PydanticAI Integration

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

Installation

pip install cortexdb[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."""
    results = await ctx.deps.recall(query, top_k=5)
    return "\n".join([m.content for m in results.memories])

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

# 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 | | namespace | None | Memory namespace | | top_k | 10 | Results per recall |