> ## Documentation Index
> Fetch the complete documentation index at: https://docs-v1.agno.com/llms.txt
> Use this file to discover all available pages before exploring further.

# LightRAG Knowledge Base

> Learn how to use LightRAG, a fast graph-based retrieval-augmented generation system for enhanced knowledge querying.

The **LightRAGKnowledgeBase** integrates with a [LightRAG Server](https://github.com/HKUDS/LightRAG), a simple and fast retrieval-augmented generation system that uses graph structures to enhance document retrieval and knowledge querying capabilities.

## Usage

```python knowledge_base.py theme={null}
import asyncio

from agno.agent import Agent
from agno.knowledge.light_rag import LightRagKnowledgeBase, lightrag_retriever
from agno.models.anthropic import Claude

# Create a knowledge base, loaded with documents from a URL
knowledge_base = LightRagKnowledgeBase(
    lightrag_server_url="http://localhost:9621",
    path="tmp/",  # Load documents from a local directory
    urls=["https://docs-v1.agno.com/introduction/agents.md"],  # Load documents from a URL
)

# Load the knowledge base with the documents from the local directory and the URL
asyncio.run(knowledge_base.load())

# Load the knowledge base with the text
asyncio.run(
    knowledge_base.load_text(text="Agno is the best framework for building Agents")
)

```

Then use the `lightrag_knowledge_base` with an Agent:

```python agent.py theme={null}
# Create an agent with the knowledge base and the retriever
agent = Agent(
    model=Claude(id="claude-3-7-sonnet-latest"),
    # Agentic RAG is enabled by default when `knowledge` is provided to the Agent.
    knowledge=knowledge_base,
    retriever=lightrag_retriever,
    # search_knowledge=True gives the Agent the ability to search on demand
    # search_knowledge is True by default
    search_knowledge=True,
    instructions=[
        "Include sources in your response.",
        "Always search your knowledge before answering the question.",
        "Use the async_search method to search the knowledge base.",
    ],
    markdown=True,
)

asyncio.run(agent.aprint_response("What are Agno Agents?"))
```

## Params

| Parameter             | Type               | Default | Description                                                          |
| --------------------- | ------------------ | ------- | -------------------------------------------------------------------- |
| `lightrag_server_url` | `str`              | -       | URL to LightRAG server.                                              |
| `path`                | `Union[str, Path]` | -       | Path to documents. Can point to a single file or directory of files. |
| `url`                 | `str`              | -       | URLs of the website to read.                                         |

## Developer Resources

* View [Cookbook](https://github.com/agno-agi/agno/blob/main/cookbook/agent_concepts/agentic_search/lightrag)