> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# PDF Input URL

> Summarize a PDF by URL and read response citations from a stored session through the OpenAI Responses API.

## Code

```python pdf_input_url.py theme={null}
from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.media import File
from agno.models.openai.responses import OpenAIResponses

# Setup the database for the Agent Session to be stored
db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"
db = PostgresDb(db_url=db_url)

agent = Agent(
    model=OpenAIResponses(id="gpt-5.2"),
    db=db,
    tools=[{"type": "file_search"}, {"type": "web_search_preview"}],
    markdown=True,
)

agent.print_response(
    "Summarize the contents of the attached file and search the web for more information.",
    files=[File(url="https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf")],
)

# Get the stored Agent session, to check the response citations
session = agent.get_session()
if session and session.runs and session.runs[-1].citations:
    print("Citations:")
    print(session.runs[-1].citations)

```

## Usage

<Snippet file="create-venv-step.mdx" />

**1. Set your API key**

```bash theme={null}
export OPENAI_API_KEY=xxx
```

**2. Install dependencies**

```bash theme={null}
uv pip install -U openai sqlalchemy psycopg agno
```

**3. Run PgVector**

```bash theme={null}
docker run -d \
  -e POSTGRES_DB=ai \
  -e POSTGRES_USER=ai \
  -e POSTGRES_PASSWORD=ai \
  -e PGDATA=/var/lib/postgresql \
  -v pgvolume:/var/lib/postgresql \
  -p 5532:5432 \
  --name pgvector \
  agnohq/pgvector:18
```

**4. Run Agent**

Save the code above as `pdf_input_url.py`, then run:

```bash theme={null}
python pdf_input_url.py
```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.