内置工具

UiPath Agents come with built-in tools, predefined, ready-to-use components that require no custom development or external configuration.

Analyze attachments

The Analyze Attachments tool allows agents to process and reason over file content using LLMs.

The following file types are currently supported: GIF, JPE, JPEG, PDF, PNG, WEBP.

To add this tool to your agent, take the following steps:

1. Define file inputs. In the Data Manager panel, add arguments to your agent schema for file inputs. These should be of type File.
   Figure 1. Creating file input arguments
   

   

   
   
2. Add the Analyze Attachments tool:
   1. Select Add Tool in the Tools panel.
   2. From the Built-in Tools category, choose Analyze Attachments.
   3. Optionally update the tool’s name and description to help the agent reason better about when to use it.

3. Understand the tool’s inputs. The tool comes preconfigured with two main inputs:

   • attachments (array): List of one or more files to analyze.
   • analysisTask (string): A prompt or instruction describing the task. If your use case involves only one file, you can update the input description to reflect that it's a single attachment.
4. Run the agent with input files.
   1. Open the Debug Configuration window:
      • Navigate to the Project arguments tab.
      • Provide a value for analysisTask, e.g., "Compare the two images".
      • Upload your input files into the fields bound to your attachments argument.
   2. Click Save and run the debug session.
5. After running the agent, inspect the execution trace via the bottom panel.
   Figure 2. The analysis in the execution trail
   

   

   
   

Attachment traces

When using the Analyze Attachments tool, all file inputs and outputs are captured in the Execution Trail panel, under the History tab. The trace provides detailed visibility into how attachments were handled during agent execution.

For each file, the trace shows:

• ID: A unique identifier for the attachment.
• Name: Original file name (e.g., 1.jpg).
• MIME type: Detected file type (e.g., image/jpeg).
• Download URL: A direct link to download the file for inspection or reuse. Download links shown in the trace currently have a Time-to-Live of 30 minutes.

Figure 3. Attachment traces

Best practices and FAQ

The Analyze Attachments tool enables agents to process documents and images using LLMs. While powerful, there are some important limitations and behaviors to be aware of when designing file-driven agents.

Large files may exceed token limits

Agents process files by embedding their contents into LLM prompts, which are constrained by the model’s token limit. Large PDFs or scanned image documents may silently fail or return vague errors like "An error occurred", especially when they exceed the model’s token budget.

To mitigate:

• Use models with higher token capacity.

• Use Context Grounding instead of full file embedding, especially for large or multi-page files.

• Pre-index documents and sync them before or during the agent run via custom tools.

LLMs resize images

When image files (e.g., .jpg, .png) are sent as part of the LLM prompt, most models automatically resize them. This can distort aspect ratios or lose pixel-precise data.

Avoid prompts that rely on exact coordinates, bounding boxes, or pixel-aligned comparisons (e.g., image diffs requiring specific x/y positioning). For more information, refer to OpenAI's image vision guide for model-specific resizing behavior.

支持的文件类型

The following file extensions are supported: GIF, JPE, JPEG, PDF, PNG, WEBP.

File-type support varies by LLM provider. For example, PDF support may fail on some Anthropic models depending on file name or encoding.

Tips for better results

• If you're working with long PDFs, consider splitting them into smaller chunks or pages before passing them to the agent.
• File names must be clean: Anthropic models, in particular, reject file names with special characters or repeated whitespace.
• Keep image count low: Some models like GPT-4o support a maximum of 10–50 images per request.