<!-- <h4 align="center">
<img alt="AdalFlow logo" src="docs/source/_static/images/adalflow-logo.png" style="width: 100%;">
</h4> -->
<h4 align="center">
<img alt="AdalFlow logo" src="https://raw.githubusercontent.com/SylphAI-Inc/LightRAG/main/docs/source/_static/images/adalflow-logo.png" style="width: 100%;">
</h4>
<p align="center">
<a href="https://colab.research.google.com/drive/1TKw_JHE42Z_AWo8UuRYZCO2iuMgyslTZ?usp=sharing">
<img alt="Try Quickstart in Colab" src="https://colab.research.google.com/assets/colab-badge.svg">
</a>
</p>
<h4 align="center">
<p>
<a href="https://lightrag.sylph.ai/">Documentation</a> |
<a href="https://lightrag.sylph.ai/apis/components/components.model_client.html">Models</a> |
<a href="https://lightrag.sylph.ai/apis/components/components.retriever.html">Retrievers</a> |
<a href="https://lightrag.sylph.ai/apis/components/components.agent.html">Agents</a>
<p>
</h4>
<p align="center">
<a href="https://pypi.org/project/lightRAG">
<img alt="PyPI Version" src="https://img.shields.io/pypi/v/lightRAG?style=flat-square">
</a>
<a href="https://star-history.com/#SylphAI-Inc/LightRAG">
<img alt="GitHub stars" src="https://img.shields.io/github/stars/SylphAI-Inc/LightRAG?style=flat-square">
</a>
<a href="https://github.com/SylphAI-Inc/LightRAG/issues">
<img alt="Open Issues" src="https://img.shields.io/github/issues-raw/SylphAI-Inc/LightRAG?style=flat-square">
</a>
<a href="https://opensource.org/license/MIT">
<img alt="License" src="https://img.shields.io/github/license/SylphAI-Inc/LightRAG">
</a>
<a href="https://discord.gg/ezzszrRZvT">
<img alt="discord-invite" src="https://dcbadge.vercel.app/api/server/ezzszrRZvT?style=flat">
</a>
</p>
<!-- <a href="https://colab.research.google.com/drive/1PPxYEBa6eu__LquGoFFJZkhYgWVYE6kh?usp=sharing">
<img alt="Try Quickstart in Colab" src="https://colab.research.google.com/assets/colab-badge.svg">
</a> -->
<!-- <a href="https://pypistats.org/packages/lightrag">
<img alt="PyPI Downloads" src="https://img.shields.io/pypi/dm/lightRAG?style=flat-square">
</a> -->
<h1>
<p align="center">
AdalFlow: The Library for Large Language Model Applications
</p>
</h1>
AdalFlow helps developers build and optimize LLM task pipelines.
Embracing similar design pattern to PyTorch, AdalFlow is light, modular, and robust, with a 100% readable codebase.
Note: We are in the progress of renaming to adalflow from lightrag.
# AdalFlow: A Tribute to Ada Lovelace
AdalFlow is named in honor of [Ada Lovelace](https://en.wikipedia.org/wiki/Ada_Lovelace), the pioneering female mathematician who first recognized that machines could do more than just calculations. As a female-led team, we aim to inspire more women to enter the AI field.
# Why AdalFlow?
LLMs are like water; they can be shaped into anything, from GenAI applications such as chatbots, translation, summarization, code generation, and autonomous agents to classical NLP tasks like text classification and named entity recognition. They interact with the world beyond the model’s internal knowledge via retrievers, memory, and tools (function calls). Each use case is unique in its data, business logic, and user experience.
Because of this, no library can provide out-of-the-box solutions. Users must build towards their own use case. This requires the library to be modular, robust, and have a clean, readable codebase. The only code you should put into production is code you either 100% trust or are 100% clear about how to customize and iterate.
