learn_context
Store preferences, rules, or context to reuse later, reducing token cost and enriching future prompts.
Instructions
Memorizes important information (preference, technical rule, context) for future use.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| information | Yes | The information to be remembered. | |
| category | No | Information category (e.g., 'preference', 'architecture', 'style'). |
Implementation Reference
- src/index.ts:89-108 (registration)Tool registration for 'learn_context' with description and inputSchema (information: string, category: optional string)
{ name: "learn_context", description: "Memorizes important information (preference, technical rule, context) for future use.", inputSchema: { type: "object", properties: { information: { type: "string", description: "The information to be remembered.", }, category: { type: "string", description: "Information category (e.g., 'preference', 'architecture', 'style').", }, }, required: ["information"], }, }, ], }; - src/index.ts:114-136 (handler)Handler for 'learn_context' tool: extracts 'information' and optional 'category' args, generates an embedding via Ollama, stores the vector + text + category + timestamp into a LanceDB table, and returns a confirmation message.
if (name === "learn_context") { const info = args?.information as string; const category = (args?.category as string) || "general"; const vector = await getEmbedding(info); const data = [{ vector, text: info, category, timestamp: new Date().toISOString() }]; if (!table) { table = await db.createTable(TABLE_NAME, data); } else { await table.add(data); } return { content: [{ type: "text", text: `Learned and stored in semantic memory: "${info}"` }], }; } - src/index.ts:52-58 (helper)getEmbedding helper function that calls Ollama's embed API with 'nomic-embed-text' model to convert text to a vector.
async function getEmbedding(text: string): Promise<number[]> { const response = await ollama.embed({ model: EMBEDDING_MODEL, input: text, }); return response.embeddings[0]!; }