custom_retriever.py
"""
Custom Retriever: Bypass the Knowledge Class
==============================================
Sometimes you need full control over retrieval logic. Instead of using
the Knowledge class, you can provide a custom retriever function.
The function receives the query and returns a list of dicts.
This is useful for:
- Non-vector retrieval (SQL queries, API calls, file lookups)
- Custom ranking logic
- Combining multiple data sources with custom logic
See also: ../01_getting_started/02_agentic_rag.py for standard Knowledge-based RAG.
"""
from typing import Dict, List, Optional, Union
from agno.agent import Agent
from agno.models.openai import OpenAIResponses
# ---------------------------------------------------------------------------
# Custom Retriever
# ---------------------------------------------------------------------------
def company_retriever(
agent: Agent, query: str, num_documents: Optional[int] = None, **kwargs
) -> Optional[List[Union[Dict, str]]]:
"""Custom retriever that returns relevant documents based on the query.
In production, this could query a SQL database, call an API, or
implement any custom retrieval logic.
Must return list of dicts (or strings), not Document objects.
"""
# Simulated knowledge base
documents = {
"engineering": {
"name": "Engineering",
"content": "The engineering team uses Python and TypeScript. "
"They follow trunk-based development with CI/CD.",
},
"sales": {
"name": "Sales",
"content": "Q4 revenue was $2.3M, up 40% year-over-year. "
"The sales team closed 145 deals in Q4.",
},
"hr": {
"name": "HR Policy",
"content": "PTO policy: 25 days per year. Remote work is allowed "
"3 days per week. All employees get learning stipends.",
},
}
# Simple keyword matching (replace with your logic)
results = []
for _key, doc in documents.items():
if any(term in query.lower() for term in doc["name"].lower().split()):
results.append(doc)
matched = results or list(documents.values())
if num_documents is not None:
matched = matched[:num_documents]
return matched
# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
agent = Agent(
model=OpenAIResponses(id="gpt-5.2"),
knowledge_retriever=company_retriever,
markdown=True,
)
# ---------------------------------------------------------------------------
# Run Demo
# ---------------------------------------------------------------------------
if __name__ == "__main__":
print("\n" + "=" * 60)
print("Custom retriever: query-specific document selection")
print("=" * 60 + "\n")
agent.print_response("What is the PTO policy?", stream=True)
print("\n" + "=" * 60)
print("Different query returns different documents")
print("=" * 60 + "\n")
agent.print_response("How did Q4 sales go?", stream=True)
Run the Example
1
Set up your virtual environment
uv venv --python 3.12
source .venv/bin/activate
uv venv --python 3.12
.venv\Scripts\activate
2
Install dependencies
uv pip install -U agno openai
3
Export your OpenAI API key
export OPENAI_API_KEY="your_openai_api_key_here"
$Env:OPENAI_API_KEY="your_openai_api_key_here"
4
Run the example
Save the code above as
custom_retriever.py, then run:python custom_retriever.py