<!-- This is what AdalFlow is: light, modular, and robust, with a 100% readable codebase. -->
Further reading: [How We Started](https://www.linkedin.com/posts/li-yin-ai_both-ai-research-and-engineering-use-pytorch-activity-7189366364694892544-Uk1U?utm_source=share&utm_medium=member_desktop),
[Introduction](https://lightrag.sylph.ai/), [Design Philosophy](https://lightrag.sylph.ai/tutorials/lightrag_design_philosophy.html) and [Class hierarchy](https://lightrag.sylph.ai/tutorials/class_hierarchy.html).
<!--
**PyTorch**
```python
import torch
import torch.nn as nn
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(1, 32, 3, 1)
self.conv2 = nn.Conv2d(32, 64, 3, 1)
self.dropout1 = nn.Dropout2d(0.25)
self.dropout2 = nn.Dropout2d(0.5)
self.fc1 = nn.Linear(9216, 128)
self.fc2 = nn.Linear(128, 10)
def forward(self, x):
x = self.conv1(x)
x = self.conv2(x)
x = self.dropout1(x)
x = self.dropout2(x)
x = self.fc1(x)
return self.fc2(x)
``` -->
# AdalFlow Task Pipeline
We will ask the model to respond with ``explanation`` and ``example`` of a concept. To achieve this, we will build a simple pipeline to get the structured output as ``QAOutput``.
## Well-designed Base Classes
This leverages our two and only powerful base classes: `Component` as building blocks for the pipeline and `DataClass` to ease the data interaction with LLMs.
```python
from dataclasses import dataclass, field
from lightrag.core import Component, Generator, DataClass
from lightrag.components.model_client import GroqAPIClient
from lightrag.components.output_parsers import JsonOutputParser
@dataclass
class QAOutput(DataClass):
explanation: str = field(
metadata={"desc": "A brief explanation of the concept in one sentence."}
)
example: str = field(metadata={"desc": "An example of the concept in a sentence."})
qa_template = r"""<SYS>
You are a helpful assistant.
<OUTPUT_FORMAT>
{{output_format_str}}
</OUTPUT_FORMAT>
</SYS>
User: {{input_str}}
You:"""
class QA(Component):
def __init__(self):
super().__init__()
parser = JsonOutputParser(data_class=QAOutput, return_data_class=True)
self.generator = Generator(
model_client=GroqAPIClient(),
model_kwargs={"model": "llama3-8b-8192"},
template=qa_template,
prompt_kwargs={"output_format_str": parser.format_instructions()},
output_processors=parser,
)
def call(self, query: str):
return self.generator.call({"input_str": query})
async def acall(self, query: str):
return await self.generator.acall({"input_str": query})
```
Run the following code for visualization and calling the model.
```python
qa = QA()
print(qa)
# call
output = qa("What is LLM?")
print(output)
```
## Clear Pipeline Structure
Simply by using `print(qa)`, you can see the pipeline structure, which helps users understand any LLM workflow quickly.
```
QA(
(generator): Generator(
model_kwargs={'model': 'llama3-8b-8192'},
(prompt): Prompt(
template: <SYS>
You are a helpful assistant.
<OUTPUT_FORMAT>
{{output_format_str}}
</OUTPUT_FORMAT>
</SYS>
User: {{input_str}}
You:, prompt_kwargs: {'output_format_str': 'Your output should be formatted as a standard JSON instance with the following schema:\n```\n{\n "explanation": "A brief explanation of the concept in one sentence. (str) (required)",\n "example": "An example of the concept in a sentence. (str) (required)"\n}\n```\n-Make sure to always enclose the JSON output in triple backticks (```). Please do not add anything other than valid JSON output!\n-Use double quotes for the keys and string values.\n-Follow the JSON formatting conventions.'}, prompt_variables: ['output_format_str', 'input_str']
)
(model_client): GroqAPIClient()
(output_processors): JsonOutputParser(
data_class=QAOutput, examples=None, exclude_fields=None, return_data_class=True
(json_output_format_prompt): Prompt(
template: Your output should be formatted as a standard JSON instance with the following schema:
```
{{schema}}
```
{% if example %}
Examples:
```
{{example}}
```
{% endif %}
-Make sure to always enclose the JSON output in triple backticks (```). Please do not add anything other than valid JSON output!
-Use double quotes for the keys and string values.
