> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2-studio-tools-doc.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.
# Overview
> Give agents access to documents, databases, and domain expertise.
**Knowledge** gives agents access to information beyond their training data. Load files, URLs, or raw text, and agents can search this knowledge to provide accurate, contextual responses.
```python theme={null}
from agno.agent import Agent
from agno.knowledge.knowledge import Knowledge
from agno.vectordb.chroma import ChromaDb
# Create a knowledge base
knowledge = Knowledge(
vector_db=ChromaDb(collection="docs", path="tmp/chromadb"),
)
# Load content
knowledge.insert(url="https://docs.agno.com/introduction.md")
# Create an agent that searches the knowledge base
agent = Agent(knowledge=knowledge, search_knowledge=True)
agent.print_response("What is Agno?")
```
The agent searches its knowledge base and grounds its response in the content.
## How It Works
Knowledge combines three components:
1. **Content ingestion**: Read documents from files, URLs, cloud storage, or raw text. Agno includes readers for PDF, DOCX, CSV, Markdown, and more.
2. **Chunking and embedding**: Documents are split into searchable chunks and converted to vector embeddings that capture semantic meaning.
3. **Search and retrieval**: When an agent needs information, it searches the vector database for relevant chunks and includes them in its context.
You can use **Agentic RAG** (agent decides when to search) or **Traditional RAG** (always inject context). Agentic RAG is the default and works well for most use cases.
## Why Knowledge Matters
Language models have broad general knowledge but lack context about your specific domain. Knowledge bridges this gap by providing relevant information at runtime.
**Start with your content.** Load company documentation, database schemas, product specs, support FAQs, or research papers. The agent uses this information to answer questions accurately instead of guessing.
**Then let agents learn.** Knowledge isn't read-only. Agents can save insights they discover and retrieve them later, building expertise across conversations.
```python theme={null}
def save_learning(title: str, insight: str) -> str:
"""Save a reusable insight to the knowledge base."""
knowledge.insert(name=title, text_content=insight)
return f"Saved: {title}"
agent = Agent(
knowledge=knowledge,
search_knowledge=True,
tools=[save_learning], # Agent can write to knowledge
)
```
This turns agents from static systems into systems that learn over time.
## Examples
Build an agent with knowledge in 5 minutes
Agentic RAG, traditional RAG, reranking
Distributed search, coordinated RAG
## Concepts
Store and search embeddings
Track knowledge contents
Vector, keyword, and hybrid search
Ingest from various sources
Control document splitting
Convert text to vectors
Filter results by metadata
## Vector Stores
Agno supports 20+ vector databases, from local options like LanceDB and ChromaDB to managed services like Pinecone and Weaviate.
See supported databases