Agent Configuration Quick Start¶

Quick reference guide for getting started with agent configurations.

Installation¶

Agent configurations are part of the bast_ai_agno package:

# Already available if you have bast_ai_agno installed
from bast_ai_agno.dto.agent_configs import basic_agent_config

5-Minute Quick Start¶

Step 1: Import Configuration¶

from bast_ai_agno.dto.agent_configs import basic_agent_config
from bast_ai_agno import AgnoAgentFactory, AgnoMongoDBResources, AgnoModelResources

Step 2: Initialize Resources¶

cat_name = "myapp"
storage_resources = AgnoMongoDBResources(cat_name)
model_resources = AgnoModelResources(cat_name)
factory = AgnoAgentFactory(cat_name)

Step 3: Get Storage and Model¶

agent_storage = storage_resources.get_agent_storage("my_agent")
agent_model = model_resources.get_open_ai_chat("gpt-4o-mini")

Step 4: Create Agent¶

agent = factory.create_openai_chat_agent(
    name="my_agent",
    model=agent_model,
    db=agent_storage,
    config_raw=basic_agent_config
)

Step 5: Use Agent¶

response = agent.run(
    input="Hello, how can you help me?",
    user_id="user123",
    session_id="session1",
    stream=False
)

print(response.content)

Common Patterns¶

Pattern 1: Basic Agent¶

from bast_ai_agno.dto.agent_configs import basic_agent_config

agent = factory.create_openai_chat_agent(
    name="basic",
    model=model,
    db=storage,
    config_raw=basic_agent_config
)

Pattern 2: Agent with Knowledge¶

from bast_ai_agno.dto.agent_configs import knowledge_agent_config
from bast_ai_agno import AgnoKnowledgeResources

kb_resources = AgnoKnowledgeResources(cat_name)
knowledge = kb_resources.get_knowledge("my_kb")

agent = factory.create_openai_chat_agent(
    name="rag_agent",
    model=model,
    db=storage,
    knowledge=knowledge,
    config_raw=knowledge_agent_config
)

Pattern 3: Agent with Tools¶

from bast_ai_agno.dto.agent_configs import tool_enabled_agent_config
from bast_ai_agno.dto.agent_tool_utils import add_tools_to_config
from agno.tools.duckduckgo import DuckDuckGoTools

config = add_tools_to_config(
    tool_enabled_agent_config,
    [DuckDuckGoTools()]
)

agent = factory.create_openai_chat_agent(
    name="tool_agent",
    model=model,
    db=storage,
    config_raw=config
)

Pattern 4: Agent with Memory¶

from bast_ai_agno.dto.agent_configs import memory_agent_config
from bast_ai_agno import AgnoMemoryResources

memory_resources = AgnoMemoryResources(cat_name)
memory_manager = memory_resources.get_memory_manager(
    model=model,
    db=storage
)

agent = factory.create_openai_chat_agent(
    name="memory_agent",
    model=model,
    db=storage,
    memory_manager=memory_manager,
    config_raw=memory_agent_config
)

Configuration Selection Guide¶

Need a simple assistant?¶

→ Use basic_agent_config

Need to search knowledge base?¶

→ Use knowledge_agent_config or rxdemo_agent_config

Need external tools?¶

→ Use tool_enabled_agent_config + add_tools_to_config()

Need to remember user preferences?¶

→ Use memory_agent_config

Need multi-turn conversations?¶

→ Use session_aware_agent_config

Need complex problem solving?¶

→ Use reasoning_agent_config or deep_reasoning_agent_config

Need everything?¶

→ Use full_featured_agent_config

Utility Functions Quick Reference¶

Add Tools¶

from bast_ai_agno.dto.agent_tool_utils import add_tools_to_config
config = add_tools_to_config(base_config, tools)

Add Reasoning¶

from bast_ai_agno.dto.agent_reasoning_utils import build_reasoning_config
config = build_reasoning_config(base_config, min_steps=2, max_steps=10)

Add Session Management¶

from bast_ai_agno.dto.agent_session_utils import build_session_config
config = build_session_config(base_config, cache=True, num_sessions=5)

Validate Config¶

from bast_ai_agno.dto.agent_validation_utils import validate_agent_config
is_valid, errors = validate_agent_config(config)

Merge Configs¶

from bast_ai_agno.dto.agent_merge_utils import merge_configs
merged = merge_configs(base_config, override_config)

Next Steps¶

Read Configuration Guide for detailed documentation
Check Configuration Schema for all available fields
See Examples for real-world use cases
Visit Agno Documentation for Agno-specific details

Troubleshooting¶

Import Error¶

# Make sure bast_ai_agno is installed
from bast_ai_agno.dto.agent_configs import basic_agent_config

Validation Errors¶

# Always validate before use
from bast_ai_agno.dto.agent_validation_utils import validate_agent_config
is_valid, errors = validate_agent_config(config)
if not is_valid:
    print(f"Errors: {errors}")

Configuration Not Working¶

# Check that you're passing config_raw correctly
agent = factory.create_openai_chat_agent(
    name="agent",
    model=model,
    db=storage,
    config_raw=config  # Make sure config_raw is set
)