diff --git a/src/InboxIntel.Application/Abstractions/IServices.cs b/src/InboxIntel.Application/Abstractions/IServices.cs
index 2f77901..60b4170 100644
--- a/src/InboxIntel.Application/Abstractions/IServices.cs
+++ b/src/InboxIntel.Application/Abstractions/IServices.cs
@@ -82,6 +82,25 @@ public interface IAiProvider
     Task<string> CompleteAsync(string systemPrompt, string userPrompt, CancellationToken ct = default);
 }
 
+/// <summary>
+/// Produces vector embeddings for text (the foundation for semantic search, near-duplicate
+/// detection, and "find similar"). Kept separate from <see cref="IAiProvider"/> because
+/// embeddings are a distinct capability with their own model. The Null implementation returns
+/// an empty vector and <see cref="IsAvailable"/> = false, so callers detect unavailability and
+/// fall back to lexical search — AI is never required for core functionality.
+/// </summary>
+public interface IEmbeddingProvider
+{
+    /// <summary>False for the Null provider (AI off / no embedding model configured).</summary>
+    bool IsAvailable { get; }
+
+    /// <summary>Embed a single text. Returns an empty array when unavailable.</summary>
+    Task<float[]> EmbedAsync(string text, CancellationToken ct = default);
+
+    /// <summary>Embed many texts, result aligned to input order. Empty list when unavailable.</summary>
+    Task<IReadOnlyList<float[]>> EmbedBatchAsync(IReadOnlyList<string> texts, CancellationToken ct = default);
+}
+
 public enum ExportFormat { Pdf, Csv, Json }
 
 public interface IExportService
diff --git a/src/InboxIntel.Infrastructure/Ai/AiProviders.cs b/src/InboxIntel.Infrastructure/Ai/AiProviders.cs
index 8908ac2..b1b05ec 100644
--- a/src/InboxIntel.Infrastructure/Ai/AiProviders.cs
+++ b/src/InboxIntel.Infrastructure/Ai/AiProviders.cs
@@ -2,6 +2,7 @@ using InboxIntel.Application.Abstractions;
 using InboxIntel.Domain.Enums;
 using InboxIntel.Infrastructure.Configuration;
 using Microsoft.Extensions.Options;
+using System.Linq;
 using System.Net.Http.Json;
 using System.Text.Json;
 
@@ -15,6 +16,53 @@ public class NullAiProvider : IAiProvider
         => Task.FromResult(string.Empty);
 }
 
+/// <summary>No-op embeddings used when AI is disabled. Returns empty vectors so callers fall
+/// back to lexical search.</summary>
+public class NullEmbeddingProvider : IEmbeddingProvider
+{
+    public bool IsAvailable => false;
+    public Task<float[]> EmbedAsync(string text, CancellationToken ct = default)
+        => Task.FromResult(Array.Empty<float>());
+    public Task<IReadOnlyList<float[]>> EmbedBatchAsync(IReadOnlyList<string> texts, CancellationToken ct = default)
+        => Task.FromResult<IReadOnlyList<float[]>>(Array.Empty<float[]>());
+}
+
+/// <summary>Local embeddings via Ollama's /api/embeddings endpoint (e.g. nomic-embed-text).</summary>
+public class OllamaEmbeddingProvider : IEmbeddingProvider
+{
+    private readonly HttpClient _http;
+    private readonly AiOptions _options;
+
+    public OllamaEmbeddingProvider(IHttpClientFactory factory, IOptions<AiOptions> options)
+    {
+        _options = options.Value;
+        _http = factory.CreateClient("ollama");
+        _http.BaseAddress = new Uri(_options.OllamaBaseUrl);
+    }
+
+    public bool IsAvailable => true;
+
+    public async Task<float[]> EmbedAsync(string text, CancellationToken ct = default)
+    {
+        var payload = new { model = _options.EmbeddingModel, prompt = text };
+        var resp = await _http.PostAsJsonAsync("/api/embeddings", payload, ct);
+        resp.EnsureSuccessStatusCode();
+        using var doc = JsonDocument.Parse(await resp.Content.ReadAsStringAsync(ct));
+        return doc.RootElement.GetProperty("embedding").EnumerateArray()
+            .Select(e => e.GetSingle()).ToArray();
+    }
+
+    // Ollama's /api/embeddings takes one prompt per call, so batch is a sequential loop.
+    // Kept behind the interface so a future batch endpoint is a drop-in swap.
+    public async Task<IReadOnlyList<float[]>> EmbedBatchAsync(IReadOnlyList<string> texts, CancellationToken ct = default)
+    {
+        var results = new List<float[]>(texts.Count);
+        foreach (var t in texts)
+            results.Add(await EmbedAsync(t, ct));
+        return results;
+    }
+}
+
 /// <summary>Local LLM via Ollama's /api/chat endpoint.</summary>
 public class OllamaProvider : IAiProvider
 {
diff --git a/src/InboxIntel.Infrastructure/Configuration/Options.cs b/src/InboxIntel.Infrastructure/Configuration/Options.cs
index 77786e2..3d155e9 100644
--- a/src/InboxIntel.Infrastructure/Configuration/Options.cs
+++ b/src/InboxIntel.Infrastructure/Configuration/Options.cs
@@ -43,6 +43,8 @@ public class AiOptions
     // Ollama (local)
     public string OllamaBaseUrl { get; set; } = "http://localhost:11434";
     public string OllamaModel { get; set; } = "llama3.1";
+    // Embedding model for semantic search (per docs/discovery/06). Small, always-on when local.
+    public string EmbeddingModel { get; set; } = "nomic-embed-text";
 
