Skip to main content

File handling utilities for CrewAI multimodal inputs

Project description

crewai-files

File handling utilities for CrewAI multimodal inputs.

Supported File Types

  • ImageFile - PNG, JPEG, GIF, WebP
  • PDFFile - PDF documents
  • TextFile - Plain text files
  • AudioFile - MP3, WAV, FLAC, OGG, M4A
  • VideoFile - MP4, WebM, MOV, AVI

Usage

from crewai_files import File, ImageFile, PDFFile

# Auto-detect file type
file = File(source="document.pdf")  # Resolves to PDFFile

# Or use specific types
image = ImageFile(source="chart.png")
pdf = PDFFile(source="report.pdf")

Passing Files to Crews

crew.kickoff(
    input_files={"chart": ImageFile(source="chart.png")}
)

Passing Files to Tasks

task = Task(
    description="Analyze the chart",
    expected_output="Analysis",
    agent=agent,
    input_files=[ImageFile(source="chart.png")],
)

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

crewai_files-1.13.0a4.tar.gz (678.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

crewai_files-1.13.0a4-py3-none-any.whl (61.5 kB view details)

Uploaded Python 3

File details

Details for the file crewai_files-1.13.0a4.tar.gz.

File metadata

  • Download URL: crewai_files-1.13.0a4.tar.gz
  • Upload date:
  • Size: 678.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.8.4

File hashes

Hashes for crewai_files-1.13.0a4.tar.gz
Algorithm Hash digest
SHA256 b90982212dad4bb732dd059af11dfb2d3e9254e0a71998a50485a76b2f2a487e
MD5 ffb46d4aaaa762400b6ed6ec9259783f
BLAKE2b-256 6550cdfedaa5b0799c3d98b5afd0a79d51a950c0c58f5be600731ffeec1162cf

See more details on using hashes here.

File details

Details for the file crewai_files-1.13.0a4-py3-none-any.whl.

File metadata

File hashes

Hashes for crewai_files-1.13.0a4-py3-none-any.whl
Algorithm Hash digest
SHA256 ab64fc281ce208a3d66f98cece9b1774eade7aebd282c50b08dee75386691350
MD5 0c91ea02348a213826f53fcbf34348f7
BLAKE2b-256 e1b5bd1d237a41fe8da7014ed1a5534c5e21f10fa3da6f538ee9998954f4363e

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page