# Document Intelligence Client
This Python package offers a robust client for seamless interaction with the Document Intelligence API. It enables you to efficiently retrieve, manage, and process document data within your workspace.
## Installation
To install the package directly from GitHub using `pip`, run the following command:
```sh
pip install sema4ai-di-client
```
## Usage
After installing the package, you can import it and start using the `DocumentIntelligenceClient` class.
### Importing the Package
```python
from sema4ai.di_client import DocumentIntelligenceClient
```
### Getting a Document Work Item
To retrieve a document work item, make sure you've set the required environment variables before initializing the client. Specifically, ensure that `DOCUMENT_INTELLIGENCE_SERVICE_URL` and `AGENTS_EVENTS_SERVICE_URL` is set.
When running in Sema4.ai Control Room these are all handled by the platform.
- **Environment Variables:** Make sure the required environment variables (`DOCUMENT_INTELLIGENCE_SERVICE_URL`, `AGENTS_EVENTS_SERVICE_URL`) are set in your environment before running the code.
- **Workspace ID:** If you are developing on local, then make sure to set workspace_id in `DocumentIntelligenceClient(workspace_id='<your_workspace_id>')`, which is optional and deduced on non-local environments from the URL passed.
- **Initialize the Client:** The client will automatically read the environment variables and initialize the connection.
- **Error Handling:** The example includes error handling and ensures the client is properly closed at the end.
Here's an example:
```python
from sema4ai.di_client import DocumentIntelligenceClient
# Ensure environment variables are set for the service URLs
# Example:
# export DOCUMENT_INTELLIGENCE_SERVICE_URL='https://api.yourdomain.com'
# export AGENTS_EVENTS_SERVICE_URL='https://agents.yourdomain.com'
# Initialize the client
client = DocumentIntelligenceClient()
# Specify the document ID you want to retrieve
document_id = 'your_document_id'
# Get the document work item
try:
document_work_item = client.get_document_work_item(document_id)
if document_work_item:
print("Document Work Item:")
print(document_work_item)
else:
print("No document work item found for the given document ID.")
except Exception as e:
print(f"An error occurred: {e}")
finally:
client.close() # Make sure to close the client connection
```
### Available Methods
The `DocumentIntelligenceClient` offers several methods to interact with the Document Intelligence API and manage work items. Below are examples of the available operations:
- **Get Document Type:** Retrieve details about a specific document type.
```python
document_type = client.get_document_type(document_type_name)
```
- **Get Document Format:** Fetch the format of a document based on its type and class.
```python
document_format = client.get_document_format(document_type_name, document_class_name)
```
- **Store Extracted Content:** Store extracted content after processing a document.
```python
client.store_extracted_content(extracted_content)
```
- **Store Transformed Content:** Save content that has been transformed by a process.
```python
client.store_transformed_content(transformed_content)
```
- **Store Computed Content:** Submit content that has been computed after analysis.
```python
client.store_computed_content(computed_content)
```
- **Get Document Content:** Retrieve document content in various states, such as raw, extracted, transformed, or computed.
```python
content = client.get_document_content(document_id, content_state)
```
- **Remove Document Content:** Delete content for a document in a specific state.
```python
client.remove_document_content(document_id, content_state)
```
- **Complete Work Item Stage:** Mark a work item’s current stage as complete and move to the next stage.
```python
response = client.work_items_complete_stage(
work_item_id='your_work_item_id',
status='SUCCESS', # or 'FAILURE'
status_reason='optional_reason', # Optional
log_details_path='optional_log_path' # Optional
)
```
## Dependencies
The package requires the following dependencies:
- `urllib3 >= 1.25.3, < 2.1.0`
- `python-dateutil`
- `pydantic >= 2`
- `typing-extensions >= 4.7.1`
These should be installed automatically when you install the package via `pip`.
### Example Code Snippet
Below is an example code snippet if you are testing on prod.
```python
from sema4ai.di_client import DocumentIntelligenceClient
client = DocumentIntelligenceClient()
# Fetch and print the document type
try:
document_type = client.get_document_type("CounterParty Reconciliation")
print(document_type)
except Exception as e:
print(f"An error occurred: {e}")
finally:
client.close() # Ensure proper resource cleanup
```
Below is an example code snippet if you are testing on local.