-Follow the JSON formatting conventions., prompt_variables: ['schema', 'example']
)
(output_processors): JsonParser()
)
)
)
```
**The Output**
We structure the output to both track the data and potential errors if any part of the Generator component fails.
Here is what we get from ``print(output)``:
```
GeneratorOutput(data=QAOutput(explanation='LLM stands for Large Language Model, which refers to a type of artificial intelligence designed to process and generate human-like language.', example='For instance, LLMs are used in chatbots and virtual assistants, such as Siri and Alexa, to understand and respond to natural language input.'), error=None, usage=None, raw_response='```\n{\n "explanation": "LLM stands for Large Language Model, which refers to a type of artificial intelligence designed to process and generate human-like language.",\n "example": "For instance, LLMs are used in chatbots and virtual assistants, such as Siri and Alexa, to understand and respond to natural language input."\n}', metadata=None)
```
**Focus on the Prompt**
Use the following code will let us see the prompt after it is formatted:
```python
qa2.generator.print_prompt(
output_format_str=qa2.generator.output_processors.format_instructions(),
input_str="What is LLM?",
)
```
The output will be:
````markdown
<SYS>
You are a helpful assistant.
<OUTPUT_FORMAT>
Your output should be formatted as a standard JSON instance with the following schema:
```
{
"explanation": "A brief explanation of the concept in one sentence. (str) (required)",
"example": "An example of the concept in a sentence. (str) (required)"
}
```
-Make sure to always enclose the JSON output in triple backticks (```). Please do not add anything other than valid JSON output!
-Use double quotes for the keys and string values.
-Follow the JSON formatting conventions.
</OUTPUT_FORMAT>
</SYS>
User: What is LLM?
You:
````
## Model-agnostic
You can switch to any model simply by using a different `model_client` (provider) and `model_kwargs`.
Let's use OpenAI's `gpt-3.5-turbo` model.
```python
from lightrag.components.model_client import OpenAIClient
self.generator = Generator(
model_client=OpenAIClient(),
model_kwargs={"model": "gpt-3.5-turbo"},
template=qa_template,
prompt_kwargs={"output_format_str": parser.format_instructions()},
output_processors=parser,
)
```
# Quick Install
Install AdalFlow with pip:
```bash
pip install lightrag
```
Please refer to the [full installation guide](https://lightrag.sylph.ai/get_started/installation.html) for more details.
# Documentation
AdalFlow full documentation available at [lightrag.sylph.ai](https://lightrag.sylph.ai/):
- [How We Started](https://www.linkedin.com/posts/li-yin-ai_both-ai-research-and-engineering-use-pytorch-activity-7189366364694892544-Uk1U?utm_source=share&utm_medium=member_desktop)
- [Introduction](https://lightrag.sylph.ai/)
- [Full installation guide](https://lightrag.sylph.ai/get_started/installation.html)
- [Design philosophy](https://lightrag.sylph.ai/tutorials/lightrag_design_philosophy.html)
- [Class hierarchy](https://lightrag.sylph.ai/tutorials/class_hierarchy.html)
- [Tutorials](https://lightrag.sylph.ai/tutorials/index.html)
- [Supported Models](https://lightrag.sylph.ai/apis/components/components.model_client.html)
- [Supported Retrievers](https://lightrag.sylph.ai/apis/components/components.retriever.html)
- [API reference](https://lightrag.sylph.ai/apis/index.html)
# Contributors
[](https://github.com/SylphAI-Inc/LightRAG/graphs/contributors)
# Citation
```bibtex
@software{Yin2024AdalFlow,
author = {Li Yin},
title = {{AdalFlow: The Library for Large Language Model (LLM) Applications}},
