Agent Office Python SDK
Python SDK for the Agent Office API - AI-powered document editing for agentic workflows.
Installation
pip install agent-office
Quick Start
from agent_office import AgentOffice
from uuid import uuid4
# Initialize the client
client = AgentOffice(api_key="sk_ao_your_api_key") # Get your key from https://agentoffice.dev
# Upload a document
doc = client.documents.create(
file="document.docx",
return_markdown=True
)
print(f"Uploaded: {doc.doc_id}")
# Edit the document
edit = client.edit(
doc_id=doc.doc_id,
edit_uid=str(uuid4()),
edit_instructions="Change the title to 'My New Title'",
tracked_changes=False
)
print(f"Edit applied: {edit.edit_applied}")
# Download the edited document
result = client.documents.download(doc_id=doc.doc_id)
print(f"Download URL: {result.download_url}")
# You can then download the file using requests
import requests
response = requests.get(result.download_url)
with open(f"edited_{doc.name}", "wb") as f:
f.write(response.content)
Features
- 📝 Upload and convert documents (DOCX, PDF, etc.)
- ✏️ AI-powered document editing
- 📖 Read document content as Markdown
- 💾 Download edited documents
- 🔄 Track changes support
API Reference
Client Initialization
client = AgentOffice(
api_key="sk_ao_your_api_key", # Required: Your API key
base_url="https://api.agentoffice.dev", # Optional: API base URL
timeout=60 # Optional: Request timeout in seconds
)
Documents
Create Document
doc = client.documents.create(
file="path/to/document.docx", # File path or file-like object
return_markdown=True, # Return markdown content
ttl_seconds=3600 # Time to live in seconds (300-21600)
)
Create Document from URL
doc = client.documents.create_from_url(
file_url="https://example.com/document.docx",
ttl_seconds=3600
)
List Documents
docs = client.documents.list()
for doc in docs.documents:
print(f"{doc.name}: {doc.doc_id}")
Download Document
result = client.documents.download(
doc_id="doc-id",
expires_in=3600 # Presigned URL expiration in seconds
)
print(result.download_url)
Check Document Exists
result = client.documents.exists(doc_id="doc-id")
if result.exists:
print(f"Document exists: {result.document.name}")
Edit Document
edit = client.edit(
doc_id="doc-id",
edit_uid=str(uuid4()), # Unique identifier for the edit
edit_instructions="Change the title to 'My New Title'", # Natural language instructions
lookup_text="Section 1", # Optional: Text to locate edit position
tracked_changes=False, # Enable track changes
use_large_model=False # Use larger AI model
)
Read Document
result = client.read(doc_id="doc-id")
print(result.markdown)
Error Handling
The SDK provides specific exception types for different error conditions:
from agent_office import (
AgentOffice,
AgentOfficeError,
AuthenticationError,
NotFoundError,
ValidationError,
RateLimitError,
ServerError,
)
client = AgentOffice(api_key="sk_ao_your_api_key")
try:
doc = client.documents.create("document.docx")
except AuthenticationError:
print("Invalid API key")
except NotFoundError:
print("Document not found")
except ValidationError as e:
print(f"Validation error: {e.message}")
except RateLimitError:
print("Rate limit exceeded")
except ServerError:
print("Server error")
except AgentOfficeError as e:
print(f"General error: {e.message}")
Development
Install from source
git clone https://github.com/agentoffice/python-sdk.git
cd python-sdk
pip install -e .
Install development dependencies
pip install -e ".[dev]"
License
MIT
Support
- Website: https://agentoffice.dev
- Documentation: https://docs.agentoffice.dev
- Email: support@agentoffice.dev
Metadata
Release files for agent-office 0.0.4
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| agent_office-0.0.4.tar.gz | 9.7 kB | Without provenance | Details for agent_office-0.0.4.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agent_office-0.0.4-py3-none-any.whl | Python 3 | none | any | Details for agent_office-0.0.4-py3-none-any.whl |
Total release size: 22.0 kB
Release files / agent_office-0.0.4.tar.gz
| Download URL | agent_office-0.0.4.tar.gz |
|---|---|
| Size | 9.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
ff6009f8915837919e01e42b64ddbd5d5e3b9c724d6dd2280a1c6e8681042149
|
|
BLAKE2b-256 checksum How to use checksums |
ba38f48ac98f50a9528fcc0a3c926000f26fbb5b7920a1783684d262a3c38d3d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.7
|
Release files / agent_office-0.0.4-py3-none-any.whl
| Download URL | agent_office-0.0.4-py3-none-any.whl |
|---|---|
| Size | 12.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
cc567027a2b7d161df038b3a0a1674e69da71055c5854004cc1e69b06879ef7c
|
|
BLAKE2b-256 checksum How to use checksums |
c80d34030685b5fdbbc706cf9998fb06e59057aef25b807c829a3efeb113ae8e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.7
|
Security for agent-office 0.0.4
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.