Milvus is a production-ready vector database that enables semantic search over your documents using dense vector embeddings. Upload documents to collections, and agents will automatically search them using semantic similarity.
Overview
Milvus provides:
- Semantic Search: Find relevant information using natural language queries
- Document Collections: Organize documents into searchable collections
- Custom Embeddings: Configure embedding models and dimensions
- Fine-grained Control: Tune chunking, retrieval, and search parameters
Configuration
agents:
- name: "support_agent"
agent_type: "llm_agent"
knowledge_bases:
- name: "company_docs"
knowledge_base_type: "milvus"
id: "kb_abc123"
config:
top_k: 10
search_ef: 64
metric_type: "COSINE"
Required Fields
Unique identifier for this knowledge base instance
Knowledge base ID for isolation and multi-tenancyReferences a KnowledgeBase record in the database.
Retrieval Configuration
The config object controls how documents are retrieved:
Number of most relevant results to returnRange: 1-1000
HNSW search parameter controlling accuracy vs speed trade-offRange: 1-512
Higher values = more accurate but slower
Distance metric for similarity searchOptions:
COSINE - Cosine similarity (recommended)L2 - Euclidean distanceIP - Inner product
Number of results to skip (for pagination)
Minimum similarity score thresholdRange: 0.0-1.0
Only return results above this score
Enable reranking of search results for improved relevance
Reranking model to use (required if enable_rerank is true)
Usage Examples
Basic Knowledge Base Agent
agents:
- name: "support_agent"
agent_type: "llm_agent"
knowledge_bases:
- name: "support_kb"
knowledge_base_type: "milvus"
id: "kb_support_001"
config:
top_k: 5
metric_type: "COSINE"
system_prompt: |
You are a customer support agent with access to our support documentation.
Always search the knowledge base first for answers to customer questions.
Provide accurate information based on our documentation.
Advanced Configuration with Reranking
agents:
- name: "research_agent"
agent_type: "react_agent"
tools:
- "tavily_search"
knowledge_bases:
- name: "research_kb"
knowledge_base_type: "milvus"
id: "kb_research_001"
config:
top_k: 20
search_ef: 128
metric_type: "COSINE"
score_threshold: 0.7
enable_rerank: true
rerank_model: "cross-encoder"
system_prompt: |
You are a research assistant with access to internal research papers.
Search the knowledge base for relevant research before using web search.
Prioritize high-quality, relevant results.
Multiple Knowledge Bases
agents:
- name: "comprehensive_agent"
agent_type: "llm_agent"
knowledge_bases:
- name: "technical_docs"
knowledge_base_type: "milvus"
id: "kb_tech_001"
config:
top_k: 10
- name: "company_policies"
knowledge_base_type: "milvus"
id: "kb_policy_001"
config:
top_k: 5
system_prompt: |
You have access to multiple knowledge bases:
- Technical documentation
- Company policies
Search the appropriate knowledge base based on the question type.
Best Practices
Top K Selection: Start with top_k: 5-10 for most use cases. Increase if you need more context.
Search Accuracy: Use search_ef: 64 for balanced performance. Increase to 128+ for higher accuracy needs.
Metric Type: Use COSINE for most semantic search applications as it’s normalized and works well with embeddings.
Score Threshold: Set a score_threshold (e.g., 0.7) to filter out low-relevance results.
Higher search_ef values improve accuracy but increase query latency. Balance based on your performance requirements.
Next Steps
