OpenAI Key Request While Using Other Models

If you see a request for an OpenAI API key but haven’t configured OpenAI, check these defaults:

The default model when Agent has no model set
The default OpenAIEmbedder used by many vector database implementations

Vector database defaults vary. PgVector creates an OpenAIEmbedder when embedder is omitted. UpstashVectorDb uses Upstash hosted embeddings instead.

Quick fix: Configure a Different Model

Specify the model explicitly. Without one, the agent defaults to OpenAIResponses with gpt-5.4, which requires OPENAI_API_KEY. For example, to use Google’s Gemini instead of OpenAI:

from agno.agent import Agent
from agno.models.google import Gemini

agent = Agent(
    model=Gemini(id="gemini-3.5-flash"),
    markdown=True,
)

# Print the response in the terminal
agent.print_response("Share a 2 sentence horror story.")

See Models for the full provider list.

Quick fix: Configure the Vector Database Embedder

If your vector database defaults to OpenAIEmbedder, pass a different embedder explicitly. For example, to use Google’s Gemini as an embedder, use GeminiEmbedder:

from agno.knowledge.knowledge import Knowledge
from agno.vectordb.pgvector import PgVector
from agno.knowledge.embedder.google import GeminiEmbedder

# Embed a sentence
embeddings = GeminiEmbedder().get_embedding("The quick brown fox jumps over the lazy dog.")

# Print the embeddings and their dimensions
print(f"Embeddings: {embeddings[:5]}")
print(f"Dimensions: {len(embeddings)}")

# Use an embedder in a knowledge base
knowledge = Knowledge(
    vector_db=PgVector(
        db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
        table_name="gemini_embeddings",
        embedder=GeminiEmbedder(),
    ),
    max_results=2,
)

See Embedders for the available options.

​Quick fix: Configure a Different Model

​Quick fix: Configure the Vector Database Embedder

Quick fix: Configure a Different Model

Quick fix: Configure the Vector Database Embedder