Simple agent
This flow demonstrates using an Agent in a flow. An Agent uses an LLM as its "brain" to select among the connected tools and complete its tasks.
In this flow, the Agent reasons using a connected Language model component. The Agent selects the Calculator tool for simple math problems, and the URL tool to search a URL for content.
Prerequisites
Open Langflow and start a new flow
-
From the Langflow dashboard, click New Flow.
-
Select Simple Agent.
The Simple Agent flow is created.
Run the simple agent flow
-
Add your OpenAI API key to the Agent component.
Optionally, create a global variable for the OpenAI API key.
- In the OpenAI API Key field, click Globe, and then click Add New Variable.
- In the Variable Name field, enter
openai_api_key
. - In the Value field, paste your OpenAI API Key (
sk-...
). - Click Save Variable.
-
To run the flow, click Playground.
-
To confirm the tools are connected, ask the agent,
What tools are available to you?
The response is similar to the following:_10I have access to the following tools:_10Calculator: Perform basic arithmetic operations._10fetch_content: Load and retrieve data from specified URLs._10fetch_content_text: Load and retrieve text data from specified URLs._10as_dataframe: Load and retrieve data in a structured format (dataframe) from specified URLs._10get_current_date: Returns the current date and time in a selected timezone. -
Ask the agent a question. For example, ask it to create a tabletop character using your favorite rules set. The agent tells you when it's using the
URL-fetch_content_text
tool to search for rules information, and when it's usingCalculatorComponent-evaluate_expression
to generate attributes with dice rolls. The final output should be similar to this:_10Final Attributes_10Strength (STR): 10_10Constitution (CON): 12_10Size (SIZ): 14_10Dexterity (DEX): 9_10Intelligence (INT): 11_10Power (POW): 13_10Charisma (CHA): 8
Now that your query has completed the journey from Chat input to Chat output, you have completed the Simple Agent flow.