```python
from sema4ai.di_client import DocumentIntelligenceClient
import os
# Set the required environment variables within the Python code
os.environ['DOCUMENT_INTELLIGENCE_SERVICE_URL'] = 'http://127.0.0.1:9080'
os.environ['AGENTS_EVENTS_SERVICE_URL'] = 'http://127.0.0.1:9080'
workspace_id = "<your Sema4.ai Control Room Workspace ID>"
client = DocumentIntelligenceClient(workspace_id=workspace_id)
# Fetch and print the document type
try:
document_type = client.get_document_type("CounterParty Reconciliation")
print(document_type)
except Exception as e:
print(f"An error occurred: {e}")
finally:
client.close() # Ensure proper resource cleanup
```
Raw data
{
"_id": null,
"home_page": "https://github.com/Sema4AI/document-intelligence-client",
"name": "sema4ai-di-client",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.10",
"maintainer_email": null,
"keywords": "OpenAPI, OpenAPI-Generator, Document Intelligence API",
"author": "Sukeesh V.",
"author_email": "sukeesh@sema4.ai",
"download_url": "https://files.pythonhosted.org/packages/27/2c/9ba7647584a1d5cfca7aec1491102671eefa0889e19ef3a30db423aac62c/sema4ai_di_client-1.0.13.tar.gz",
"platform": null,
"description": "# Document Intelligence Client\n\nThis Python package offers a robust client for seamless interaction with the Document Intelligence API. It enables you to efficiently retrieve, manage, and process document data within your workspace.\n\n## Installation\n\nTo install the package directly from GitHub using `pip`, run the following command:\n\n```sh\npip install sema4ai-di-client\n```\n\n## Usage\n\nAfter installing the package, you can import it and start using the `DocumentIntelligenceClient` class.\n\n### Importing the Package\n\n```python\nfrom sema4ai.di_client import DocumentIntelligenceClient\n```\n\n### Getting a Document Work Item\n\nTo retrieve a document work item, make sure you've set the required environment variables before initializing the client. Specifically, ensure that `DOCUMENT_INTELLIGENCE_SERVICE_URL` and `AGENTS_EVENTS_SERVICE_URL` is set.\n\nWhen running in Sema4.ai Control Room these are all handled by the platform.\n\n- **Environment Variables:** Make sure the required environment variables (`DOCUMENT_INTELLIGENCE_SERVICE_URL`, `AGENTS_EVENTS_SERVICE_URL`) are set in your environment before running the code.\n- **Workspace ID:** If you are developing on local, then make sure to set workspace_id in `DocumentIntelligenceClient(workspace_id='<your_workspace_id>')`, which is optional and deduced on non-local environments from the URL passed.\n- **Initialize the Client:** The client will automatically read the environment variables and initialize the connection.\n- **Error Handling:** The example includes error handling and ensures the client is properly closed at the end.\n\nHere's an example:\n\n```python\nfrom sema4ai.di_client import DocumentIntelligenceClient\n\n# Ensure environment variables are set for the service URLs\n# Example:\n# export DOCUMENT_INTELLIGENCE_SERVICE_URL='https://api.yourdomain.com'\n# export AGENTS_EVENTS_SERVICE_URL='https://agents.yourdomain.com'\n\n# Initialize the client\nclient = DocumentIntelligenceClient()\n\n# Specify the document ID you want to retrieve\ndocument_id = 'your_document_id'\n\n# Get the document work item\ntry:\n document_work_item = client.get_document_work_item(document_id)\n if document_work_item:\n print(\"Document Work Item:\")\n print(document_work_item)\n else:\n print(\"No document work item found for the given document ID.\")\nexcept Exception as e:\n print(f\"An error occurred: {e}\")\nfinally:\n client.close() # Make sure to close the client connection\n```\n\n### Available Methods\n\nThe `DocumentIntelligenceClient` offers several methods to interact with the Document Intelligence API and manage work items. Below are examples of the available operations:\n\n- **Get Document Type:** Retrieve details about a specific document type.\n\n ```python\n document_type = client.get_document_type(document_type_name)\n ```\n\n- **Get Document Format:** Fetch the format of a document based on its type and class.\n\n ```python\n document_format = client.get_document_format(document_type_name, document_class_name)\n ```\n\n- **Store Extracted Content:** Store extracted content after processing a document.\n\n ```python\n client.store_extracted_content(extracted_content)\n ```\n\n- **Store Transformed Content:** Save content that has been transformed by a process.