| Name | llama-parse JSON |
| Version |
0.6.78
JSON |
| download |
| home_page | None |
| Summary | Parse files into RAG-Optimized formats. |
| upload_time | 2025-11-04 02:16:22 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | <4.0,>=3.9 |
| license | None |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# LlamaParse
[](https://pypi.org/project/llama-parse/)
[](https://github.com/run-llama/llama_parse/graphs/contributors)
[](https://discord.gg/dGcwcsnxhU)
LlamaParse is a **GenAI-native document parser** that can parse complex document data for any downstream LLM use case (RAG, agents).
It is really good at the following:
- ✅ **Broad file type support**: Parsing a variety of unstructured file types (.pdf, .pptx, .docx, .xlsx, .html) with text, tables, visual elements, weird layouts, and more.
- ✅ **Table recognition**: Parsing embedded tables accurately into text and semi-structured representations.
- ✅ **Multimodal parsing and chunking**: Extracting visual elements (images/diagrams) into structured formats and return image chunks using the latest multimodal models.
- ✅ **Custom parsing**: Input custom prompt instructions to customize the output the way you want it.
LlamaParse directly integrates with [LlamaIndex](https://github.com/run-llama/llama_index).
The free plan is up to 1000 pages a day. Paid plan is free 7k pages per week + 0.3c per additional page by default. There is a sandbox available to test the API [**https://cloud.llamaindex.ai/parse ↗**](https://cloud.llamaindex.ai/parse).
Read below for some quickstart information, or see the [full documentation](https://docs.cloud.llamaindex.ai/).
If you're a company interested in enterprise RAG solutions, and/or high volume/on-prem usage of LlamaParse, come [talk to us](https://www.llamaindex.ai/contact).
## Getting Started
First, login and get an api-key from [**https://cloud.llamaindex.ai/api-key ↗**](https://cloud.llamaindex.ai/api-key).
Then, make sure you have the latest LlamaIndex version installed.
**NOTE:** If you are upgrading from v0.9.X, we recommend following our [migration guide](https://pretty-sodium-5e0.notion.site/v0-10-0-Migration-Guide-6ede431dcb8841b09ea171e7f133bd77), as well as uninstalling your previous version first.
```
pip uninstall llama-index # run this if upgrading from v0.9.x or older
pip install -U llama-index --upgrade --no-cache-dir --force-reinstall
```
Lastly, install the package:
`pip install llama-parse`
Now you can parse your first PDF file using the command line interface. Use the command `llama-parse [file_paths]`. See the help text with `llama-parse --help`.
```bash
export LLAMA_CLOUD_API_KEY='llx-...'
# output as text
llama-parse my_file.pdf --result-type text --output-file output.txt
# output as markdown
llama-parse my_file.pdf --result-type markdown --output-file output.md
# output as raw json
llama-parse my_file.pdf --output-raw-json --output-file output.json
```
You can also create simple scripts:
```python
import nest_asyncio
nest_asyncio.apply()
from llama_parse import LlamaParse
parser = LlamaParse(
api_key="llx-...", # can also be set in your env as LLAMA_CLOUD_API_KEY
result_type="markdown", # "markdown" and "text" are available
num_workers=4, # if multiple files passed, split in `num_workers` API calls
verbose=True,
language="en", # Optionally you can define a language, default=en
)
# sync
documents = parser.load_data("./my_file.pdf")
# sync batch
documents = parser.load_data(["./my_file1.pdf", "./my_file2.pdf"])
# async
documents = await parser.aload_data("./my_file.pdf")
# async batch
documents = await parser.aload_data(["./my_file1.pdf", "./my_file2.pdf"])
```
## Using with file object
You can parse a file object directly:
```python
import nest_asyncio
nest_asyncio.apply()
from llama_parse import LlamaParse
parser = LlamaParse(
api_key="llx-...", # can also be set in your env as LLAMA_CLOUD_API_KEY
result_type="markdown", # "markdown" and "text" are available
num_workers=4, # if multiple files passed, split in `num_workers` API calls
verbose=True,
language="en", # Optionally you can define a language, default=en
)
file_name = "my_file1.pdf"
extra_info = {"file_name": file_name}
with open(f"./{file_name}", "rb") as f:
# must provide extra_info with file_name key with passing file object
documents = parser.load_data(f, extra_info=extra_info)
# you can also pass file bytes directly
with open(f"./{file_name}", "rb") as f:
file_bytes = f.read()
# must provide extra_info with file_name key with passing file bytes
documents = parser.load_data(file_bytes, extra_info=extra_info)
```
## Using with `SimpleDirectoryReader`
You can also integrate the parser as the default PDF loader in `SimpleDirectoryReader`:
```python
import nest_asyncio
nest_asyncio.apply()
from llama_parse import LlamaParse
from llama_index.core import SimpleDirectoryReader
parser = LlamaParse(
api_key="llx-...", # can also be set in your env as LLAMA_CLOUD_API_KEY
result_type="markdown", # "markdown" and "text" are available
verbose=True,
)
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
Several end-to-end indexing examples can be found in the examples folder
- [Getting Started](/docs/examples-py/parse/demo_basic.ipynb)
- [Advanced RAG Example](/docs/examples-py/parse/demo_advanced.ipynb)
- [Raw API Usage](/docs/examples-py/parse/demo_api.ipynb)
## Documentation
[https://docs.cloud.llamaindex.ai/](https://docs.cloud.llamaindex.ai/)
## Terms of Service
See the [Terms of Service Here](./TOS.pdf).
