Overview

The Knowledge System provides domain-specific guidance during problem-solving. It helps the agent recommend proven approaches and avoid common pitfalls by learning from repositories, research, and past experiments.

Key Concepts

Knowledge Graph (KG)

The KG stores domain knowledge in a structured format:

Vector Storage: Weaviate for semantic embeddings and similarity search
Graph Storage: Neo4j for relationships and graph traversal
Content: Wiki pages with overviews, detailed content, and connections

Learning Pipeline

A two-stage process for acquiring knowledge from sources:

Stage 1 (Ingestors): Extract structured wiki pages from sources
Stage 2 (Merger): Hierarchical sub-graph-aware merge into the existing KG

Knowledge Search

Hybrid retrieval that combines multiple approaches:

Semantic search: Vector similarity in Weaviate
Graph traversal: Connected pages from Neo4j
LLM reranking: Relevance scoring for better results

Using Knowledge in Kapso

Option 1: Pre-indexed KG

from kapso.kapso import Kapso

# One-time: Index wiki pages
kapso = Kapso()
kapso.index_kg(
    wiki_dir="data/wikis_llm_finetuning",
    save_to="data/indexes/llm_finetuning.index",
)

# Every time: Load existing index
kapso = Kapso(kg_index="data/indexes/llm_finetuning.index")
solution = kapso.evolve(goal="Fine-tune LLaMA with QLoRA")

Option 2: Learn from Sources

from kapso.kapso import Kapso, Source

kapso = Kapso()

# Learn from a repository
kapso.learn(
    Source.Repo("https://github.com/huggingface/transformers"),
    wiki_dir="data/wikis",
)

# Learn from web research
findings = kapso.research("QLoRA best practices", mode="idea")
kapso.learn(*findings.ideas, wiki_dir="data/wikis")

Option 3: Research as Context

from kapso.kapso import Kapso

kapso = Kapso()

# Research without persisting to KG
findings = kapso.research(
    "unsloth FastLanguageModel example",
    mode="implementation",
    depth="deep",
)

# Use research as context
solution = kapso.evolve(
    goal="Fine-tune with Unsloth + LoRA",
    context=[findings.to_string()],
)

Search Backends

Backend	Data Format	Storage	Use Case
`kg_graph_search`	Wiki pages (.md)	Weaviate + Neo4j	Semantic search with reranking
`kg_llm_navigation`	JSON (nodes/edges)	Neo4j only	LLM-guided graph navigation

Infrastructure Requirements

Both backends require database infrastructure:

# Start Weaviate and Neo4j
./scripts/start_infra.sh

# Stop infrastructure
./scripts/stop_infra.sh

Next Steps

Learning Pipeline

How knowledge is extracted and merged

Search Backends

Hybrid search implementation

Configuration

YAML config for knowledge search

Research

Web research for knowledge acquisition

Getting Started

Evolve System

Knowledge System & Learning

Research

Deployment

Benchmarks

Overview

Overview

Key Concepts

Knowledge Graph (KG)

Learning Pipeline

Knowledge Search

Using Knowledge in Kapso

Option 1: Pre-indexed KG

Option 2: Learn from Sources

Option 3: Research as Context

Search Backends

Infrastructure Requirements

Next Steps

Learning Pipeline

Search Backends

Configuration

Research

​Overview

​Key Concepts

​Knowledge Graph (KG)

​Learning Pipeline

​Knowledge Search

​Using Knowledge in Kapso

​Option 1: Pre-indexed KG

​Option 2: Learn from Sources

​Option 3: Research as Context

​Search Backends

​Infrastructure Requirements

​Next Steps

Learning Pipeline

Search Backends

Configuration

Research

Overview

Key Concepts

Knowledge Graph (KG)

Learning Pipeline

Knowledge Search

Using Knowledge in Kapso

Option 1: Pre-indexed KG

Option 2: Learn from Sources

Option 3: Research as Context

Search Backends

Infrastructure Requirements

Next Steps