Weaviate plugins

Build production-ready data engineering stacks: Airflow DAGs for orchestration, dbt models for transformations, scalable pipelines with Spark on cloud warehouses like BigQuery and Snowflake, Kafka streaming, optimized embeddings for RAG, and vector databases like Pinecone, Weaviate, and pgvector.

Build production LLM applications using expert strategies for context window management via summarization trimming routing and caching, RAG pipelines with chunking embeddings vector stores and agents, observability via Langfuse tracing evaluations, and retrieval optimization workflows.

Architect production-grade autonomous AI agents using bundled skills: design tool-using multi-agents with ReAct planning and safety, build stateful LangGraph systems with persistence and human-in-loop, implement optimized RAG pipelines, engineer prompts for reliability, evaluate via benchmarks and monitoring, and set up MCP servers for LLM-tool interactions.

Design secure multi-tenant RAG/CAG systems by selecting vector databases like Qdrant, Weaviate, Pinecone, PostgreSQL, or Redis, applying chunking strategies (fixed-size, semantic, recursive), and implementing security patterns for tenant isolation, access control, prompt injection prevention, and data classification.

Recover deleted Claude Code sessions, search past conversations via hybrid Postgres+Weaviate recall, list recent sessions, and ground AI code suggestions against indexed project symbols (tree-sitter across Python/TS/JS/Go/Rust/etc.), API routes (Express/FastAPI/Next.js), DB schemas (Prisma/Drizzle), env vars, flags, GraphQL types, and page paths to lint fabrications, suggest fixes, and rewrite with 89% hallucination reduction before disk writes.