This file contains example prompts for external LLMs (e.g., OpenAI, Anthropic, local models) to interact with Semem facilities via the MCP (Memory Control Protocol) server. These prompts are designed to help LLMs generate JSON-RPC requests that invoke Semem and Ragno pipeline services, including sea
Sign in to like and favorite skills
I want you to act as a composer. I will provide the lyrics to a song and you will create music for it. This could include using various instruments or tools, such as synthesizers or samplers, in order...
I want you to act as a philosopher. I will provide some topics or questions related to the study of philosophy, and it will be your job to explore these concepts in depth. This could involve conductin...
I want you to act as a personal trainer. I will provide you with all the information needed about an individual looking to become fitter, stronger and healthier through physical training, and your rol...
This file contains example prompts for external LLMs (e.g., OpenAI, Anthropic, local models) to interact with Semem facilities via the MCP (Memory Control Protocol) server. These prompts are designed to help LLMs generate JSON-RPC requests that invoke Semem and Ragno pipeline services, including search, augmentation, embedding, and community detection.
You are a memory agent. Given a user query, generate a JSON-RPC 2.0 request to the MCP server to perform a semantic search using the `searchGraph` method. Use the query as `queryText` and set `limit` to 5. Return only the JSON-RPC request.
Generate a JSON-RPC request to call the `callLLM` method on the MCP server. Use the following prompt: "Summarize the key findings from the provided context." Provide an empty context array. Use systemPrompt: "You are a helpful assistant."
Create a JSON-RPC request to the MCP server for the `embedText` method. The text to embed is: "Semantic memory enables contextual retrieval."
Formulate a JSON-RPC request to the MCP server using the `sparqlQuery` method. The query should select all distinct entities of type `ragno:Attribute` from the default graph. Use endpoint: "http://localhost:4030/semem/query" and basic auth: user "admin", password "admin123".
Given a JSON object representing a knowledge graph (entities, units, relationships), generate a JSON-RPC request for the `augmentGraph` method on the MCP server. The graph object should be passed as the `graph` parameter.
Generate a JSON-RPC request to the MCP server for the `discoverCommunities` method, passing a graph object as the `graph` parameter. The response should include detected communities and LLM-generated summaries.
searchGraphcallLLM