andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-04-13 06:23:03 +00:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

docs: add file upload support documentation for flows

Browse Source 
- Add 'File Inputs' section to flows.mdx documenting:
  - Using crewai-files types (ImageFile, PDFFile, etc.) in flow state
  - CrewAI Platform (AMP) automatic file upload dropzone rendering
  - API usage with URL string coercion via Pydantic
- Update files.mdx with:
  - Example of file types in flow state
  - Note about CrewAI Platform integration for flows

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Alex
2026-03-27 00:45:31 -07:00
parent 5a850a708b
commit d8ba5b823a
2 changed files with 86 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
docs/en/concepts/files.mdx
View File

@@ -134,6 +134,29 @@ result = flow.kickoff(
)
```
You can also define file types directly in your flow state for structured file handling:
```python
from pydantic import BaseModel
from crewai.flow.flow import Flow, start
from crewai_files import ImageFile, PDFFile
class DocumentState(BaseModel):
document: PDFFile
cover_image: ImageFile
title: str = ""
class DocumentFlow(Flow[DocumentState]):
@start()
def process(self):
content = self.state.document.read()
return {"processed": True}
```
<Note type="info" title="CrewAI Platform Integration">
When deploying flows to the CrewAI Platform (AMP), file fields in your state automatically render as file upload dropzones in the UI. For API usage, you can pass URL strings directly and Pydantic coerces them to file objects automatically. See [Flows - File Inputs](/en/concepts/flows#file-inputs) for details.
</Note>
### With Standalone Agents
Pass files directly to agent kickoff:

63
docs/en/concepts/flows.mdx
View File

@@ -341,6 +341,69 @@ flow.kickoff()
By providing both unstructured and structured state management options, CrewAI Flows empowers developers to build AI workflows that are both flexible and robust, catering to a wide range of application requirements.
## File Inputs
Flows support file inputs through the `crewai-files` package, enabling you to build workflows that process images, PDFs, and other file types. When you use file types like `ImageFile` or `PDFFile` in your flow state, they integrate seamlessly with both local development and the CrewAI Platform.
<Note type="info" title="Optional Dependency">
File support requires the optional `crewai-files` package. Install it with:
```bash
uv add 'crewai[file-processing]'
```
</Note>
### Using File Types in Flow State
You can include file types directly in your structured flow state:
```python
from pydantic import BaseModel
from crewai.flow.flow import Flow, start
from crewai_files import ImageFile, PDFFile
class DocumentProcessingState(BaseModel):
document: PDFFile # Renders as file upload in CrewAI Platform
cover_image: ImageFile # Renders as image upload
title: str = "" # Renders as text input
class DocumentFlow(Flow[DocumentProcessingState]):
@start()
def process_document(self):
# Access the file - works with URLs, paths, or uploaded files
content = self.state.document.read()
# Or pass to an agent with VisionTool, etc.
return {"processed": True}
```
### CrewAI Platform Integration
When you deploy a flow to the CrewAI Platform (AMP), file fields in your state automatically render as file upload dropzones in the UI. This makes it easy to build user-facing applications that accept file uploads without any additional frontend work.
| State Field Type | Platform UI Rendering |
|:-----------------|:----------------------|
| `ImageFile` | Image upload dropzone |
| `PDFFile` | PDF upload dropzone |
| `AudioFile` | Audio upload dropzone |
| `VideoFile` | Video upload dropzone |
| `TextFile` | Text file upload dropzone |
| `str`, `int`, etc. | Standard form inputs |
### API Usage
When calling your flow via API, you can pass URL strings directly for file fields. Pydantic automatically coerces URLs into the appropriate file type:
```python
# API request body - URLs are automatically converted to file objects
{
"document": "https://example.com/report.pdf",
"cover_image": "https://example.com/cover.png",
"title": "Q4 Report"
}
```
For more details on file types, sources, and provider support, see the [Files documentation](/en/concepts/files).
## Flow Persistence
The @persist decorator enables automatic state persistence in CrewAI Flows, allowing you to maintain flow state across restarts or different workflow executions. This decorator can be applied at either the class level or method level, providing flexibility in how you manage state persistence.