month = {7},
year = {2024},
doi = {10.5281/zenodo.12639531},
url = {https://github.com/SylphAI-Inc/LightRAG}
}
```
Raw data
{
"_id": null,
"home_page": "https://github.com/SylphAI-Inc/LightRAG",
"name": "lightrag",
"maintainer": "Xiaoyi Gu",
"docs_url": null,
"requires_python": "<4.0,>=3.9",
"maintainer_email": "xiaoyi@sylphai.com",
"keywords": "LLM, NLP, RAG, devtools, retrieval, agent",
"author": "Li Yin",
"author_email": "li@sylphai.com",
"download_url": "https://files.pythonhosted.org/packages/87/42/a7209315eb9627fa50a6b882c40530e4a543a2571a97a9382bffa66e9ed0/lightrag-0.1.0b5.tar.gz",
"platform": null,
"description": "\n<!-- <h4 align=\"center\">\n <img alt=\"AdalFlow logo\" src=\"docs/source/_static/images/adalflow-logo.png\" style=\"width: 100%;\">\n</h4> -->\n\n<h4 align=\"center\">\n <img alt=\"AdalFlow logo\" src=\"https://raw.githubusercontent.com/SylphAI-Inc/LightRAG/main/docs/source/_static/images/adalflow-logo.png\" style=\"width: 100%;\">\n</h4>\n\n\n<p align=\"center\">\n <a href=\"https://colab.research.google.com/drive/1TKw_JHE42Z_AWo8UuRYZCO2iuMgyslTZ?usp=sharing\">\n <img alt=\"Try Quickstart in Colab\" src=\"https://colab.research.google.com/assets/colab-badge.svg\">\n </a>\n</p>\n\n<h4 align=\"center\">\n <p>\n <a href=\"https://lightrag.sylph.ai/\">Documentation</a> |\n <a href=\"https://lightrag.sylph.ai/apis/components/components.model_client.html\">Models</a> |\n <a href=\"https://lightrag.sylph.ai/apis/components/components.retriever.html\">Retrievers</a> |\n <a href=\"https://lightrag.sylph.ai/apis/components/components.agent.html\">Agents</a>\n <p>\n</h4>\n\n<p align=\"center\">\n <a href=\"https://pypi.org/project/lightRAG\">\n <img alt=\"PyPI Version\" src=\"https://img.shields.io/pypi/v/lightRAG?style=flat-square\">\n </a>\n <a href=\"https://star-history.com/#SylphAI-Inc/LightRAG\">\n <img alt=\"GitHub stars\" src=\"https://img.shields.io/github/stars/SylphAI-Inc/LightRAG?style=flat-square\">\n </a>\n <a href=\"https://github.com/SylphAI-Inc/LightRAG/issues\">\n <img alt=\"Open Issues\" src=\"https://img.shields.io/github/issues-raw/SylphAI-Inc/LightRAG?style=flat-square\">\n </a>\n <a href=\"https://opensource.org/license/MIT\">\n <img alt=\"License\" src=\"https://img.shields.io/github/license/SylphAI-Inc/LightRAG\">\n </a>\n <a href=\"https://discord.gg/ezzszrRZvT\">\n <img alt=\"discord-invite\" src=\"https://dcbadge.vercel.app/api/server/ezzszrRZvT?style=flat\">\n </a>\n</p>\n\n\n\n<!-- <a href=\"https://colab.research.google.com/drive/1PPxYEBa6eu__LquGoFFJZkhYgWVYE6kh?usp=sharing\">\n <img alt=\"Try Quickstart in Colab\" src=\"https://colab.research.google.com/assets/colab-badge.svg\">\n </a> -->\n\n<!-- <a href=\"https://pypistats.org/packages/lightrag\">\n<img alt=\"PyPI Downloads\" src=\"https://img.shields.io/pypi/dm/lightRAG?style=flat-square\">\n</a> -->\n\n\n\n<h1>\n <p align=\"center\">\n AdalFlow: The Library for Large Language Model Applications\n </p>\n</h1>\n\nAdalFlow helps developers build and optimize LLM task pipelines.\nEmbracing similar design pattern to PyTorch, AdalFlow is light, modular, and robust, with a 100% readable codebase.\n\nNote: We are in the progress of renaming to adalflow from lightrag.\n\n# AdalFlow: A Tribute to Ada Lovelace\n\nAdalFlow is named in honor of [Ada Lovelace](https://en.wikipedia.org/wiki/Ada_Lovelace), the pioneering female mathematician who first recognized that machines could do more than just calculations. As a female-led team, we aim to inspire more women to enter the AI field.\n\n# Why AdalFlow?