations;
using System.ComponentModel.DataAnnotations.Schema;
namespace NexusReader.Domain.Entities;
public class KnowledgeUnitLink
{
[Key]
public int Id { get; set; }
[Required]
[MaxLength(128)]
public string SourceUnitId { get; set; } = string.Empty;
[Required]
[MaxLength(128)]
public string TargetUnitId { get; set; } = string.Empty;
[Required]
[MaxLength(50)]
public string RelationType { get; set; } = "References"; // e.g., "Next", "Defines", "Contains"
[ForeignKey(nameof(SourceUnitId))]
public KnowledgeUnit SourceUnit { get; set; } = null!;
[ForeignKey(nameof(TargetUnitId))]
public KnowledgeUnit TargetUnit { get; set; } = null!;
}
@@ -1,4 +1,5 @@
using System.ComponentModel.DataAnnotations;
using System.ComponentModel.DataAnnotations.Schema;
namespace NexusReader.Domain.Entities;
@@ -11,6 +12,9 @@ public class SemanticKnowledgeCache
[Required]
public string JsonData { get; set; } = string.Empty;
[Required]
public string OriginalText { get; set; } = string.Empty;
[Required]
[MaxLength(50)]
public string ModelId { get; set; } = "gemini-1.5-flash";
@@ -19,5 +23,12 @@ public class SemanticKnowledgeCache
[MaxLength(10)]
public string PromptVersion { get; set; } = "1.0";
[Required]
[MaxLength(128)]
public string TenantId { get; set; } = string.Empty;
[Column(TypeName = "vector(1536)")] // text-embedding-004 has 768 or 1536 dims, assuming 1536 for high-fidelity
public float[]? Vector { get; set; }
public DateTime CreatedAt { get; set; } = DateTime.UtcNow;
}
@@ -0,0 +1,12 @@
namespace NexusReader.Domain.Enums;
public enum KnowledgeUnitType
{
Section,
Table,
Definition,
ProcedureStep,
PolicyRule,
KeyConcept,
Snippet
}