     // OpenAI (cloud, optional)
     public string OpenAiApiKey { get; set; } = string.Empty;
diff --git a/src/InboxIntel.Infrastructure/DependencyInjection.cs b/src/InboxIntel.Infrastructure/DependencyInjection.cs
index 6d5c30f..69e4338 100644
--- a/src/InboxIntel.Infrastructure/DependencyInjection.cs
+++ b/src/InboxIntel.Infrastructure/DependencyInjection.cs
@@ -67,13 +67,23 @@ public static class DependencyInjection
         services.AddHttpClient("ollama");
         services.AddHttpClient("openai");
 
-        // AI provider selected by configured mode.
+        // AI provider selected by configured mode. Embeddings come from Ollama when local,
+        // otherwise the Null provider (empty vectors) so semantic features degrade to lexical.
         var aiMode = config.GetSection(AiOptions.SectionName).GetValue<AiProviderMode>("Mode");
         switch (aiMode)
         {
-            case AiProviderMode.LocalOllama: services.AddScoped<IAiProvider, OllamaProvider>(); break;
-            case AiProviderMode.CloudOpenAi: services.AddScoped<IAiProvider, OpenAiProvider>(); break;
-            default: services.AddScoped<IAiProvider, NullAiProvider>(); break;
+            case AiProviderMode.LocalOllama:
+                services.AddScoped<IAiProvider, OllamaProvider>();
+                services.AddScoped<IEmbeddingProvider, OllamaEmbeddingProvider>();
+                break;
+            case AiProviderMode.CloudOpenAi:
+                services.AddScoped<IAiProvider, OpenAiProvider>();
+                services.AddScoped<IEmbeddingProvider, NullEmbeddingProvider>(); // OpenAI embeddings: future
+                break;
+            default:
+                services.AddScoped<IAiProvider, NullAiProvider>();
+                services.AddScoped<IEmbeddingProvider, NullEmbeddingProvider>();
+                break;
         }
         services.AddScoped<IAiService, AiService>();
 
diff --git a/tests/InboxIntel.UnitTests/EmbeddingProviderTests.cs b/tests/InboxIntel.UnitTests/EmbeddingProviderTests.cs
new file mode 100644
index 0000000..d4c7f3c
--- /dev/null
+++ b/tests/InboxIntel.UnitTests/EmbeddingProviderTests.cs
@@ -0,0 +1,23 @@
+using FluentAssertions;
+using InboxIntel.Infrastructure.Ai;
+using Xunit;
+
+namespace InboxIntel.UnitTests;
+
+/// <summary>
+/// The Null embedding provider is the AI-off / no-model path. Semantic features must be able
+/// to detect unavailability (IsAvailable=false) and fall back to lexical search — this locks
+/// that contract so "AI is never required" can't silently regress.
+/// </summary>
+public class EmbeddingProviderTests
+{
+    [Fact]
+    public async Task Null_provider_reports_unavailable_and_returns_empty_vectors()
+    {
+        var sut = new NullEmbeddingProvider();
+
+        sut.IsAvailable.Should().BeFalse();
+        (await sut.EmbedAsync("anything")).Should().BeEmpty();
+        (await sut.EmbedBatchAsync(new[] { "a", "b" })).Should().BeEmpty();
+    }
+}