\n\nLLMs are like water; they can be shaped into anything, from GenAI applications such as chatbots, translation, summarization, code generation, and autonomous agents to classical NLP tasks like text classification and named entity recognition. They interact with the world beyond the model\u2019s internal knowledge via retrievers, memory, and tools (function calls). Each use case is unique in its data, business logic, and user experience.\n\nBecause of this, no library can provide out-of-the-box solutions. Users must build towards their own use case. This requires the library to be modular, robust, and have a clean, readable codebase. The only code you should put into production is code you either 100% trust or are 100% clear about how to customize and iterate.\n\n<!-- This is what AdalFlow is: light, modular, and robust, with a 100% readable codebase. -->\n\n\nFurther reading: [How We Started](https://www.linkedin.com/posts/li-yin-ai_both-ai-research-and-engineering-use-pytorch-activity-7189366364694892544-Uk1U?utm_source=share&utm_medium=member_desktop),\n[Introduction](https://lightrag.sylph.ai/), [Design Philosophy](https://lightrag.sylph.ai/tutorials/lightrag_design_philosophy.html) and [Class hierarchy](https://lightrag.sylph.ai/tutorials/class_hierarchy.html).\n\n\n<!--\n\n**PyTorch**\n\n```python\nimport torch\nimport torch.nn as nn\n\nclass Net(nn.Module):\n def __init__(self):\n super(Net, self).__init__()\n self.conv1 = nn.Conv2d(1, 32, 3, 1)\n self.conv2 = nn.Conv2d(32, 64, 3, 1)\n self.dropout1 = nn.Dropout2d(0.25)\n self.dropout2 = nn.Dropout2d(0.5)\n self.fc1 = nn.Linear(9216, 128)\n self.fc2 = nn.Linear(128, 10)\n\n def forward(self, x):\n x = self.conv1(x)\n x = self.conv2(x)\n x = self.dropout1(x)\n x = self.dropout2(x)\n x = self.fc1(x)\n return self.fc2(x)\n``` -->\n# AdalFlow Task Pipeline\n\nWe will ask the model to respond with ``explanation`` and ``example`` of a concept. To achieve this, we will build a simple pipeline to get the structured output as ``QAOutput``.\n\n## Well-designed Base Classes\n\nThis leverages our two and only powerful base classes: `Component` as building blocks for the pipeline and `DataClass` to ease the data interaction with LLMs.\n\n```python\n\nfrom dataclasses import dataclass, field\n\nfrom lightrag.core import Component, Generator, DataClass\nfrom lightrag.components.model_client import GroqAPIClient\nfrom lightrag.components.output_parsers import JsonOutputParser\n\n@dataclass\nclass QAOutput(DataClass):\n explanation: str = field(\n metadata={\"desc\": \"A brief explanation of the concept in one sentence.\"}\n )\n example: str = field(metadata={\"desc\": \"An example of the concept in a sentence.\"})\n\n\n\nqa_template = r\"\"\"<SYS>\nYou are a helpful assistant.\n<OUTPUT_FORMAT>\n{{output_format_str}}\n</OUTPUT_FORMAT>\n</SYS>\nUser: {{input_str}}\nYou:\"\"\"\n\nclass QA(Component):\n def __init__(self):\n super().__init__()\n\n parser = JsonOutputParser(data_class=QAOutput, return_data_class=True)\n self.generator = Generator(\n model_client=GroqAPIClient(),\n model_kwargs={\"model\": \"llama3-8b-8192\"},\n template=qa_template,\n prompt_kwargs={\"output_format_str\": parser.format_instructions()},\n output_processors=parser,\n )\n\n def call(self, query: str):\n return self.generator.call({\"input_str\": query})\n\n async def acall(self, query: str):\n return await self.generator.acall({\"input_str\": query})\n```\n\n\nRun the following code for visualization and calling the model.\n\n```python\n\nqa = QA()\nprint(qa)\n\n# call\noutput = qa(\"What is LLM?\")\nprint(output)\n```\n\n## Clear Pipeline Structure\n\nSimply by using `print(qa)`, you can see the pipeline structure, which helps users understand any LLM workflow quickly.