Skip to main content
Control how agents retrieve and inject knowledge through the knowledge parameter — one surface for sources, chunking, reranking, and retrieval policy. 
from praisonaiagents import Agent

agent = Agent(
    name="Research Agent",
    instructions="Answer questions based on the provided documents.",
    knowledge={
        "sources": ["docs/", "papers.pdf"],
        "retrieval_k": 5,
        "rerank": True,
    },
)
response = agent.start("What are the key findings?")
The user asks a question; the agent retrieves relevant chunks from configured knowledge sources before answering.

​
Quick Start

1

Simple Usage

from praisonaiagents import Agent

agent = Agent(
    name="Research Agent",
    instructions="Answer questions based on the provided documents.",
    knowledge={
        "sources": ["docs/"],
        "retrieval_k": 5,
        "rerank": True,
    },
)
response = agent.start("What are the key findings?")
2

With Configuration

from praisonaiagents import Agent, KnowledgeConfig

agent = Agent(
    name="Agent",
    instructions="You are a helpful assistant.",
    knowledge=KnowledgeConfig(
        sources=["documents/"],
        embedder="openai",
        chunking_strategy="semantic",
        chunk_size=1000,
        chunk_overlap=200,
        retrieval_k=5,
        retrieval_threshold=0.3,
        rerank=True,
        auto_retrieve=True,
        vector_store={"provider": "chroma", "collection_name": "default"},
    ),
)

​
How It Works

The user asks a question; the agent embeds the query, retrieves the top-k chunks, then generates an answer with citations.

​
Configuration Options

OptionTypeDefaultDescription
sourcesList[str][]Files, directories, or URLs to index
embedderstr"openai"Embedding provider
chunking_strategystr"semantic"Chunking method
chunk_sizeint1000Target chunk size in tokens
chunk_overlapint200Overlap between chunks
retrieval_kint5Number of chunks to retrieve
retrieval_thresholdfloat0.0Minimum relevance score (0.0–1.0)
rerankboolFalseEnable reranking
rerank_modelstrNoneCustom rerank model
auto_retrieveboolTrueInject context automatically
vector_storedictNoneVector store provider config

​
Agent Methods

​
agent.start() / agent.chat()

Conversation with automatic retrieval when auto_retrieve=True: 
response = agent.start("What is the main topic?")
response = agent.start("Hello", force_retrieval=True)
response = agent.start("What is 2+2?", skip_retrieval=True)

​
agent.query()

Structured answer with citations: 
result = agent.query("What are the main findings?")
print(result.answer)
for citation in result.citations:
    print(f"[{citation.id}] {citation.source} (score: {citation.score:.2f})")

​
agent.retrieve()

Retrieval only — no LLM generation: 
context_pack = agent.retrieve("What are the key points?")
print(f"Found {len(context_pack.citations)} sources")

​
Multi-Agent Shared Knowledge

from praisonaiagents import Agent, Knowledge

shared = Knowledge(config={"vector_store": {"provider": "chroma", "config": {"collection_name": "shared_docs"}}})
shared.add("company_docs/")

analyst = Agent(
    name="Analyst",
    instructions="Analyse data from documents.",
    knowledge={"sources": shared, "retrieval_k": 10},
)

summariser = Agent(
    name="Summariser",
    instructions="Summarise key points.",
    knowledge={"sources": shared, "retrieval_k": 5},
)

​
Best Practices

Use retrieval_threshold=0.3 or higher when low-scoring chunks pollute answers.
For large bases, set retrieval_k=20 with rerank=True — cast a wide net, then keep the best chunks.
Arithmetic, greetings, and meta questions do not need retrieval — pass skip_retrieval=True.
Create one Knowledge instance and pass it as sources to multiple agents to avoid re-indexing.

Retrieval Strategies

Auto-select strategy by corpus size

CLI Retrieval

Run retrieval from the command line