add_books_to_project

Instructions

Implementation Reference

• server.js:604-710 (handler)

  The core handler function that processes books for a RAG project: fetches metadata, extracts content (txt or OCR), intelligently chunks it, generates embeddings, saves vectors and metadata, and updates project config.

  async addBooksToProject(projectName, bookIds) {
      const project = this.projects.get(projectName);
      if (!project) {
          throw new Error(`Project '${projectName}' not found`);
      }
      
      const projectPath = path.join(CONFIG.RAG.PROJECTS_DIR, projectName);
      const chunksPath = path.join(projectPath, 'chunks');
      const vectorsPath = path.join(projectPath, 'vectors.bin');
      const metadataPath = path.join(projectPath, 'metadata.json');
      
      // Get book metadata
      const idQuery = `id:${bookIds.join(' OR id:')}`;
      const listResult = await this.runCalibreCommand([
          'list',
          '--fields', 'id,title,authors,formats',
          '--for-machine',
          '--search', idQuery
      ]);
      
      const books = JSON.parse(listResult || '[]');
      const allChunks = [];
      const allVectors = [];
      const allMetadata = [];
      
      for (const book of books) {
          this.log(`Processing book: ${book.title}`);
          
          let content = '';
          let contentSource = 'unknown';
          
          // Try text format first
          const txtPath = book.formats?.find(f => f.endsWith('.txt'));
          if (txtPath && fs.existsSync(txtPath)) {
              this.log(`Using text format: ${txtPath}`);
              content = fs.readFileSync(txtPath, 'utf8');
              contentSource = 'text';
          } else {
              // Fallback to OCR
              this.log(`No text format available for: ${book.title}, trying OCR...`);
              content = await this.processBookWithOCR(book);
              contentSource = 'ocr';
              
              if (!content || content.trim().length === 0) {
                  this.log(`OCR failed or no content extracted for: ${book.title}`);
                  continue;
              }
          }
          
          // Read and chunk content
          const bookMetadata = {
              book_id: book.id,
              title: book.title,
              authors: book.authors,
              project: projectName,
              content_source: contentSource,
              content_length: content.length
          };
          
          const chunks = this.intelligentChunk(content, bookMetadata);
          
          // Generate embeddings for chunks
          for (const chunk of chunks) {
              try {
                  const embedding = await this.generateEmbedding(chunk.text);
                  
                  allChunks.push(chunk);
                  allVectors.push(embedding);
                  allMetadata.push(chunk.metadata);
                  
                  // Save individual chunk
                  fs.writeFileSync(
                      path.join(chunksPath, `${chunk.id}.json`),
                      JSON.stringify(chunk, null, 2)
                  );
                  
                  this.log(`Processed chunk ${chunk.id} from ${book.title}`);
              } catch (error) {
                  this.log(`Failed to process chunk ${chunk.id}: ${error.message}`);
              }
          }
      }
      
      // Save vectors and metadata
      if (allVectors.length > 0) {
          this.saveVectors(vectorsPath, allVectors);
          fs.writeFileSync(metadataPath, JSON.stringify(allMetadata, null, 2));
          
          // Update project config
          project.books = [...new Set([...project.books, ...bookIds])];
          project.chunk_count = allChunks.length;
          project.last_updated = new Date().toISOString();
          
          fs.writeFileSync(
              path.join(projectPath, 'project.json'),
              JSON.stringify(project, null, 2)
          );
          
          this.projects.set(projectName, project);
      }
      
      return {
          processed_books: books.length,
          total_chunks: allChunks.length,
          project: project
      };
  }

• server.js:1033-1047 (schema)

  JSON schema defining the input parameters for the 'add_books_to_project' tool: project_name (string) and book_ids (array of integers).

  inputSchema: {
      type: 'object',
      properties: {
          project_name: {
              type: 'string',
              description: 'Name of the project'
          },
          book_ids: {
              type: 'array',
              items: { type: 'integer' },
              description: 'Array of book IDs to add to the project'
          }
      },
      required: ['project_name', 'book_ids']
  }

• server.js:1165-1186 (registration)

  Registration and dispatch logic in the tools/call handler: validates arguments, calls the addBooksToProject method, and sends success/error responses.

  case 'add_books_to_project':
      const projName = args.project_name;
      const bookIds = args.book_ids;
      
      if (!projName || !bookIds) {
          this.sendError(id, -32602, 'Missing required parameters: project_name, book_ids');
          return;
      }
      
      try {
          const result = await this.addBooksToProject(projName, bookIds);
          this.sendSuccess(id, {
              content: [{
                  type: 'text',
                  text: `Successfully processed ${result.processed_books} books and created ${result.total_chunks} chunks for project '${projName}'.\n\nProject is now ready for context search!`
              }],
              result: result
          });
      } catch (error) {
          this.sendError(id, -32603, error.message);
      }
      break;

• server.js:1030-1048 (registration)

  Tool registration in the tools/list response, including name, description, and input schema.

  {
      name: 'add_books_to_project',
      description: 'Add books to a RAG project for vectorization and context search',
      inputSchema: {
          type: 'object',
          properties: {
              project_name: {
                  type: 'string',
                  description: 'Name of the project'
              },
              book_ids: {
                  type: 'array',
                  items: { type: 'integer' },
                  description: 'Array of book IDs to add to the project'
              }
          },
          required: ['project_name', 'book_ids']
      }
  },