From 0e98320d3b237f1927b9f1367494dccd7f66eda9 Mon Sep 17 00:00:00 2001 From: "A.J. Shulman" Date: Wed, 21 May 2025 12:38:55 -0400 Subject: Added codebase search and retrieval to Vectorstore Summary indexing: Added functionality to embed and index file summaries from file_summaries.json in Pinecone Vector search: Implemented semantic search to find the top 5 most relevant files for a query Content retrieval: Added method to fetch full file content from file_content.json API endpoints: /getFileSummaries - Retrieves all file summaries /getFileContent - Fetches file content by path /getRawFileContent - Returns content as plain text to avoid JSON parsing errors Error handling: Added comprehensive error handling and debugging throughout Initialization: Implemented proper async initialization sequence with verification Performance: Added streaming for large files to improve memory efficiency Testing: Added automated test queries to validate functionality --- src/client/views/nodes/chatbot/tools/RAGTool.ts | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'src/client/views/nodes/chatbot/tools/RAGTool.ts') diff --git a/src/client/views/nodes/chatbot/tools/RAGTool.ts b/src/client/views/nodes/chatbot/tools/RAGTool.ts index 90b803d21..af44de520 100644 --- a/src/client/views/nodes/chatbot/tools/RAGTool.ts +++ b/src/client/views/nodes/chatbot/tools/RAGTool.ts @@ -12,6 +12,12 @@ const ragToolParams = [ description: "A detailed prompt representing an ideal chunk to embed and compare against document vectors to retrieve the most relevant content for answering the user's query.", required: true, }, + { + name: 'doc_ids', + type: 'string[]', + description: 'An optional array of document IDs to retrieve chunks from. If you want to retrieve chunks from all documents, leave this as an empty array: [] (DO NOT LEAVE THIS EMPTY).', + required: false, + }, ] as const; type RAGToolParamsType = typeof ragToolParams; @@ -69,7 +75,7 @@ export class RAGTool extends BaseTool { } async execute(args: ParametersType): Promise { - const relevantChunks = await this.vectorstore.retrieve(args.hypothetical_document_chunk); + const relevantChunks = await this.vectorstore.retrieve(args.hypothetical_document_chunk, undefined, args.doc_ids ?? undefined); const formattedChunks = await this.getFormattedChunks(relevantChunks); return formattedChunks; } -- cgit v1.2.3-70-g09d2