HTML Splitter

pip install beautifulsoup4 lxml

from upsonic import Agent, Task, KnowledgeBase
from upsonic.loaders import HTMLLoader, HTMLLoaderConfig
from upsonic.embeddings import OpenAIEmbedding, OpenAIEmbeddingConfig
from upsonic.text_splitter import HTMLChunker, HTMLChunkingConfig
from upsonic.vectordb import ChromaProvider, ChromaConfig, ConnectionConfig, Mode

# Configure splitter
splitter_config = HTMLChunkingConfig(
    chunk_size=512,
    chunk_overlap=50,
    split_on_tags=["h1", "h2", "h3", "p"],
    preserve_whole_tags=["table", "pre"]
)
splitter = HTMLChunker(splitter_config)

# Setup KnowledgeBase
loader = HTMLLoader(HTMLLoaderConfig())
embedding = OpenAIEmbedding(OpenAIEmbeddingConfig())
vectordb = ChromaProvider(ChromaConfig(
    collection_name="html_docs",
    vector_size=1536,
    connection=ConnectionConfig(mode=Mode.IN_MEMORY)
))

kb = KnowledgeBase(
    sources=["https://example.com/article"],
    embedding_provider=embedding,
    vectordb=vectordb,
    loaders=[loader],
    splitters=[splitter]
)

# Query with Agent
agent = Agent("openai/gpt-4o")
task = Task("Extract main content", context=[kb])
result = agent.do(task)
print(result)