Name | llama-parser JSON |
Version |
0.1.2
JSON |
| download |
home_page | |
Summary | Parse files into RAG-Optimized formats. |
upload_time | 2024-02-02 01:52:46 |
maintainer | |
docs_url | None |
author | Logan Markewich |
requires_python | >=3.8.1,<4.0 |
license | MIT |
keywords |
|
VCS |
|
bugtrack_url |
|
requirements |
No requirements were recorded.
|
Travis-CI |
No Travis.
|
coveralls test coverage |
No coveralls.
|
# Llama Parser (Preview)
Llama Parser is an API created by LlamaIndex to effeciently parse and represent files for effecient retrieval and context augmentation using LlamaIndex frameworks.
Available for free as a preivew, you can try it out today.
**NOTE:** Currently, only PDF files are supported.
## Getting Started
First, login and get an api-key from `https://cloud.llamaindex.ai`.
Simply install the package:
`pip install llama-parser`
Then, you can run the following to parse your first PDF file:
```python
from llama_parser import LlamaParser
parser = LlamaParser(
api_key="...", # can also be set in your env as LLAMA_CLOUD_API_KEY
result_type="markdown" # "markdown" and "text" are available
)
# sync
documents = parser.load_data("./my_file.pdf")
# async
documents = await parser.aload_data("./my_file.pdf")
```
## Using with `SimpleDirectoryReader`
You can also integrate the parser as the default PDF loader in `SimpleDirectoryReader`:
```python
from llama_parser import LlamaParser
from llama_index import SimpleDirectoryReader
parser = LlamaParser(
api_key="...", # can also be set in your env as LLAMA_CLOUD_API_KEY
result_type="markdown" # "markdown" and "text" are available
)
file_extractor = {".pdf": parser}
documents = SimpleDirectoryReader("./data", file_extractor=file_extractor).load_data()
```
Full documentation for `SimpleDirectoryReader` can be found on the [LlamaIndex Documentation](https://docs.llamaindex.ai/en/stable/module_guides/loading/simpledirectoryreader.html).
## Examples
Serveral end-to-end indexing examples can be found in the examples folder
- [Getting Started](examples/demo_basic.ipynb)
- [Advanced RAG Example](examples/demo_advanced.ipynb)
- [Raw API Usage](examples/demo_api.ipynb)
Raw data
{
"_id": null,
"home_page": "",
"name": "llama-parser",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.8.1,<4.0",
"maintainer_email": "",
"keywords": "",
"author": "Logan Markewich",
"author_email": "logan@llamaindex.ai",
"download_url": "https://files.pythonhosted.org/packages/de/f8/a342a438683fe3bdc913c71bf0d8b9579505944ee635392f677e06ab846f/llama_parser-0.1.2.tar.gz",
"platform": null,
"description": "# Llama Parser (Preview)\n\nLlama Parser is an API created by LlamaIndex to effeciently parse and represent files for effecient retrieval and context augmentation using LlamaIndex frameworks.\n\nAvailable for free as a preivew, you can try it out today.\n\n**NOTE:** Currently, only PDF files are supported.\n\n## Getting Started\n\nFirst, login and get an api-key from `https://cloud.llamaindex.ai`.\n\nSimply install the package:\n\n`pip install llama-parser`\n\nThen, you can run the following to parse your first PDF file:\n\n```python\nfrom llama_parser import LlamaParser\n\nparser = LlamaParser(\n api_key=\"...\", # can also be set in your env as LLAMA_CLOUD_API_KEY\n result_type=\"markdown\" # \"markdown\" and \"text\" are available\n)\n\n# sync\ndocuments = parser.load_data(\"./my_file.pdf\")\n\n# async\ndocuments = await parser.aload_data(\"./my_file.pdf\")\n```\n\n## Using with `SimpleDirectoryReader`\n\nYou can also integrate the parser as the default PDF loader in `SimpleDirectoryReader`:\n\n```python\nfrom llama_parser import LlamaParser\nfrom llama_index import SimpleDirectoryReader\n\nparser = LlamaParser(\n api_key=\"...\", # can also be set in your env as LLAMA_CLOUD_API_KEY\n result_type=\"markdown\" # \"markdown\" and \"text\" are available\n)\n\nfile_extractor = {\".pdf\": parser}\ndocuments = SimpleDirectoryReader(\"./data\", file_extractor=file_extractor).load_data()\n```\n\nFull documentation for `SimpleDirectoryReader` can be found on the [LlamaIndex Documentation](https://docs.llamaindex.ai/en/stable/module_guides/loading/simpledirectoryreader.html).\n\n## Examples\n\nServeral end-to-end indexing examples can be found in the examples folder\n\n- [Getting Started](examples/demo_basic.ipynb)\n- [Advanced RAG Example](examples/demo_advanced.ipynb)\n- [Raw API Usage](examples/demo_api.ipynb)\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Parse files into RAG-Optimized formats.",
"version": "0.1.2",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "a170408f9b2ed393d1b3c70411433b813d35e39919d032030df02df63cab73f8",
"md5": "9684a51dfaad175174f28c735ae424df",
"sha256": "908c69632b4671542743a73ef3574a7c1fa730f70ceed1b2b86b6f69481efd09"
},
"downloads": -1,
"filename": "llama_parser-0.1.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "9684a51dfaad175174f28c735ae424df",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8.1,<4.0",
"size": 4214,
"upload_time": "2024-02-02T01:52:44",
"upload_time_iso_8601": "2024-02-02T01:52:44.636965Z",
"url": "https://files.pythonhosted.org/packages/a1/70/408f9b2ed393d1b3c70411433b813d35e39919d032030df02df63cab73f8/llama_parser-0.1.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "def8a342a438683fe3bdc913c71bf0d8b9579505944ee635392f677e06ab846f",
"md5": "eddd31b2deacb4937af5f56f879ac8bf",
"sha256": "6b7b4c1dfe23573fd0ba09ac7301463fffd493e2b12308948009f0ca5c038a04"
},
"downloads": -1,
"filename": "llama_parser-0.1.2.tar.gz",
"has_sig": false,
"md5_digest": "eddd31b2deacb4937af5f56f879ac8bf",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8.1,<4.0",
"size": 3494,
"upload_time": "2024-02-02T01:52:46",
"upload_time_iso_8601": "2024-02-02T01:52:46.348044Z",
"url": "https://files.pythonhosted.org/packages/de/f8/a342a438683fe3bdc913c71bf0d8b9579505944ee635392f677e06ab846f/llama_parser-0.1.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-02-02 01:52:46",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "llama-parser"
}