## Get in Touch (LlamaCloud)
LlamaParse is part of LlamaCloud, our e2e enterprise RAG platform that provides out-of-the-box, production-ready connectors, indexing, and retrieval over your complex data sources. We offer SaaS and VPC options.
LlamaCloud is currently available via waitlist (join by [creating an account](https://cloud.llamaindex.ai/)). If you're interested in state-of-the-art quality and in centralizing your RAG efforts, come [get in touch with us](https://www.llamaindex.ai/contact).
Raw data
{
"_id": null,
"home_page": null,
"name": "llama-parse",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.9",
"maintainer_email": null,
"keywords": null,
"author": null,
"author_email": "Logan Markewich <logan@llamaindex.ai>",
"download_url": "https://files.pythonhosted.org/packages/e7/6c/906cc53ff9a3fd0aec639de4809b4050664a10f8270de651ce33bbc299b0/llama_parse-0.6.78.tar.gz",
"platform": null,
"description": "# LlamaParse\n\n[](https://pypi.org/project/llama-parse/)\n[](https://github.com/run-llama/llama_parse/graphs/contributors)\n[](https://discord.gg/dGcwcsnxhU)\n\nLlamaParse is a **GenAI-native document parser** that can parse complex document data for any downstream LLM use case (RAG, agents).\n\nIt is really good at the following:\n\n- \u2705 **Broad file type support**: Parsing a variety of unstructured file types (.pdf, .pptx, .docx, .xlsx, .html) with text, tables, visual elements, weird layouts, and more.\n- \u2705 **Table recognition**: Parsing embedded tables accurately into text and semi-structured representations.\n- \u2705 **Multimodal parsing and chunking**: Extracting visual elements (images/diagrams) into structured formats and return image chunks using the latest multimodal models.\n- \u2705 **Custom parsing**: Input custom prompt instructions to customize the output the way you want it.\n\nLlamaParse directly integrates with [LlamaIndex](https://github.com/run-llama/llama_index).\n\nThe free plan is up to 1000 pages a day. Paid plan is free 7k pages per week + 0.3c per additional page by default. There is a sandbox available to test the API [**https://cloud.llamaindex.ai/parse \u2197**](https://cloud.llamaindex.ai/parse).\n\nRead below for some quickstart information, or see the [full documentation](https://docs.cloud.llamaindex.ai/).\n\nIf you're a company interested in enterprise RAG solutions, and/or high volume/on-prem usage of LlamaParse, come [talk to us](https://www.llamaindex.ai/contact).\n\n## Getting Started\n\nFirst, login and get an api-key from [**https://cloud.llamaindex.ai/api-key \u2197**](https://cloud.llamaindex.ai/api-key).\n\nThen, make sure you have the latest LlamaIndex version installed.\n\n**NOTE:** If you are upgrading from v0.9.X, we recommend following our [migration guide](https://pretty-sodium-5e0.notion.site/v0-10-0-Migration-Guide-6ede431dcb8841b09ea171e7f133bd77), as well as uninstalling your previous version first.\n\n```\npip uninstall llama-index # run this if upgrading from v0.9.x or older\npip install -U llama-index --upgrade --no-cache-dir --force-reinstall\n```\n\nLastly, install the package:\n\n`pip install llama-parse`\n\nNow you can parse your first PDF file using the command line interface. Use the command `llama-parse [file_paths]`. See the help text with `llama-parse --help`.\n\n```bash\nexport LLAMA_CLOUD_API_KEY='llx-...'\n\n# output as text\nllama-parse my_file.pdf --result-type text --output-file output.txt\n\n# output as markdown\nllama-parse my_file.pdf --result-type markdown --output-file output.md\n\n# output as raw json\nllama-parse my_file.pdf --output-raw-json --output-file output.json\n```\n\nYou can also create simple scripts:\n\n```python\nimport nest_asyncio\n\nnest_asyncio.apply()\n\nfrom llama_parse import LlamaParse\n\nparser = LlamaParse(\n api_key=\"llx-...\", # can also be set in your env as LLAMA_CLOUD_API_KEY\n result_type=\"markdown\", # \"markdown\" and \"text\" are available\n num_workers=4, # if multiple files passed, split in `num_workers` API calls\n verbose=True,\n language=\"en\", # Optionally you can define a language, default=en\n)\n\n# sync\ndocuments = parser.load_data(\"./my_file.pdf\")\n\n# sync batch\ndocuments = parser.load_data([\"./my_file1.pdf\", \"./my_file2.pdf\"])\n\n# async\ndocuments = await parser.aload_data(\"./my_file.pdf\")\n\n# async batch\ndocuments = await parser.aload_data([\"./my_file1.pdf\", \"./my_file2.pdf\"])\n```\n\n## Using with file object\n\nYou can parse a file object directly:\n\n```python\nimport nest_asyncio\n\nnest_asyncio.apply()\n\nfrom llama_parse import LlamaParse\n\nparser = LlamaParse(\n api_key=\"llx-...