\n\n ```python\n client.store_transformed_content(transformed_content)\n ```\n\n- **Store Computed Content:** Submit content that has been computed after analysis.\n\n ```python\n client.store_computed_content(computed_content)\n ```\n\n- **Get Document Content:** Retrieve document content in various states, such as raw, extracted, transformed, or computed.\n\n ```python\n content = client.get_document_content(document_id, content_state)\n ```\n\n- **Remove Document Content:** Delete content for a document in a specific state.\n\n ```python\n client.remove_document_content(document_id, content_state)\n ```\n\n- **Complete Work Item Stage:** Mark a work item\u2019s current stage as complete and move to the next stage.\n\n ```python\n response = client.work_items_complete_stage(\n work_item_id='your_work_item_id',\n status='SUCCESS', # or 'FAILURE'\n status_reason='optional_reason', # Optional\n log_details_path='optional_log_path' # Optional\n )\n ```\n\n## Dependencies\n\nThe package requires the following dependencies:\n\n- `urllib3 >= 1.25.3, < 2.1.0`\n- `python-dateutil`\n- `pydantic >= 2`\n- `typing-extensions >= 4.7.1`\n\nThese should be installed automatically when you install the package via `pip`.\n\n### Example Code Snippet\n\nBelow is an example code snippet if you are testing on prod.\n\n```python\nfrom sema4ai.di_client import DocumentIntelligenceClient\n\nclient = DocumentIntelligenceClient()\n\n# Fetch and print the document type\ntry:\n document_type = client.get_document_type(\"CounterParty Reconciliation\")\n print(document_type)\nexcept Exception as e:\n print(f\"An error occurred: {e}\")\nfinally:\n client.close() # Ensure proper resource cleanup\n```\n\nBelow is an example code snippet if you are testing on local.\n\n```python\nfrom sema4ai.di_client import DocumentIntelligenceClient\nimport os\n\n# Set the required environment variables within the Python code\nos.environ['DOCUMENT_INTELLIGENCE_SERVICE_URL'] = 'http://127.0.0.1:9080'\nos.environ['AGENTS_EVENTS_SERVICE_URL'] = 'http://127.0.0.1:9080'\n\nworkspace_id = \"<your Sema4.ai Control Room Workspace ID>\"\nclient = DocumentIntelligenceClient(workspace_id=workspace_id)\n\n# Fetch and print the document type\ntry:\n document_type = client.get_document_type(\"CounterParty Reconciliation\")\n print(document_type)\nexcept Exception as e:\n print(f\"An error occurred: {e}\")\nfinally:\n client.close() # Ensure proper resource cleanup\n```\n",
"bugtrack_url": null,
"license": "Sema4.ai Proprietary (see LICENSE)",
"summary": "Sema4AI Document Intelligence API client",
"version": "1.0.13",
"project_urls": {
"Homepage": "https://github.com/Sema4AI/document-intelligence-client",
"Repository": "https://github.com/Sema4AI/document-intelligence-client"
},
"split_keywords": [
"openapi",
" openapi-generator",
" document intelligence api"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "3239b0477388c0431616b859f0df0611f6c17f2763e78052edcd8ef961e327b3",
"md5": "d1d8195940b0f18cb8ac5da4b4ba53b5",
"sha256": "98a47556fb4caa9ad22fa8cd7c94d341a0c7df9d064a0251743d243080587014"
},
"downloads": -1,
"filename": "sema4ai_di_client-1.0.13-py3-none-any.whl",
"has_sig": false,
"md5_digest": "d1d8195940b0f18cb8ac5da4b4ba53b5",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.10",
"size": 147597,
"upload_time": "2025-01-06T17:04:24",
"upload_time_iso_8601": "2025-01-06T17:04:24.107626Z",
"url": "https://files.pythonhosted.org/packages/32/39/b0477388c0431616b859f0df0611f6c17f2763e78052edcd8ef961e327b3/sema4ai_di_client-1.0.13-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "272c9ba7647584a1d5cfca7aec1491102671eefa0889e19ef3a30db423aac62c",
"md5": "54e5a6462c920351ba425a2d1a66b5f5",
"sha256": "a67ca009c9dea1494b204c924856c9b24c92730dd69abde0e4de2ccf9c0d8615"
},
"downloads": -1,
"filename": "sema4ai_di_client-1.0.13.tar.gz",
"has_sig": false,
"md5_digest": "54e5a6462c920351ba425a2d1a66b5f5",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.10",
"size": 72633,
"upload_time": "2025-01-06T17:04:25",
"upload_time_iso_8601": "2025-01-06T17:04:25.431744Z",
"url": "https://files.pythonhosted.org/packages/27/2c/9ba7647584a1d5cfca7aec1491102671eefa0889e19ef3a30db423aac62c/sema4ai_di_client-1.0.13.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-01-06 17:04:25",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "Sema4AI",
"github_project": "document-intelligence-client",
"github_not_found": true,
"lcname": "sema4ai-di-client"
}
JSON
