The Fabric Data Agent SDK supports programmatic access for [Fabric Data Agent](https://learn.microsoft.com/en-us/fabric/data-science/concept-ai-skill) artifacts.
This package is released as a preview and has been tested with Microsoft Fabric Python notebooks.
# Getting started
## Prerequisites
* A [Microsoft Fabric subscription](https://learn.microsoft.com/en-us/fabric/enterprise/licenses). Or sign up for a free [Microsoft Fabric (Preview) trial](https://learn.microsoft.com/en-us/fabric/get-started/fabric-trial).
* Sign in to [Microsoft Fabric](https://fabric.microsoft.com/).
* Create [a new notebook](https://learn.microsoft.com/en-us/fabric/data-engineering/how-to-use-notebook#create-notebooks) or a new [spark job](https://learn.microsoft.com/en-us/fabric/data-engineering/create-spark-job-definition) to use this package. **Note that semantic link is supported only within Microsoft Fabric.**
## Install the `fabric-data-agent-sdk` package
To install the most recent version `fabric-data-agent-sdk` in your Fabric Python notebook kernel by executing this code in a notebook cell:
```python
%pip install -U fabric-data-agent-sdk
```
# Key concepts
Fabric Data Agent SDK has two main entry points:
* Data plane using OpenAI SDK for conversational interaction with an existing Data Agent artifact.
* Management plane to create, update and delete Data Agent artifacts.
# Change logs
## 0.1.14a0
* fix thread url for fabcon tenant
## 0.1.13a0
* add support for granular quality feedback in few-shot validation and improve Dataframe output
* fix invalid data type for delta lake
## 0.1.12a0
* fix python error in the release pipeline
* add robust few-shot validation utilities to SDK with dual LLM support and DataFrame output
* update parameter type in add-datasource
## 0.1.11a0
* upgrade OneBranch Azure Linux Build Image: Migrating from 2.0 to 3.0
* remove "AISkill" from artifact name list due to invalid item type error in openai
* make Data Agent and Data Source Creation Idempotent
* add publish description
* refactoring the evaluation apis and add code coverage
* remove AISkill artifact type in data agent api
## 0.1.10a0
* fix get_evaluation_summary_per_question if no question fails
## 0.1.9a0
* Use correct workspace context in delete_data_agent function.
* Update notebooks with data source notes
* display failed threads and fix percentage
## 0.1.8a0
* evaluation API enhancements including parallelizing, number of variations and single thread.
* speed-up add_ground_truth_batch and stabilise Kusto tests
* ground-truth generation for Kusto (KQL) datasources
## 0.1.7a0
* added Warehouse to list of artifact types.
* added Method for Updating Ground Truth before Evaluation.
* made Publish Info Optional.
## 0.1.6a0
* update sdk to make compatible with both python and spark.
## 0.1.5a0
* add PySpark support for the evaluation APIs.
* added pipeline for running unit tests.
## 0.1.4a0
* switch to public apis for artifact management.
## 0.1.3a0
* add column/table descriptions for sql data sources.
* allow selection of multiple columns at once in the datasource.
* bug fix to address the run_steps response structure change.
## 0.1.2a0
* bugfix for *fabric_openai* artifact type - should support "DataAgent".
* bugfix for data source type ("datawarehouse" should be "warehouse").
## 0.1.1a0
* bugfix for *create_data_agent* where type should support "DataAgent".
## 0.1.0a0
* add upload_fewshots for adding multiple fewshots to DataSource.
## 0.0.4a0
* add evaluation APIs to the SDK
## 0.0.3a1
* return fewshot id from add_fewshots
* fix the aiskill stage parameter
* return datasource display name in pretty_print
* return thread object for get_or_create_thread API.
## 0.0.2a0
* rename module
* support Fabric get_or_create_thread to decouple from UX thread
## 0.0.1a0
Initial alpha release of the package.
