Store, index, and search documents with LLMemory in Python.
npx skills add https://github.com/juanre/llmemory --skill basic-usage
Please help me install this Agent Skill. Skill: basic-usage Source: https://github.com/juanre/llmemory/tree/main/skills/basic-usage Command: npx skills add https://github.com/juanre/llmemory --skill basic-usage
llmemory basic-usage provides a guided starting point for storing, indexing, and querying documents with a memory-backed, vector-enabled store, enabling developers to prototype and adopt document-centric workflows quickly.
Install LLMemory in a Python environment, configure a PostgreSQL+pgvector backend, initialize the schema, and begin by adding a document and performing a simple search to validate the setup.
High-intent search queries and answers about installing and using this skill.
You can store and search documents using PostgreSQL and pgvector by installing LLMemory, initializing the schema, adding documents via the add_document API, and executing vector or hybrid searches.
Yes, multi-tenant document repositories are supported. You can add, index, and query documents across distinct tenants using vector, text, and hybrid search APIs within your Python application.
Hybrid search combines semantic vector and text matching by calling the search API. This allows you to retrieve documents based on both embedding similarity and keyword filters across your stored chunks.
Yes, an external embedding provider is required. Semantic search relies on generating vector embeddings from your documents before storing and querying them in the PostgreSQL database with the pgvector extension.
Setting up a vector-enabled document store requires Python 3.10 or higher and PostgreSQL 14 or higher with the pgvector extension installed to support vector indexing and retrieval operations.
You can retrieve document metadata and statistics for RAG audits by calling the get_document, list_documents, and get_statistics APIs to query stored chunks and monitor repository usage across tenants.
NaveedTechLabManages PostgreSQL CRM database operations including Alembic migrations, identity resolution, ticket lifecycle, and pgvector search.
LLM-Dev-OpsPerform semantic vector search over large document collections with AgentDB.
patricio0312revAutomate document embedding pipelines for semantic search.
ccfCombine vector similarity with keyword matching for hybrid retrieval.
