# LlamaIndex Node_Parser Integration: Alibabacloud_Aisearch
## Installation
```
pip install llama-index-node-parser-alibabacloud-aisearch
```
## Optional Installation
For automatic parsing of image slices, you can optionally install `llama-index-readers-alibabacloud-aisearch`.
```
pip install llama-index-readers-alibabacloud-aisearch
```
## Usage
For further details, please visit [document-split-api-details](https://help.aliyun.com/zh/open-search/search-platform/developer-reference/document-split-api-details).
You can specify the `endpoint` and `aisearch_api_key` in the constructor, or set the environment variables `AISEARCH_ENDPOINT` and `AISEARCH_API_KEY`.
```python
from llama_index.node_parser.alibabacloud_aisearch import (
AlibabaCloudAISearchNodeParser,
)
from llama_index.core import Document
try:
from llama_index.readers.alibabacloud_aisearch import (
AlibabaCloudAISearchImageReader,
)
image_reader = AlibabaCloudAISearchImageReader(
service_id="ops-image-analyze-vlm-001"
)
except ImportError:
image_reader = None
node_parser = AlibabaCloudAISearchNodeParser(
chunk_size=1024, image_reader=image_reader
)
nodes = node_parser(
[
Document(text="content1", mimetype="text/markdown"),
Document(
text="content2 ",
mimetype="text/markdown",
),
],
show_progress=True,
)
for i, node in enumerate(nodes):
print(f"[SPLIT#{i}]:\n{node.get_content()}")
print("-" * 80)
```
Raw data
{
"_id": null,
"home_page": null,
"name": "llama-index-node-parser-alibabacloud-aisearch",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.8.1",
"maintainer_email": null,
"keywords": null,
"author": "llama-index",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/0a/22/2483aadc6898207ce4f75651cd20d471bdeb1310c78e36f3aad67858c4e1/llama_index_node_parser_alibabacloud_aisearch-0.1.0.tar.gz",
"platform": null,
"description": "# LlamaIndex Node_Parser Integration: Alibabacloud_Aisearch\n\n## Installation\n\n```\npip install llama-index-node-parser-alibabacloud-aisearch\n```\n\n## Optional Installation\n\nFor automatic parsing of image slices, you can optionally install `llama-index-readers-alibabacloud-aisearch`.\n\n```\npip install llama-index-readers-alibabacloud-aisearch\n```\n\n## Usage\n\nFor further details, please visit [document-split-api-details](https://help.aliyun.com/zh/open-search/search-platform/developer-reference/document-split-api-details).\n\nYou can specify the `endpoint` and `aisearch_api_key` in the constructor, or set the environment variables `AISEARCH_ENDPOINT` and `AISEARCH_API_KEY`.\n\n```python\nfrom llama_index.node_parser.alibabacloud_aisearch import (\n AlibabaCloudAISearchNodeParser,\n)\nfrom llama_index.core import Document\n\ntry:\n from llama_index.readers.alibabacloud_aisearch import (\n AlibabaCloudAISearchImageReader,\n )\n\n image_reader = AlibabaCloudAISearchImageReader(\n service_id=\"ops-image-analyze-vlm-001\"\n )\nexcept ImportError:\n image_reader = None\nnode_parser = AlibabaCloudAISearchNodeParser(\n chunk_size=1024, image_reader=image_reader\n)\nnodes = node_parser(\n [\n Document(text=\"content1\", mimetype=\"text/markdown\"),\n Document(\n text=\"content2 \",\n mimetype=\"text/markdown\",\n ),\n ],\n show_progress=True,\n)\nfor i, node in enumerate(nodes):\n print(f\"[SPLIT#{i}]:\\n{node.get_content()}\")\n print(\"-\" * 80)\n```\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "llama-index node_parser alibabacloud_aisearch integration",
"version": "0.1.0",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "2a6e95f9cc1b5f63f697188fe8008f3e7a9d774c1fb6bb675b7f6eee7f329b0a",
"md5": "6aa31f907018056a2550c73e031eebf4",
"sha256": "1e8af6a4b623af51045d58aee54ae0c15e13ad8e1f76c92697261d6516ab48ed"
},
"downloads": -1,
"filename": "llama_index_node_parser_alibabacloud_aisearch-0.1.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "6aa31f907018056a2550c73e031eebf4",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.8.1",
"size": 4472,
"upload_time": "2024-09-11T04:15:12",
"upload_time_iso_8601": "2024-09-11T04:15:12.807934Z",
"url": "https://files.pythonhosted.org/packages/2a/6e/95f9cc1b5f63f697188fe8008f3e7a9d774c1fb6bb675b7f6eee7f329b0a/llama_index_node_parser_alibabacloud_aisearch-0.1.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "0a222483aadc6898207ce4f75651cd20d471bdeb1310c78e36f3aad67858c4e1",
"md5": "d2e74118bc64f1efb07e968acc0d20da",
"sha256": "985528f73bd24f1562c67ae08908a597b512638d9edfcbbbe4c08e63650d844f"
},
"downloads": -1,
"filename": "llama_index_node_parser_alibabacloud_aisearch-0.1.0.tar.gz",
"has_sig": false,
"md5_digest": "d2e74118bc64f1efb07e968acc0d20da",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.8.1",
"size": 3865,
"upload_time": "2024-09-11T04:15:13",
"upload_time_iso_8601": "2024-09-11T04:15:13.944346Z",
"url": "https://files.pythonhosted.org/packages/0a/22/2483aadc6898207ce4f75651cd20d471bdeb1310c78e36f3aad67858c4e1/llama_index_node_parser_alibabacloud_aisearch-0.1.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-09-11 04:15:13",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "llama-index-node-parser-alibabacloud-aisearch"
}
JSON