PydanticAI Integration

CortexDB integrates with PydanticAI to provide type-safe, persistent memory for structured AI agents.

Installation

pip install cortexdbai[pydanticai]

Setup

from pydantic_ai import Agent
from cortexdb.integrations.pydanticai import CortexMemoryDep

# Define memory as a dependency
memory = CortexMemoryDep(
    api_key="your-cortex-api-key",
    tenant_id="my-app",
)

agent = Agent(
    "openai:gpt-4o",
    deps_type=CortexMemoryDep,
    system_prompt="You are a helpful assistant with long-term memory.",
)

@agent.tool
async def recall_memory(ctx, query: str) -> str:
    """Recall relevant information from memory."""
    result = await ctx.deps.recall(query)
    return result.context

@agent.tool
async def store_memory(ctx, content: str) -> str:
    """Store information in long-term memory."""
    result = await ctx.deps.remember(content)
    return f"Stored (event_id={result.event_id})."

# Use the agent
result = await agent.run(
    "What do you know about our deployment process?",
    deps=memory,
)

Configuration

| Parameter | Default | Description | |---|---|---| | api_key | $CORTEX_API_KEY | CortexDB API key | | tenant_id | Required | Tenant identifier |

Under the Hood

The integration wrapper maps to CortexDB's REST API:

# ctx.deps.remember("deployment uses blue-green strategy")
curl -X POST https://api.cortexdb.ai/v1/remember \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "content": "deployment uses blue-green strategy",
    "tenant_id": "my-app"
  }'
# Returns: { "event_id": "019d6359-d3cc-7671-9e4c-9151011fa016" }

# ctx.deps.recall("deployment process")
curl -X POST https://api.cortexdb.ai/v1/recall \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "deployment process",
    "tenant_id": "my-app"
  }'
# Returns: { "context": "...", "confidence": 0.95, "latency_ms": 8 }