HTML Loader

pip install "upsonic[loaders]"

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

# Configure loader
loader_config = HTMLLoaderConfig(
    extract_text=True,
    extract_tables=True,
    table_format="markdown",
    include_links=True
)
loader = HTMLLoader(loader_config)

# Setup KnowledgeBase
embedding = OpenAIEmbedding(OpenAIEmbeddingConfig())
chunker = RecursiveChunker(RecursiveChunkingConfig())
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=[chunker]
)

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