langgenius/dify-docs
1
0
Fork 0
mirror of https://github.com/langgenius/dify-docs.git synced 2026-07-22 12:25:45 -04:00
Code Issues 10 Packages Projects Releases Wiki Activity

test indent rendering

Browse Source
This commit is contained in:
Riskey
2026-01-28 19:22:50 +08:00
committed by GitHub
parent 79f9ea9b03
commit ca9a126021
1 changed files with 12 additions and 106 deletions
Download Patch File Download Diff File Expand all files Collapse all files
en/use-dify/nodes/agent.mdx
+12 -106
View File
@@ -1,115 +1,21 @@
---
title: "Agent"
description: "Give LLMs autonomous control over tools for complex task execution"
icon: "robot"
---
### Form Content
The Agent node gives your LLM autonomous control over tools, enabling it to iteratively decide which tools to use and when to use them. Instead of pre-planning every step, the Agent reasons through problems dynamically, calling tools as needed to complete complex tasks.
Customize what appears in the request form:
<Frame caption="Agent node configuration interface">
<img src="https://assets-docs.dify.ai/dify-enterprise-mintlify/en/guides/workflow/node/1f4d803ff68394d507abd3bcc13ba0f3.png" alt="Agent node interface" />
</Frame>
- Format and structure the content using **Markdown** syntax.
## Agent Strategies
- Reference available **variables** to display dynamic data.
Agent strategies define how your Agent thinks and acts. Choose the approach that best matches your model's capabilities and task requirements.
For example, reference an LLM node's output to show AI-generated content that recipients can review.
<Frame caption="Available agent strategy options">
<img src="https://assets-docs.dify.ai/dify-enterprise-mintlify/en/guides/workflow/node/f14082c44462ac03955e41d66ffd4cca.png" alt="Agent strategies selection" />
</Frame>
<Tabs>
<Tab title="Function Calling">
Uses the LLM's native function calling capabilities to directly pass tool definitions through the tools parameter. The LLM decides when and how to call tools using its built-in mechanism.
<Tip>
If you reference the `text` output variable from a reasoning model, the form will display the model's thinking process along with the final answer.
Best for models like GPT-4, Claude 3.5, and other models with robust function calling support.
</Tab>
<Tab title="ReAct (Reason + Act)">
Uses structured prompts that guide the LLM through explicit reasoning steps. Follows a **Thought → Action → Observation** cycle for transparent decision-making.
Works well with models that may not have native function calling or when you need explicit reasoning traces.
</Tab>
</Tabs>
To show only the answer, toggle on **Enable Reasoning Tag Separation** for the corresponding LLM node.
</Tip>
<Info>
Install additional strategies from **Marketplace → Agent Strategies** or contribute custom strategies to the [community repository](https://github.com/langgenius/dify-plugins).
</Info>
- Add interactive **input fields** to collect information from recipients.
<Frame caption="Function calling strategy configuration">
<img src="https://assets-docs.dify.ai/dify-enterprise-mintlify/en/guides/workflow/node/10505cd7c6f0b3ba10161abb88d9e36b.png" alt="Function calling setup" />
</Frame>
Input fields can be pre-filled with variables (to show suggested content) or static text (to provide examples or default values). Recipients can edit the pre-filled content or leave it unchanged.
## Configuration
### Model Selection
Choose an LLM that supports your selected agent strategy. More capable models handle complex reasoning better but cost more per iteration. Ensure your model supports function calling if using that strategy.
### Tool Configuration
Configure the tools your Agent can access. Each tool requires:
**Authorization** - API keys and credentials for external services configured in your workspace
**Description** - Clear explanation of what the tool does and when to use it (this guides the Agent's decision-making)
**Parameters** - Required and optional inputs the tool accepts with proper validation
### Instructions and Context
Define the Agent's role, goals, and context using natural language instructions. Use Jinja2 syntax to reference variables from upstream workflow nodes.
**Query** specifies the user input or task the Agent should work on. This can be dynamic content from previous workflow nodes.
<Frame caption="Agent configuration parameters">
<img src="https://assets-docs.dify.ai/dify-enterprise-mintlify/en/guides/workflow/node/54c8e4f0eaa7379bd8c1b5ac6305b326.png" alt="Agent configuration interface" />
</Frame>
### Execution Controls
**Maximum Iterations** sets a safety limit to prevent infinite loops. Configure based on task complexity - simple tasks need 3-5 iterations, while complex research might require 10-15.
**Memory** controls how many previous messages the Agent remembers using TokenBufferMemory. Larger memory windows provide more context but increase token costs. This enables conversational continuity where users can reference previous actions.
### Tool Parameter Auto-Generation
Tools can have parameters configured as **auto-generated** or **manual input**. Auto-generated parameters (`auto: false`) are automatically populated by the Agent, while manual input parameters require explicit values that become part of the tool's permanent configuration.
<video controls src="https://assets-docs.dify.ai/2025/04/1801b96763eb8f22f1e2158645897885.mp4" width="100%" />
## Output Variables
Agent nodes provide comprehensive output including:
**Final Answer** - The Agent's ultimate response to the query
**Tool Outputs** - Results from each tool invocation during execution
**Reasoning Trace** - Step-by-step decision process (especially detailed with ReAct strategy) available in the JSON output
**Iteration Count** - Number of reasoning cycles used
**Success Status** - Whether the Agent completed the task successfully
**Agent Logs** - Structured log events with metadata for debugging and monitoring tool invocations
## Use Cases
**Research and Analysis** - Agents can autonomously search multiple sources, synthesize information, and provide comprehensive answers.
**Troubleshooting** - Diagnostic tasks where the Agent needs to gather information, test hypotheses, and adapt its approach based on findings.
**Multi-step Data Processing** - Complex workflows where the next action depends on intermediate results.
**Dynamic API Integration** - Scenarios where the sequence of API calls depends on responses and conditions that can't be predetermined.
## Best Practices
**Clear Tool Descriptions** help the Agent understand when and how to use each tool effectively.
**Appropriate Iteration Limits** prevent runaway costs while allowing sufficient flexibility for complex tasks.
**Detailed Instructions** provide context about the Agent's role, goals, and any constraints or preferences.
**Memory Management** balance context retention with token efficiency based on your use case requirements.
Each input field becomes an variable that can be referenced in downstream nodes to incorporate recipient input. For example, pass edited content to a publishing node or send feedback to an LLM node for regeneration.