| Name | caseflow JSON |
| Version |
0.1.4
JSON |
| download |
| home_page | None |
| Summary | Replay the interface recording packets, orchestrate and run them based on the LCEL using the langChain. |
| upload_time | 2024-07-28 12:48:58 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.11 |
| license | MIT |
| keywords |
caseflow
langchain
lcel
rpa
case
interface test
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# caseflow
使用langchain 的LCEL语法来编排用例组成，每一步，每一个用例都是runnable对象。
每个步骤或用例都可使用 lanngchain的callbackmanager、retry等
每个自动化用例都可装饰成agent tool，供agent使用。此agent即为具有AI的RPA（Robotic Process Automation）。
用例采用接口录制har文件转接口自动化用例，并完成用例参数化。（todo: 此转换过程也可交由agent来自动转换）
# 安装
``` shell
pip install caseflow
```
# 示例
``` python
import asyncio
from langchain_core.globals import set_verbose
from caseflow import CaseStep
from caseflow.run_case import parse_har
set_verbose(True)
stepJson_1 = parse_har("file/request.step_1.har")
stepJson_2 = parse_har("file/request.step_2.har")
flow = (
CaseStep(step_json_file_path=stepJson_1)
| CaseStep(step_json_file_path=stepJson_2)
)
# invoke
result = flow.invoke({})
print(result)
# ainvoke
result = asyncio.run(
flow.ainvoke(
{},
config={
"callbacks": [
# CaseStepStdOutCallbackHandler(),
]
},
)
)
print(result)
# stream
for chunk in flow.stream({}):
print(chunk)
# astream
async def stream_output():
async for chunk in flow.astream({}):
print(chunk)
asyncio.run(stream_output())
```
Raw data
{
"_id": null,
"home_page": null,
"name": "caseflow",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.11",
"maintainer_email": null,
"keywords": "caseflow, langchain, LCEL, RPA, case, interface test",
"author": null,
"author_email": "gnakw <gnakw@outlook.com>",
"download_url": "https://files.pythonhosted.org/packages/99/bb/f4f0adf03ee7225523138f96cac0de4e4ad27c7b67d1bd5b6bd87dcb7066/caseflow-0.1.4.tar.gz",
"platform": null,
"description": "# caseflow\n\n\u4f7f\u7528langchain \u7684LCEL\u8bed\u6cd5\u6765\u7f16\u6392\u7528\u4f8b\u7ec4\u6210\uff0c\u6bcf\u4e00\u6b65\uff0c\u6bcf\u4e00\u4e2a\u7528\u4f8b\u90fd\u662frunnable\u5bf9\u8c61\u3002\n\n\u6bcf\u4e2a\u6b65\u9aa4\u6216\u7528\u4f8b\u90fd\u53ef\u4f7f\u7528 lanngchain\u7684callbackmanager\u3001retry\u7b49\n\n\u6bcf\u4e2a\u81ea\u52a8\u5316\u7528\u4f8b\u90fd\u53ef\u88c5\u9970\u6210agent tool\uff0c\u4f9bagent\u4f7f\u7528\u3002\u6b64agent\u5373\u4e3a\u5177\u6709AI\u7684RPA\uff08Robotic Process Automation\uff09\u3002\n\n\u7528\u4f8b\u91c7\u7528\u63a5\u53e3\u5f55\u5236har\u6587\u4ef6\u8f6c\u63a5\u53e3\u81ea\u52a8\u5316\u7528\u4f8b\uff0c\u5e76\u5b8c\u6210\u7528\u4f8b\u53c2\u6570\u5316\u3002\uff08todo: \u6b64\u8f6c\u6362\u8fc7\u7a0b\u4e5f\u53ef\u4ea4\u7531agent\u6765\u81ea\u52a8\u8f6c\u6362\uff09\n\n# \u5b89\u88c5\n\n``` shell\npip install caseflow\n```\n\n# \u793a\u4f8b\n\n``` python\n\nimport asyncio\n\nfrom langchain_core.globals import set_verbose\n\nfrom caseflow import CaseStep\nfrom caseflow.run_case import parse_har\n\nset_verbose(True)\n\nstepJson_1 = parse_har(\"file/request.step_1.har\")\nstepJson_2 = parse_har(\"file/request.step_2.har\")\n\nflow = (\n CaseStep(step_json_file_path=stepJson_1)\n | CaseStep(step_json_file_path=stepJson_2)\n)\n \n\n# invoke\nresult = flow.invoke({})\nprint(result)\n\n# ainvoke\nresult = asyncio.run(\n flow.ainvoke(\n {},\n config={\n \"callbacks\": [\n # CaseStepStdOutCallbackHandler(),\n ]\n },\n )\n)\nprint(result)\n\n# stream\nfor chunk in flow.stream({}):\n print(chunk)\n\n\n# astream\nasync def stream_output():\n async for chunk in flow.astream({}):\n print(chunk)\n\n\nasyncio.run(stream_output())\n\n```\n\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Replay the interface recording packets, orchestrate and run them based on the LCEL using the langChain.",
"version": "0.1.4",
"project_urls": null,
"split_keywords": [
"caseflow",
" langchain",
" lcel",
" rpa",
" case",
" interface test"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "09fd7ed636a20babf6c51a5574e8c09424684bc357421883a714acd7bedfe082",
"md5": "c45f639bf7c23e0da0fcde7687f20e28",
"sha256": "4df680208f18610f7692fe7b0de93dc5abc3bd28084c04184c57a88b947c37ee"
},
"downloads": -1,
"filename": "caseflow-0.1.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "c45f639bf7c23e0da0fcde7687f20e28",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.11",
"size": 22944,
"upload_time": "2024-07-28T12:48:57",
"upload_time_iso_8601": "2024-07-28T12:48:57.067314Z",
"url": "https://files.pythonhosted.org/packages/09/fd/7ed636a20babf6c51a5574e8c09424684bc357421883a714acd7bedfe082/caseflow-0.1.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "99bbf4f0adf03ee7225523138f96cac0de4e4ad27c7b67d1bd5b6bd87dcb7066",
"md5": "5afbaa942ecc07003dc9f22d38503c72",
"sha256": "668d88a01d7204531fe735378a68931f0bc0895477474bfdc3127c3d806612d2"
},
"downloads": -1,
"filename": "caseflow-0.1.4.tar.gz",
"has_sig": false,
"md5_digest": "5afbaa942ecc07003dc9f22d38503c72",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.11",
"size": 19645,
"upload_time": "2024-07-28T12:48:58",
"upload_time_iso_8601": "2024-07-28T12:48:58.324622Z",
"url": "https://files.pythonhosted.org/packages/99/bb/f4f0adf03ee7225523138f96cac0de4e4ad27c7b67d1bd5b6bd87dcb7066/caseflow-0.1.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-07-28 12:48:58",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "caseflow"
}
