Connic Composer SDK

Knowledge Tools

Give your agents persistent memory with store, query, and delete operations.

Knowledge tools let your agents store and retrieve information that persists across runs. Store documents, FAQs, or any text, then query it naturally. The system automatically finds relevant content based on meaning, not just keywords.

Namespaces let you organize knowledge into categories (e.g., "policies", "products", "faq"). Entry IDs are unique within a namespace.

You can view, search, and manage all stored knowledge from the Knowledge page in your project dashboard.

query_knowledge

Search the knowledge base. Finds the most relevant content based on meaning, not just exact keywords.

Parameters

Parameter	Type	Default	Description
query	string	required	The search query. Be specific for best results
namespace	string?	null	Filter results to a specific namespace
min_score	float	0.7	Minimum relevance score (0.0 to 1.0)
max_results	int	3	Maximum number of results to return

Return Value

Returns matching results with: content, entry_id, score (relevance 0-1), namespace

Examples

python

# Simple query
result = await query_knowledge("What is the refund policy?")

# Results contain matching content with relevance scores
for item in result["results"]:
    print(f"[{item['score']:.0%}] {item['content'][:100]}...")

python

# Filter by namespace
result = await query_knowledge(
    query="How do I reset my password?",
    namespace="support"
)

# Adjust score threshold and result count
result = await query_knowledge(
    query="pricing information",
    min_score=0.5,    # Lower threshold = more results
    max_results=10    # Return up to 10 results
)

store_knowledge

Add new information to the knowledge base. Content is automatically processed and made searchable.

Parameters

Parameter	Type	Default	Description
content	string	required	The text content to store (any length)
entry_id	string?	auto	Custom ID for the entry (UUID generated if omitted)
namespace	string?	null	Category for organizing knowledge
metadata	dict?	null	Additional key-value data to store

Return Value

Returns: entry_id, success, job_id. Storage is asynchronous. Returns immediately while content is processed in the background.

Examples

python

# Simple store (auto-generated ID)
result = await store_knowledge(
    content="The company refund policy allows returns within 30 days."
)
# Returns: {"entry_id": "abc123...", "success": true}

python

# Store with custom ID for later updates
result = await store_knowledge(
    content="Q1 sales target is $1M with focus on enterprise.",
    entry_id="q1-sales-target",
    namespace="planning",
    metadata={"quarter": "Q1", "year": "2024"}
)

# Store user preferences
result = await store_knowledge(
    content="User prefers dark mode and metric units.",
    entry_id="user-preferences",
    namespace="user_data"
)

delete_knowledge

Remove entries from the knowledge base by their entry ID. Useful for keeping the knowledge base clean and up-to-date.

Parameters

Parameter	Type	Default	Description
entry_id	string	required	The ID of the entry to delete
namespace	string?	null	Namespace to scope the deletion

Return Value

Returns: ok (success), deleted_count. Entry IDs are unique per namespace. Specify namespace if the ID exists in multiple.

Examples

python

# Delete by entry_id
result = await delete_knowledge(entry_id="old-product-info")

# Delete from specific namespace
result = await delete_knowledge(
    entry_id="q1-sales-target",
    namespace="planning"
)

Complete Agent Example

yaml

# agents/knowledge-agent.yaml
version: "1.0"

name: knowledge-agent
model: gemini/gemini-2.5-pro
description: "Agent with persistent memory"
system_prompt: |
  You are an assistant with access to a knowledge base.
  Always search the knowledge base first before answering.
  
tools:
  - query_knowledge
  - store_knowledge
  - delete_knowledge

Best Practices

Use descriptive entry_ids for easy updates
Organize with namespaces (policies, products, faq)
Be specific in queries for better results
Clean up old entries regularly

Tips

Query before answering: check knowledge base first
Store structured content with clear headings
Use metadata for dates, versions, categories
Test queries in the Knowledge dashboard page

Predefined Tools

See all available predefined tools

Agent Configuration

Configure agents with knowledge tools