| Name | llama-extract JSON |
| Version |
0.0.5
JSON |
| download |
| home_page | None |
| Summary | Infer schema and extract data from unstructured files |
| upload_time | 2024-09-27 15:33:22 |
| maintainer | None |
| docs_url | None |
| author | Logan Markewich |
| requires_python | <4.0,>=3.8.1 |
| license | MIT |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# LlamaExtract (Experimental)
LlamaExtract is an API created by LlamaIndex to efficiently infer schema and extract data from unstructured files.
LlamaExtract directly integrates with [LlamaIndex](https://github.com/run-llama/llama_index).
Note: LlamaExtract is currently experimental and may change in the future.
Read below for some quickstart information, or see the [full documentation](https://docs.cloud.llamaindex.ai/).
## Getting Started
First, login and get an api-key from [**https://cloud.llamaindex.ai ↗**](https://cloud.llamaindex.ai).
Install the package:
`pip install llama-extract`
Now you can easily infer schemas and extract data from your files:
```python
import nest_asyncio
nest_asyncio.apply()
from llama_extract import LlamaExtract
extractor = LlamaExtract(
api_key="llx-...", # can also be set in your env as LLAMA_CLOUD_API_KEY
num_workers=4, # if multiple files passed, split in `num_workers` API calls
verbose=True,
)
# Infer schema
schema = extractor.infer_schema(
"my_schema", ["./my_file1.pdf", "./my_file2.pdf"]
)
# Extract data
results = extractor.extract(schema.id, ["./my_file1.pdf", "./my_file2.pdf"])
```
## Examples
Several end-to-end examples can be found in the examples folder
- [Getting Started](examples/demo_basic.ipynb)
## Documentation
[https://docs.cloud.llamaindex.ai/](https://docs.cloud.llamaindex.ai/)
Raw data
{
"_id": null,
"home_page": null,
"name": "llama-extract",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.8.1",
"maintainer_email": null,
"keywords": null,
"author": "Logan Markewich",
"author_email": "logan@llamaindex.ai",
"download_url": "https://files.pythonhosted.org/packages/26/b1/a49cd4fa1ac2f0c515d67537ce715e4c66729f9327c8f17ea5ba942d5322/llama_extract-0.0.5.tar.gz",
"platform": null,
"description": "# LlamaExtract (Experimental)\n\nLlamaExtract is an API created by LlamaIndex to efficiently infer schema and extract data from unstructured files.\n\nLlamaExtract directly integrates with [LlamaIndex](https://github.com/run-llama/llama_index).\n\nNote: LlamaExtract is currently experimental and may change in the future.\n\nRead below for some quickstart information, or see the [full documentation](https://docs.cloud.llamaindex.ai/).\n\n## Getting Started\n\nFirst, login and get an api-key from [**https://cloud.llamaindex.ai \u2197**](https://cloud.llamaindex.ai).\n\nInstall the package:\n\n`pip install llama-extract`\n\nNow you can easily infer schemas and extract data from your files:\n\n```python\nimport nest_asyncio\n\nnest_asyncio.apply()\n\nfrom llama_extract import LlamaExtract\n\nextractor = LlamaExtract(\n api_key=\"llx-...\", # can also be set in your env as LLAMA_CLOUD_API_KEY\n num_workers=4, # if multiple files passed, split in `num_workers` API calls\n verbose=True,\n)\n\n# Infer schema\nschema = extractor.infer_schema(\n \"my_schema\", [\"./my_file1.pdf\", \"./my_file2.pdf\"]\n)\n\n# Extract data\nresults = extractor.extract(schema.id, [\"./my_file1.pdf\", \"./my_file2.pdf\"])\n```\n\n## Examples\n\nSeveral end-to-end examples can be found in the examples folder\n\n- [Getting Started](examples/demo_basic.ipynb)\n\n## Documentation\n\n[https://docs.cloud.llamaindex.ai/](https://docs.cloud.llamaindex.ai/)\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Infer schema and extract data from unstructured files",
"version": "0.0.5",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "fd2f0d5f4f46aad941f157ecb73d22596d56664d735494f348fa48cef48486e5",
"md5": "34283d0005c19a7fbcd8b47bd147ca43",
"sha256": "8bf7ec8c7db3052fefb0afcdac785e87824593a65fe408eed18726b0fd1d88fa"
},
"downloads": -1,
"filename": "llama_extract-0.0.5-py3-none-any.whl",
"has_sig": false,
"md5_digest": "34283d0005c19a7fbcd8b47bd147ca43",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.8.1",
"size": 6420,
"upload_time": "2024-09-27T15:33:21",
"upload_time_iso_8601": "2024-09-27T15:33:21.450953Z",
"url": "https://files.pythonhosted.org/packages/fd/2f/0d5f4f46aad941f157ecb73d22596d56664d735494f348fa48cef48486e5/llama_extract-0.0.5-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "26b1a49cd4fa1ac2f0c515d67537ce715e4c66729f9327c8f17ea5ba942d5322",
"md5": "cc276cb68f5a4b9e68e417739c496d0a",
"sha256": "91ecdbe69df5a292b88dee1041d0a702591b7cc1d79a55006f431d77a90f66ed"
},
"downloads": -1,
"filename": "llama_extract-0.0.5.tar.gz",
"has_sig": false,
"md5_digest": "cc276cb68f5a4b9e68e417739c496d0a",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.8.1",
"size": 5575,
"upload_time": "2024-09-27T15:33:22",
"upload_time_iso_8601": "2024-09-27T15:33:22.653104Z",
"url": "https://files.pythonhosted.org/packages/26/b1/a49cd4fa1ac2f0c515d67537ce715e4c66729f9327c8f17ea5ba942d5322/llama_extract-0.0.5.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-09-27 15:33:22",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "llama-extract"
}
