KnowledgeConfig

Defined in the Feature Configs module.

AI Agent Configuration for RAG and knowledge retrieval. Consolidates: knowledge, retrieval_config, knowledge_config, rag_config, embedder_config

Properties

sources

List

No description available.

embedder

str

No description available.

embedder_config

Optional

No description available.

chunking_strategy

Union

No description available.

chunk_size

int

No description available.

chunk_overlap

int

No description available.

chunker

Optional

No description available.

retrieval_k

int

No description available.

retrieval_threshold

float

No description available.

rerank

bool

No description available.

rerank_model

Optional

No description available.

auto_retrieve

bool

No description available.

vector_store

Optional

No description available.

config

Optional

No description available.

Internal & Generic Methods

to_dict: Convert to dictionary.

Usage

# Simple enable with sources
    Agent(knowledge=["docs/", "data.pdf"])
    
    # With config
    Agent(knowledge=KnowledgeConfig(
        sources=["docs/"],
        embedder="openai",
        chunking_strategy="semantic",
        retrieval_k=5,
        rerank=True,
    ))
    
    # With chunker config
    Agent(knowledge={
        "sources": ["docs/"],
        "chunker": {
            "type": "semantic",
            "chunk_size": 512
        }
    })

Source

View on GitHub

praisonaiagents/config/feature_configs.py at line 208

Knowledge Concept

Knowledge Overview