Semantic Splitter

uv pip install numpy

from upsonic import Agent, Task, KnowledgeBase
from upsonic.loaders.text import TextLoader
from upsonic.loaders.config import TextLoaderConfig
from upsonic.embeddings import OpenAIEmbedding, OpenAIEmbeddingConfig
from upsonic.text_splitter.semantic import SemanticChunker, SemanticChunkingConfig, BreakpointThresholdType
from upsonic.vectordb import ChromaProvider, ChromaConfig, ConnectionConfig, Mode

# Configure splitter with embedding provider
embedding = OpenAIEmbedding(OpenAIEmbeddingConfig())
splitter_config = SemanticChunkingConfig(
    chunk_size=512,
    chunk_overlap=50,
    embedding_provider=embedding,
    breakpoint_threshold_type=BreakpointThresholdType.PERCENTILE,
    breakpoint_threshold_amount=95.0
)
splitter = SemanticChunker(splitter_config)

# Setup KnowledgeBase
loader = TextLoader(TextLoaderConfig())
vectordb = ChromaProvider(ChromaConfig(
    collection_name="semantic_docs",
    vector_size=1536,
    connection=ConnectionConfig(mode=Mode.IN_MEMORY)
))

kb = KnowledgeBase(
    sources=["document.txt"],
    embedding_provider=embedding,
    vectordb=vectordb,
    loaders=[loader],
    splitters=[splitter]
)

# Query with Agent
agent = Agent("anthropic/claude-sonnet-4-5")
task = Task("Identify different topics", context=[kb])
result = agent.do(task)
print(result)