Gemini
Agent with PDF Input (Local file)
Examples
- Introduction
- Getting Started
- Agents
- Teams
- Workflows
- Applications
Agent Concepts
- Multimodal
- RAG
- Knowledge
- Memory
- Async
- Hybrid Search
- Storage
- Tools
- Vector Databases
- Embedders
Models
- Anthropic
- AWS Bedrock
- AWS Bedrock Claude
- Azure AI Foundry
- Azure OpenAI
- Cohere
- DeepInfra
- DeepSeek
- Fireworks
- Gemini
- Basic Agent
- Streaming Agent
- Agent with Structured Outputs
- Agent with Tools
- Agent with Storage
- Agent with Knowledge
- Image Agent
- Flash Thinking Agent
- Audio Input (Bytes Content)
- Audio Input (Upload the file)
- Audio Input (Local file)
- Agent with PDF Input (Local file)
- Agent with PDF Input (URL)
- Video Input (Bytes Content)
- Video Input (File Upload)
- Video Input (Local File Upload)
- Groq
- Hugging Face
- Mistral
- NVIDIA
- Ollama
- OpenAI
- Perplexity
- Together
- xAI
- IBM
- LM Studio
- LiteLLM
- LiteLLM OpenAI
Gemini
Agent with PDF Input (Local file)
Code
cookbook/models/google/gemini/pdf_input_local.py
from pathlib import Path
from agno.agent import Agent
from agno.media import File
from agno.models.google import Gemini
from agno.utils.media import download_file
pdf_path = Path(__file__).parent.joinpath("ThaiRecipes.pdf")
# Download the file using the download_file function
download_file(
"https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf", str(pdf_path)
)
agent = Agent(
model=Gemini(id="gemini-2.0-flash-exp"),
markdown=True,
add_history_to_messages=True,
)
agent.print_response(
"Summarize the contents of the attached file.",
files=[File(filepath=pdf_path)],
)
agent.print_response("Suggest me a recipe from the attached file.")
Usage
1
Create a virtual environment
Open the Terminal
and create a python virtual environment.
python3 -m venv .venv
source .venv/bin/activate
2
Set your API key
export GOOGLE_API_KEY=xxx
3
Install libraries
pip install -U google-genai agno
4
Run Agent
python cookbook/models/google/gemini/pdf_input_local.py