\n\n```\nQA(\n (generator): Generator(\n model_kwargs={'model': 'llama3-8b-8192'},\n (prompt): Prompt(\n template: <SYS>\n You are a helpful assistant.\n <OUTPUT_FORMAT>\n {{output_format_str}}\n </OUTPUT_FORMAT>\n </SYS>\n User: {{input_str}}\n You:, prompt_kwargs: {'output_format_str': 'Your output should be formatted as a standard JSON instance with the following schema:\\n```\\n{\\n \"explanation\": \"A brief explanation of the concept in one sentence. (str) (required)\",\\n \"example\": \"An example of the concept in a sentence. (str) (required)\"\\n}\\n```\\n-Make sure to always enclose the JSON output in triple backticks (```). Please do not add anything other than valid JSON output!\\n-Use double quotes for the keys and string values.\\n-Follow the JSON formatting conventions.'}, prompt_variables: ['output_format_str', 'input_str']\n )\n (model_client): GroqAPIClient()\n (output_processors): JsonOutputParser(\n data_class=QAOutput, examples=None, exclude_fields=None, return_data_class=True\n (json_output_format_prompt): Prompt(\n template: Your output should be formatted as a standard JSON instance with the following schema:\n ```\n {{schema}}\n ```\n {% if example %}\n Examples:\n ```\n {{example}}\n ```\n {% endif %}\n -Make sure to always enclose the JSON output in triple backticks (```). Please do not add anything other than valid JSON output!\n -Use double quotes for the keys and string values.\n -Follow the JSON formatting conventions., prompt_variables: ['schema', 'example']\n )\n (output_processors): JsonParser()\n )\n )\n)\n```\n\n**The Output**\n\nWe structure the output to both track the data and potential errors if any part of the Generator component fails.\nHere is what we get from ``print(output)``:\n\n```\nGeneratorOutput(data=QAOutput(explanation='LLM stands for Large Language Model, which refers to a type of artificial intelligence designed to process and generate human-like language.', example='For instance, LLMs are used in chatbots and virtual assistants, such as Siri and Alexa, to understand and respond to natural language input.'), error=None, usage=None, raw_response='```\\n{\\n \"explanation\": \"LLM stands for Large Language Model, which refers to a type of artificial intelligence designed to process and generate human-like language.\",\\n \"example\": \"For instance, LLMs are used in chatbots and virtual assistants, such as Siri and Alexa, to understand and respond to natural language input.\"\\n}', metadata=None)\n```\n**Focus on the Prompt**\n\nUse the following code will let us see the prompt after it is formatted:\n\n```python\n\nqa2.generator.print_prompt(\n output_format_str=qa2.generator.output_processors.format_instructions(),\n input_str=\"What is LLM?\",\n)\n```\n\n\nThe output will be:\n\n````markdown\n<SYS>\nYou are a helpful assistant.\n<OUTPUT_FORMAT>\nYour output should be formatted as a standard JSON instance with the following schema:\n```\n{\n \"explanation\": \"A brief explanation of the concept in one sentence. (str) (required)\",\n \"example\": \"An example of the concept in a sentence. (str) (required)\"\n}\n```\n-Make sure to always enclose the JSON output in triple backticks (```). Please do not add anything other than valid JSON output!\n-Use double quotes for the keys and string values.\n-Follow the JSON formatting conventions.\n</OUTPUT_FORMAT>\n</SYS>\nUser: What is LLM?\nYou:\n````\n\n## Model-agnostic\n\n\nYou can switch to any model simply by using a different `model_client` (provider) and `model_kwargs`.\nLet's use OpenAI's `gpt-3.5-turbo` model.