feat(server): attachment embedding (#13348)

<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

* **New Features**
* Added support for managing "blobs" in Copilot context, including
adding and removing blobs via new GraphQL mutations and UI fields.
* Introduced tracking and querying of blob embeddings within workspaces,
enabling search and similarity matching for blob content.
* Extended Copilot context and workspace APIs, schema, and UI to display
and manage blobs alongside existing documents and files.

* **Bug Fixes**
* Updated context and embedding status logic to handle blobs, ensuring
accurate status reporting and embedding management.

* **Tests**
* Added and updated test cases and snapshots to cover blob embedding
insertion, matching, and removal scenarios.

* **Documentation**
* Updated GraphQL schema and TypeScript types to reflect new
blob-related fields and mutations.

* **Chores**
* Refactored and cleaned up code to support new blob entity and
embedding logic, including renaming and updating internal methods and
types.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

packages/backend/server/src/plugins/copilot/embedding/job.ts

@@ -65,15 +65,14 @@ export class CopilotEmbeddingJob {
   async addFileEmbeddingQueue(file: Jobs['copilot.embedding.files']) {
     if (!this.supportEmbedding) return;
 
-    const { userId, workspaceId, contextId, blobId, fileId, fileName } = file;
-    await this.queue.add('copilot.embedding.files', {
-      userId,
-      workspaceId,
-      contextId,
-      blobId,
-      fileId,
-      fileName,
-    });
+    await this.queue.add('copilot.embedding.files', file);
+  }
+
+  @CallMetric('ai', 'addBlobEmbeddingQueue')
+  async addBlobEmbeddingQueue(blob: Jobs['copilot.embedding.blobs']) {
+    if (!this.supportEmbedding) return;
+
+    await this.queue.add('copilot.embedding.blobs', blob);
   }
 
   @OnEvent('workspace.doc.embedding')
@@ -288,6 +287,55 @@ export class CopilotEmbeddingJob {
     }
   }
 
+  @OnJob('copilot.embedding.blobs')
+  async embedPendingBlob({
+    userId,
+    workspaceId,
+    contextId,
+    blobId,
+  }: Jobs['copilot.embedding.blobs']) {
+    if (!this.supportEmbedding || !this.embeddingClient) return;
+
+    try {
+      const file = await this.readCopilotBlob(
+        userId,
+        workspaceId,
+        blobId,
+        'blob'
+      );
+
+      const chunks = await this.embeddingClient.getFileChunks(file);
+      const total = chunks.reduce((acc, c) => acc + c.length, 0);
+
+      for (const chunk of chunks) {
+        const embeddings = await this.embeddingClient.generateEmbeddings(chunk);
+        await this.models.copilotWorkspace.insertBlobEmbeddings(
+          workspaceId,
+          blobId,
+          embeddings
+        );
+      }
+
+      if (contextId) {
+        this.event.emit('workspace.blob.embed.finished', {
+          contextId,
+          blobId,
+          chunkSize: total,
+        });
+      }
+    } catch (error: any) {
+      if (contextId) {
+        this.event.emit('workspace.blob.embed.failed', {
+          contextId,
+          blobId,
+          error: mapAnyError(error).message,
+        });
+      }
+
+      throw error;
+    }
+  }
+
   private async getDocFragment(
     workspaceId: string,
     docId: string
@@ -465,7 +513,7 @@ export class CopilotEmbeddingJob {
 
     const docIdsInWorkspace = readAllDocIdsFromWorkspaceSnapshot(snapshot.blob);
     const docIdsInEmbedding =
-      await this.models.copilotContext.listWorkspaceEmbedding(workspaceId);
+      await this.models.copilotContext.listWorkspaceDocEmbedding(workspaceId);
     const docIdsInWorkspaceSet = new Set(docIdsInWorkspace);
 
     const deletedDocIds = docIdsInEmbedding.filter(

packages/backend/server/src/plugins/copilot/embedding/types.ts

@@ -14,6 +14,18 @@ declare global {
       enableDocEmbedding?: boolean;
     };
 
+    'workspace.blob.embed.finished': {
+      contextId: string;
+      blobId: string;
+      chunkSize: number;
+    };
+
+    'workspace.blob.embed.failed': {
+      contextId: string;
+      blobId: string;
+      error: string;
+    };
+
     'workspace.doc.embedding': Array<{
       workspaceId: string;
       docId: string;
@@ -62,6 +74,13 @@ declare global {
       fileName: string;
     };
 
+    'copilot.embedding.blobs': {
+      contextId?: string;
+      userId: string;
+      workspaceId: string;
+      blobId: string;
+    };
+
     'copilot.embedding.cleanupTrashedDocEmbeddings': {
       workspaceId: string;
     };