* add: data plane client
* add: management plane client
Raw data
{
"_id": null,
"home_page": null,
"name": "fabric-data-agent-sdk",
"maintainer": null,
"docs_url": null,
"requires_python": "<3.13,>=3.10",
"maintainer_email": null,
"keywords": null,
"author": "Microsoft Corporation",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/c5/88/240166e3261b0b1e7c260e112c3e21c1a428cb196753f6412835b30231dc/fabric_data_agent_sdk-0.1.14a0.tar.gz",
"platform": null,
"description": "The Fabric Data Agent SDK supports programmatic access for [Fabric Data Agent](https://learn.microsoft.com/en-us/fabric/data-science/concept-ai-skill) artifacts.\n\nThis package is released as a preview and has been tested with Microsoft Fabric Python notebooks.\n\n# Getting started\n\n## Prerequisites\n\n* A [Microsoft Fabric subscription](https://learn.microsoft.com/en-us/fabric/enterprise/licenses). Or sign up for a free [Microsoft Fabric (Preview) trial](https://learn.microsoft.com/en-us/fabric/get-started/fabric-trial).\n* Sign in to [Microsoft Fabric](https://fabric.microsoft.com/).\n* Create [a new notebook](https://learn.microsoft.com/en-us/fabric/data-engineering/how-to-use-notebook#create-notebooks) or a new [spark job](https://learn.microsoft.com/en-us/fabric/data-engineering/create-spark-job-definition) to use this package. **Note that semantic link is supported only within Microsoft Fabric.**\n\n## Install the `fabric-data-agent-sdk` package\n\nTo install the most recent version `fabric-data-agent-sdk` in your Fabric Python notebook kernel by executing this code in a notebook cell:\n\n ```python\n %pip install -U fabric-data-agent-sdk\n ```\n\n# Key concepts\n\nFabric Data Agent SDK has two main entry points:\n\n* Data plane using OpenAI SDK for conversational interaction with an existing Data Agent artifact.\n* Management plane to create, update and delete Data Agent artifacts.\n\n# Change logs\n\n## 0.1.14a0\n\n* fix thread url for fabcon tenant\n\n## 0.1.13a0\n\n* add support for granular quality feedback in few-shot validation and improve Dataframe output\n* fix invalid data type for delta lake\n\n## 0.1.12a0\n\n* fix python error in the release pipeline\n* add robust few-shot validation utilities to SDK with dual LLM support and DataFrame output\n* update parameter type in add-datasource\n\n## 0.1.11a0\n\n* upgrade OneBranch Azure Linux Build Image: Migrating from 2.0 to 3.0\n* remove \"AISkill\" from artifact name list due to invalid item type error in openai\n* make Data Agent and Data Source Creation Idempotent\n* add publish description\n* refactoring the evaluation apis and add code coverage\n* remove AISkill artifact type in data agent api\n\n## 0.1.10a0\n\n* fix get_evaluation_summary_per_question if no question fails\n\n## 0.1.9a0\n\n* Use correct workspace context in delete_data_agent function.\n* Update notebooks with data source notes\n* display failed threads and fix percentage\n\n## 0.1.8a0\n\n* evaluation API enhancements including parallelizing, number of variations and single thread.\n* speed-up add_ground_truth_batch and stabilise Kusto tests\n* ground-truth generation for Kusto (KQL) datasources\n\n## 0.1.7a0\n\n* added Warehouse to list of artifact types.\n* added Method for Updating Ground Truth before Evaluation.\n* made Publish Info Optional.\n\n## 0.1.6a0\n\n* update sdk to make compatible with both python and spark.\n\n## 0.1.5a0\n\n* add PySpark support for the evaluation APIs.\n* added pipeline for running unit tests.\n\n## 0.1.4a0\n\n* switch to public apis for artifact management.\n\n## 0.1.3a0\n\n* add column/table descriptions for sql data sources.\n* allow selection of multiple columns at once in the datasource.\n* bug fix to address the run_steps response structure change.\n\n## 0.1.2a0\n\n* bugfix for *fabric_openai* artifact type - should support \"DataAgent\".\n* bugfix for data source type (\"datawarehouse\" should be \"warehouse\").\n\n## 0.1.1a0\n\n* bugfix for *create_data_agent* where type should support \"DataAgent\".\n\n## 0.1.0a0\n\n* add upload_fewshots for adding multiple fewshots to DataSource.\n\n## 0.0.4a0\n\n* add evaluation APIs to the SDK\n\n## 0.0.3a1\n\n* return fewshot id from add_fewshots\n* fix the aiskill stage parameter\n* return datasource display name in pretty_print\n* return thread object for get_or_create_thread API.\n\n## 0.0.2a0\n\n* rename module\n* support Fabric get_or_create_thread to decouple from UX thread\n\n## 0.0.1a0\n\nInitial alpha release of the package.\n\n* add: data plane client\n* add: management plane client\n",
"bugtrack_url": null,
"license": "MIT License",
"summary": "SDK for the Fabric Data Agent Library",
"version": "0.1.14a0",
"project_urls": {
"Repository": "https://msdata.visualstudio.com/DefaultCollection/A365/_git/SynapseML-Agent-SDK"
},
"split_keywords": [],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "d88750f7e8fcaaa87c808fc9b81c8364e46ac68a6b70a1ea25cfe3d1e004a943",
"md5": "a15d31d64b764ed487735d18a74c3c3c",
"sha256": "abd1a5df622d28867d22435644b5e9f72660b43368a0b1ce22003906ff3dee0d"
},
"downloads": -1,
"filename": "fabric_data_agent_sdk-0.1.14a0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "a15d31d64b764ed487735d18a74c3c3c",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<3.13,>=3.10",
"size": 48735,
"upload_time": "2025-09-10T20:54:08",
"upload_time_iso_8601": "2025-09-10T20:54:08.172294Z",
"url": "https://files.pythonhosted.org/packages/d8/87/50f7e8fcaaa87c808fc9b81c8364e46ac68a6b70a1ea25cfe3d1e004a943/fabric_data_agent_sdk-0.1.14a0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "c588240166e3261b0b1e7c260e112c3e21c1a428cb196753f6412835b30231dc",
"md5": "a19a19542d57d50959d92e82ca4a6f3b",
"sha256": "32b367a5f98b8b7ddbf04e96a4d1b886dcd7ff82b9ca15fbe0add537c3067ebf"
},
"downloads": -1,
"filename": "fabric_data_agent_sdk-0.1.14a0.tar.gz",
"has_sig": false,
"md5_digest": "a19a19542d57d50959d92e82ca4a6f3b",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<3.13,>=3.10",
"size": 108533,
"upload_time": "2025-09-10T20:54:06",
"upload_time_iso_8601": "2025-09-10T20:54:06.665622Z",
"url": "https://files.pythonhosted.org/packages/c5/88/240166e3261b0b1e7c260e112c3e21c1a428cb196753f6412835b30231dc/fabric_data_agent_sdk-0.1.14a0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-09-10 20:54:06",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "fabric-data-agent-sdk"
}
JSON