from upsonic import Agent, Task, KnowledgeBase
from upsonic.loaders import MarkdownLoader, MarkdownLoaderConfig
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 = MarkdownLoaderConfig(
parse_front_matter=True,
include_code_blocks=True,
split_by_heading="h2"
)
loader = MarkdownLoader(loader_config)
# Setup KnowledgeBase
embedding = OpenAIEmbedding(OpenAIEmbeddingConfig())
chunker = RecursiveChunker(RecursiveChunkingConfig())
vectordb = ChromaProvider(ChromaConfig(
collection_name="markdown_docs",
vector_size=1536,
connection=ConnectionConfig(mode=Mode.IN_MEMORY)
))
kb = KnowledgeBase(
sources=["document.md"],
embedding_provider=embedding,
vectordb=vectordb,
loaders=[loader],
splitters=[chunker]
)
# Query with Agent
agent = Agent("openai/gpt-4o")
task = Task("Extract all code examples", context=[kb])
result = agent.do(task)
print(result)
