llama-index-readers-alibabacloud-aisearch


Namellama-index-readers-alibabacloud-aisearch JSON
Version 0.1.0 PyPI version JSON
download
home_pageNone
Summaryllama-index readers alibabacloud_aisearch integration
upload_time2024-09-11 04:15:43
maintainerNone
docs_urlNone
authorllama-index
requires_python<4.0,>=3.8.1
licenseMIT
keywords
VCS
bugtrack_url
requirements No requirements were recorded.
Travis-CI No Travis.
coveralls test coverage No coveralls.
            # LlamaIndex Readers Integration: Alibabacloud_Aisearch

## Installation

```
pip install llama-index-readers-alibabacloud-aisearch
```

## Usage

Supported file types: ppt/pptx, doc/docx, pdf, images and so on.
For further details, please visit:

- [document-analyze-api-details](https://help.aliyun.com/zh/open-search/search-platform/developer-reference/api-details)
- [image-analyze-api-details](https://help.aliyun.com/zh/open-search/search-platform/developer-reference/opensearch-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`.

### Read local files

```python
from llama_index.readers.alibabacloud_aisearch import (
    AlibabaCloudAISearchDocumentReader,
    AlibabaCloudAISearchImageReader,
)
from llama_index.core import SimpleDirectoryReader

document_reader = AlibabaCloudAISearchDocumentReader()
image_reader = AlibabaCloudAISearchImageReader()

file_extractor = {}
for suffix in (".pdf", ".docx", ".doc", ".ppt", ".pptx"):
    file_extractor[suffix] = document_reader
for suffix in (".jpg", ".jpeg", ".png", ".bmp", ".tiff"):
    file_extractor[suffix] = image_reader

documents = SimpleDirectoryReader(
    "./data", file_extractor=file_extractor
).load_data(show_progress=True)
print(documents)
```

### Read remote files

```python
from llama_index.readers.alibabacloud_aisearch import (
    AlibabaCloudAISearchImageReader,
)

image_reader = AlibabaCloudAISearchImageReader(
    service_id="ops-image-analyze-ocr-001"
)
image_urls = [
    "https://img.alicdn.com/imgextra/i1/O1CN01WksnF41hlhBFsXDNB_!!6000000004318-0-tps-1000-1400.jpg",
]

# The file_type is automatically determined based on the file extension.
# If it cannot be identified, manual specification of the file_type is required.
documents = image_reader.load_data(file_path=image_urls, file_type="jpg")
print(documents)
```

            

Raw data

            {
    "_id": null,
    "home_page": null,
    "name": "llama-index-readers-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/97/87/19b4a4629535c8ae7cc70506779830f6ee07891ac7a1911b4e4bf3b616e8/llama_index_readers_alibabacloud_aisearch-0.1.0.tar.gz",
    "platform": null,
    "description": "# LlamaIndex Readers Integration: Alibabacloud_Aisearch\n\n## Installation\n\n```\npip install llama-index-readers-alibabacloud-aisearch\n```\n\n## Usage\n\nSupported file types: ppt/pptx, doc/docx, pdf, images and so on.\nFor further details, please visit:\n\n- [document-analyze-api-details](https://help.aliyun.com/zh/open-search/search-platform/developer-reference/api-details)\n- [image-analyze-api-details](https://help.aliyun.com/zh/open-search/search-platform/developer-reference/opensearch-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### Read local files\n\n```python\nfrom llama_index.readers.alibabacloud_aisearch import (\n    AlibabaCloudAISearchDocumentReader,\n    AlibabaCloudAISearchImageReader,\n)\nfrom llama_index.core import SimpleDirectoryReader\n\ndocument_reader = AlibabaCloudAISearchDocumentReader()\nimage_reader = AlibabaCloudAISearchImageReader()\n\nfile_extractor = {}\nfor suffix in (\".pdf\", \".docx\", \".doc\", \".ppt\", \".pptx\"):\n    file_extractor[suffix] = document_reader\nfor suffix in (\".jpg\", \".jpeg\", \".png\", \".bmp\", \".tiff\"):\n    file_extractor[suffix] = image_reader\n\ndocuments = SimpleDirectoryReader(\n    \"./data\", file_extractor=file_extractor\n).load_data(show_progress=True)\nprint(documents)\n```\n\n### Read remote files\n\n```python\nfrom llama_index.readers.alibabacloud_aisearch import (\n    AlibabaCloudAISearchImageReader,\n)\n\nimage_reader = AlibabaCloudAISearchImageReader(\n    service_id=\"ops-image-analyze-ocr-001\"\n)\nimage_urls = [\n    \"https://img.alicdn.com/imgextra/i1/O1CN01WksnF41hlhBFsXDNB_!!6000000004318-0-tps-1000-1400.jpg\",\n]\n\n# The file_type is automatically determined based on the file extension.\n# If it cannot be identified, manual specification of the file_type is required.\ndocuments = image_reader.load_data(file_path=image_urls, file_type=\"jpg\")\nprint(documents)\n```\n",
    "bugtrack_url": null,
    "license": "MIT",
    "summary": "llama-index readers alibabacloud_aisearch integration",
    "version": "0.1.0",
    "project_urls": null,
    "split_keywords": [],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "5561bff08ca197cc56149c809903d7d643656721263556141b47fb0281993751",
                "md5": "9736f3cac5b983db4c7e92782a69086f",
                "sha256": "91edf94db55b7d1c3d1fa1d2a0d16f68ce7f3020815423144b5a8ec14bd6f444"
            },
            "downloads": -1,
            "filename": "llama_index_readers_alibabacloud_aisearch-0.1.0-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "9736f3cac5b983db4c7e92782a69086f",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": "<4.0,>=3.8.1",
            "size": 4903,
            "upload_time": "2024-09-11T04:15:42",
            "upload_time_iso_8601": "2024-09-11T04:15:42.014965Z",
            "url": "https://files.pythonhosted.org/packages/55/61/bff08ca197cc56149c809903d7d643656721263556141b47fb0281993751/llama_index_readers_alibabacloud_aisearch-0.1.0-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "978719b4a4629535c8ae7cc70506779830f6ee07891ac7a1911b4e4bf3b616e8",
                "md5": "b1d448a215ad4ed7f609f80e6f3b6227",
                "sha256": "8da2ba9a8888018f0946206cd43bdcbd8f6c95504882cb06d8a92409c3c8343f"
            },
            "downloads": -1,
            "filename": "llama_index_readers_alibabacloud_aisearch-0.1.0.tar.gz",
            "has_sig": false,
            "md5_digest": "b1d448a215ad4ed7f609f80e6f3b6227",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": "<4.0,>=3.8.1",
            "size": 4276,
            "upload_time": "2024-09-11T04:15:43",
            "upload_time_iso_8601": "2024-09-11T04:15:43.646324Z",
            "url": "https://files.pythonhosted.org/packages/97/87/19b4a4629535c8ae7cc70506779830f6ee07891ac7a1911b4e4bf3b616e8/llama_index_readers_alibabacloud_aisearch-0.1.0.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2024-09-11 04:15:43",
    "github": false,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "lcname": "llama-index-readers-alibabacloud-aisearch"
}
        
Elapsed time: 0.46149s