Deep web research for Kapso campaigns and knowledge

from kapso import Kapso

kapso = Kapso()

# mode: "idea" | "implementation" | "study", or a list
#       (default: ["idea", "implementation"])
# depth: "light" | "deep" (default: "deep")

findings = kapso.research(
    "QLoRA fine-tuning best practices for LLaMA models",
    depth="deep",
)

# Access results
for idea in findings.ideas:
    print(idea.query)      # Original query
    print(idea.source)     # URL
    print(idea.content)    # Full content with sections
    print(idea.to_string())  # Formatted for LLM context

for impl in findings.implementations:
    print(impl.query)      # Original query
    print(impl.source)     # URL
    print(impl.content)    # Full content with code snippet
    print(impl.to_string())  # Formatted for LLM context

ideas = kapso.research("QLoRA fine-tuning best practices", mode="idea")

for idea in ideas:  # List[Source.Idea] — not findings.ideas
    print(idea.to_string())

from kapso import Kapso

kapso = Kapso()

# Research
findings = kapso.research(
    "unsloth FastLanguageModel example",
    depth="deep",
)

# Use research as context for evolve
solution = kapso.evolve(
    goal="Fine-tune a model with Unsloth + LoRA",
    context=[findings.to_string()],
    output_path="./models/unsloth_v1",
)

from kapso import Kapso

kapso = Kapso()

# Research
findings = kapso.research(
    "LoRA rank selection best practices",
    depth="deep",
)

# Ingest everything into the knowledge graph
kapso.learn_knowledge(findings, wiki_dir="data/wikis")