Local RAG

Instructions

Implementation Reference

• src/server/index.ts:583-613 (handler)

  The MCP tool handler for 'list_files'. Calls vectorStore.listFiles(), enriches raw-data files with source information, and returns JSON-formatted list.
  * list_files tool handler * Enriches raw-data files with original source information */ async handleListFiles(): Promise<{ content: [{ type: 'text'; text: string }] }> { try { const files = await this.vectorStore.listFiles() // Enrich raw-data files with source information const enrichedFiles = files.map((file) => { if (isRawDataPath(file.filePath)) { const source = extractSourceFromPath(file.filePath) if (source) { return { ...file, source } } } return file }) return { content: [ { type: 'text', text: JSON.stringify(enrichedFiles, null, 2), }, ], } } catch (error) { console.error('Failed to list files:', error) throw error } }
• src/server/index.ts:276-281 (registration)

  Registers the 'list_files' tool in the MCP ListToolsRequestSchema handler, including name, description, and input schema.
  { name: 'list_files', description: 'List all ingested files in the vector database. Returns file paths and chunk counts for each document.', inputSchema: { type: 'object', properties: {} }, },
• src/server/index.ts:279-281 (schema)

  Input schema for 'list_files' tool: empty object (no parameters required).
  'List all ingested files in the vector database. Returns file paths and chunk counts for each document.', inputSchema: { type: 'object', properties: {} }, },
• src/vectordb/index.ts:556-599 (helper)

  Core implementation of listFiles() in VectorStore: queries all chunks from LanceDB, groups by filePath, counts chunks per file, selects latest timestamp per file.
  * Get list of ingested files * * @returns Array of file information */ async listFiles(): Promise<{ filePath: string; chunkCount: number; timestamp: string }[]> { if (!this.table) { return [] // Return empty array if table doesn't exist } try { // Retrieve all records const allRecords = await this.table.query().toArray() // Group by file path const fileMap = new Map<string, { chunkCount: number; timestamp: string }>() for (const record of allRecords) { const filePath = record.filePath as string const timestamp = record.timestamp as string if (fileMap.has(filePath)) { const fileInfo = fileMap.get(filePath) if (fileInfo) { fileInfo.chunkCount += 1 // Keep most recent timestamp if (timestamp > fileInfo.timestamp) { fileInfo.timestamp = timestamp } } } else { fileMap.set(filePath, { chunkCount: 1, timestamp }) } } // Convert Map to array of objects return Array.from(fileMap.entries()).map(([filePath, info]) => ({ filePath, chunkCount: info.chunkCount, timestamp: info.timestamp, })) } catch (error) { throw new DatabaseError('Failed to list files', error as Error) } }