\", # can also be set in your env as LLAMA_CLOUD_API_KEY\n result_type=\"markdown\", # \"markdown\" and \"text\" are available\n num_workers=4, # if multiple files passed, split in `num_workers` API calls\n verbose=True,\n language=\"en\", # Optionally you can define a language, default=en\n)\n\nfile_name = \"my_file1.pdf\"\nextra_info = {\"file_name\": file_name}\n\nwith open(f\"./{file_name}\", \"rb\") as f:\n # must provide extra_info with file_name key with passing file object\n documents = parser.load_data(f, extra_info=extra_info)\n\n# you can also pass file bytes directly\nwith open(f\"./{file_name}\", \"rb\") as f:\n file_bytes = f.read()\n # must provide extra_info with file_name key with passing file bytes\n documents = parser.load_data(file_bytes, extra_info=extra_info)\n```\n\n## Using with `SimpleDirectoryReader`\n\nYou can also integrate the parser as the default PDF loader in `SimpleDirectoryReader`:\n\n```python\nimport nest_asyncio\n\nnest_asyncio.apply()\n\nfrom llama_parse import LlamaParse\nfrom llama_index.core import SimpleDirectoryReader\n\nparser = LlamaParse(\n api_key=\"llx-...\", # can also be set in your env as LLAMA_CLOUD_API_KEY\n result_type=\"markdown\", # \"markdown\" and \"text\" are available\n verbose=True,\n)\n\nfile_extractor = {\".pdf\": parser}\ndocuments = SimpleDirectoryReader(\n \"./data\", file_extractor=file_extractor\n).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\nSeveral end-to-end indexing examples can be found in the examples folder\n\n- [Getting Started](/docs/examples-py/parse/demo_basic.ipynb)\n- [Advanced RAG Example](/docs/examples-py/parse/demo_advanced.ipynb)\n- [Raw API Usage](/docs/examples-py/parse/demo_api.ipynb)\n\n## Documentation\n\n[https://docs.cloud.llamaindex.ai/](https://docs.cloud.llamaindex.ai/)\n\n## Terms of Service\n\nSee the [Terms of Service Here](./TOS.pdf).\n\n## Get in Touch (LlamaCloud)\n\nLlamaParse is part of LlamaCloud, our e2e enterprise RAG platform that provides out-of-the-box, production-ready connectors, indexing, and retrieval over your complex data sources. We offer SaaS and VPC options.\n\nLlamaCloud is currently available via waitlist (join by [creating an account](https://cloud.llamaindex.ai/)). If you're interested in state-of-the-art quality and in centralizing your RAG efforts, come [get in touch with us](https://www.llamaindex.ai/contact).\n",
"bugtrack_url": null,
"license": null,
"summary": "Parse files into RAG-Optimized formats.",
"version": "0.6.78",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "8e82bd2f6880d4141536fe27f12103d38aec4caddbca3d8509208b6926860bcc",
"md5": "aeb4543c0de34e134e5dd5bf07065df0",
"sha256": "2ea72aa8ecca1c0ae4799d5bce9a0a3a93c5e66c9bb545b5f2ea7888bb327987"
},
"downloads": -1,
"filename": "llama_parse-0.6.78-py3-none-any.whl",
"has_sig": false,
"md5_digest": "aeb4543c0de34e134e5dd5bf07065df0",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.9",
"size": 4880,
"upload_time": "2025-11-04T02:16:21",
"upload_time_iso_8601": "2025-11-04T02:16:21.382950Z",
"url": "https://files.pythonhosted.org/packages/8e/82/bd2f6880d4141536fe27f12103d38aec4caddbca3d8509208b6926860bcc/llama_parse-0.6.78-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "e76c906cc53ff9a3fd0aec639de4809b4050664a10f8270de651ce33bbc299b0",
"md5": "ac2ace4ca27947014c2f3638bbfe3023",
"sha256": "1a386d165de9a9bbf644a56de23b4935a04c4c78cbbd489821889b16279e62be"
},
"downloads": -1,
"filename": "llama_parse-0.6.78.tar.gz",
"has_sig": false,
"md5_digest": "ac2ace4ca27947014c2f3638bbfe3023",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.9",
"size": 3579,
"upload_time": "2025-11-04T02:16:22",
"upload_time_iso_8601": "2025-11-04T02:16:22.308824Z",
"url": "https://files.pythonhosted.org/packages/e7/6c/906cc53ff9a3fd0aec639de4809b4050664a10f8270de651ce33bbc299b0/llama_parse-0.6.78.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-11-04 02:16:22",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "llama-parse"
}