\n\n```python\nfrom lightrag.components.model_client import OpenAIClient\n\nself.generator = Generator(\n model_client=OpenAIClient(),\n model_kwargs={\"model\": \"gpt-3.5-turbo\"},\n template=qa_template,\n prompt_kwargs={\"output_format_str\": parser.format_instructions()},\n output_processors=parser,\n)\n```\n\n\n# Quick Install\n\nInstall AdalFlow with pip:\n\n```bash\npip install lightrag\n```\n\nPlease refer to the [full installation guide](https://lightrag.sylph.ai/get_started/installation.html) for more details.\n\n\n\n\n# Documentation\n\nAdalFlow full documentation available at [lightrag.sylph.ai](https://lightrag.sylph.ai/):\n- [How We Started](https://www.linkedin.com/posts/li-yin-ai_both-ai-research-and-engineering-use-pytorch-activity-7189366364694892544-Uk1U?utm_source=share&utm_medium=member_desktop)\n- [Introduction](https://lightrag.sylph.ai/)\n- [Full installation guide](https://lightrag.sylph.ai/get_started/installation.html)\n- [Design philosophy](https://lightrag.sylph.ai/tutorials/lightrag_design_philosophy.html)\n- [Class hierarchy](https://lightrag.sylph.ai/tutorials/class_hierarchy.html)\n- [Tutorials](https://lightrag.sylph.ai/tutorials/index.html)\n- [Supported Models](https://lightrag.sylph.ai/apis/components/components.model_client.html)\n- [Supported Retrievers](https://lightrag.sylph.ai/apis/components/components.retriever.html)\n- [API reference](https://lightrag.sylph.ai/apis/index.html)\n\n\n\n\n# Contributors\n\n[](https://github.com/SylphAI-Inc/LightRAG/graphs/contributors)\n\n# Citation\n\n```bibtex\n@software{Yin2024AdalFlow,\n author = {Li Yin},\n title = {{AdalFlow: The Library for Large Language Model (LLM) Applications}},\n month = {7},\n year = {2024},\n doi = {10.5281/zenodo.12639531},\n url = {https://github.com/SylphAI-Inc/LightRAG}\n}\n```\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "The Lightning Library for LLM Applications.",
"version": "0.1.0b5",
"project_urls": {
"Homepage": "https://github.com/SylphAI-Inc/LightRAG",
"Repository": "https://github.com/SylphAI-Inc/LightRAG"
},
"split_keywords": [
"llm",
" nlp",
" rag",
" devtools",
" retrieval",
" agent"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "18845802f32bf6d46ff11affb85b8b1d4ea55d383a7a5e37ce17c897f78f6e29",
"md5": "28a26226b71e72131ea86d55762fb0d1",
"sha256": "717d2e79e6d3e9ee270875f9bbf828a745b0484d16d4dfaf337d942235871209"
},
"downloads": -1,
"filename": "lightrag-0.1.0b5-py3-none-any.whl",
"has_sig": false,
"md5_digest": "28a26226b71e72131ea86d55762fb0d1",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.9",
"size": 158891,
"upload_time": "2024-07-23T23:46:42",
"upload_time_iso_8601": "2024-07-23T23:46:42.259360Z",
"url": "https://files.pythonhosted.org/packages/18/84/5802f32bf6d46ff11affb85b8b1d4ea55d383a7a5e37ce17c897f78f6e29/lightrag-0.1.0b5-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "8742a7209315eb9627fa50a6b882c40530e4a543a2571a97a9382bffa66e9ed0",
"md5": "039555dafce5e201dc38efe6b891300f",
"sha256": "9e0e74c3f621e379e212cece1d34d733361dd61baa52d95d055756b4c6657216"
},
"downloads": -1,
"filename": "lightrag-0.1.0b5.tar.gz",
"has_sig": false,
"md5_digest": "039555dafce5e201dc38efe6b891300f",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.9",
"size": 126768,
"upload_time": "2024-07-23T23:46:44",
"upload_time_iso_8601": "2024-07-23T23:46:44.267366Z",
"url": "https://files.pythonhosted.org/packages/87/42/a7209315eb9627fa50a6b882c40530e4a543a2571a97a9382bffa66e9ed0/lightrag-0.1.0b5.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-07-23 23:46:44",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "SylphAI-Inc",
"github_project": "LightRAG",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "lightrag"
}
JSON
