Zilliz
Official@zilliztech · United States of America
Vector Database for Enterprise-grade AI and LLM applications
Agent Skills by Zilliz
Showing 32 vetted skills indexed across 4 GitHub repositories.
zilliztechmemory-recall
Search and recall past conversation memories via progressive semantic retrieval.
zilliztechmemory-config
Diagnose and configure MemSearch memory settings across five AI coding agent platforms.
zilliztechmemory-recall
Search and retrieve relevant memories from past sessions.
zilliztechmemory-config
Manage MemSearch configuration settings and maintenance for Claude Code.
zilliztechmemory-to-skill
Convert MemSearch memory workflows into reusable installable skills.
zilliztechmilvus
Manage Milvus collections and perform vector, hybrid, and BM25 searches via pymilvus.
zilliztechzilliz-launchpad
Ingest documents and index them in Milvus or Zilliz Cloud.
zilliztechchat-memory
Store and retrieve past chatbot conversations across sessions using vector memory.
zilliztechembedding
Encode text and images into vector representations for retrieval tasks.
zilliztechchunking
Split long documents into configurable chunks for vectorization and retrieval.
zilliztechlocal-setup
Deploy local Milvus environments using Milvus Lite, Docker Standalone, or Docker Compose.
zilliztechpilot
Generate runnable Python AI application scaffolding from requirements.
zilliztechrerank
Rerank top-K vector search results using a cross-encoder model.
zilliztechindexing
Automate Milvus collection creation and vector index management.
zilliztechray
Automate scalable data processing tasks with Ray across clusters.
zilliztechclustering
Cluster text items into labeled topics using embedding models and Milvus.
zilliztechduplicate-detection
Detect exact and near-duplicate records using hash checks and semantic similarity.
zilliztechmulti-vector-search
Search multiple item fields with separate embeddings and fused scores in Milvus.
zilliztechhybrid-search
Combine BM25 keyword matching with vector semantic similarity in Milvus.
zilliztechfiltered-search
Enforce scalar field filters on Milvus vector searches.
zilliztechcontextual-retrieval
Locate precise text chunks with hierarchical parent context in documents.
zilliztechsemantic-search
Convert text into embeddings and retrieve semantically similar items from a vector store.
zilliztechagentic-rag
Automate retrieval decisions for when and what to search in conversational Q&A.
zilliztechrag
Ground LLM answers in document corpora with cited source chunks.
Frequently Asked Questions About Zilliz
FAQPage SchemaWhat specific tasks can I perform using these vector database capabilities?▼
You can execute high-dimensional vector searches, hybrid BM25 keyword matching, and multi-vector field fusion. The system supports document chunking, cross-encoder reranking, and hierarchical contextual retrieval to ground generated responses in specific document corpora.
Which technical personas benefit most from these database integration skills?▼
Data engineers, backend developers, and machine learning practitioners focused on building scalable retrieval systems. These skills are designed for those managing large-scale document indices, recommendation engines, or complex information retrieval architectures requiring low-latency semantic search.
What are the deployment options for running these database environments?▼
You can deploy local environments using Milvus Lite, Docker Standalone, or Docker Compose for development. For production, the platform supports managed cloud instances via Zilliz Cloud, allowing for scalable ingestion and indexing of large-scale document datasets.