Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.upsonic.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Attributes

The KnowledgeBase system is configured through the KnowledgeBase class, which provides the following attributes:
AttributeTypeDefaultDescription
sourcesUnion[str, Path, List[Union[str, Path]]](required)File paths, directory paths, or string content to process
vectordbBaseVectorDBProvider(required)Vector database provider instance for storage
embedding_providerEmbeddingProvider | NoneNoneProvider for creating vector embeddings. Optional for providers that handle their own embeddings (e.g., SuperMemory)
splittersUnion[BaseChunker, List[BaseChunker]] | NoneNoneText chunking strategies (auto-detected if None)
loadersUnion[BaseLoader, List[BaseLoader]] | NoneNoneDocument loaders for different file types (auto-detected if None)
namestr | NoneNoneHuman-readable name for the knowledge base (auto-generated if None). Used to derive tool names when registered as a tool
descriptionstr | NoneNoneDescription of the knowledge base content. Shown to agents when the KB is used as a tool, helping them decide when to search it
topicsList[str] | NoneNoneList of topics covered by the knowledge base. Included in tool descriptions for better agent routing
use_casestr"rag_retrieval"Use case for chunking optimization
quality_preferencestr"balanced"Speed vs quality preference: "fast", "balanced", or "quality"
loader_configDict[str, Any] | NoneNoneConfiguration options specifically for loaders
splitter_configDict[str, Any] | NoneNoneConfiguration options specifically for splitters
isolate_searchboolTrueWhen True, search queries are scoped to only documents in this knowledge base. When False, searches across all documents in the vector database collection
storageStorage | NoneNoneOptional storage backend for persisting knowledge base state and metadata

​
Configuration Example

from upsonic import Agent, Task, KnowledgeBase
from upsonic.embeddings import OpenAIEmbedding, OpenAIEmbeddingConfig
from upsonic.vectordb import ChromaProvider, ChromaConfig, ConnectionConfig, Mode

# Setup embedding provider
embedding = OpenAIEmbedding(OpenAIEmbeddingConfig())

# Setup vector database
config = ChromaConfig(
    collection_name="my_kb",
    vector_size=1536,
    connection=ConnectionConfig(mode=Mode.EMBEDDED, db_path="./chroma_db")
)
vectordb = ChromaProvider(config)


# Create knowledge base with configuration
kb = KnowledgeBase(
    sources=["document.pdf", "data/"],
    embedding_provider=embedding,
    vectordb=vectordb,
    name="product_docs",
    description="Product documentation including specs, guides, and FAQs",
    topics=["product specs", "user guides", "troubleshooting"],
    use_case="rag_retrieval",
    quality_preference="balanced",
    loader_config={"chunk_size": 1000},
    splitter_config={"chunk_overlap": 200}
)

# Use with Agent
agent = Agent("anthropic/claude-sonnet-4-5")
task = Task(
    description="What are the main topics in the documents?",
    context=[kb]
)

result = agent.do(task)
print(result)

​
SuperMemory (No Embedding Provider)

When using SuperMemory as your vector database, you don’t need an embedding provider — SuperMemory handles embeddings internally: 
from upsonic import Agent, Task, KnowledgeBase
from upsonic.vectordb import SuperMemoryProvider, SuperMemoryConfig

# No embedding provider needed
vectordb = SuperMemoryProvider(SuperMemoryConfig(
    collection_name="my_kb",
    api_key="sm_your_api_key_here"
))

kb = KnowledgeBase(
    sources=["document.pdf"],
    vectordb=vectordb
)

agent = Agent("anthropic/claude-sonnet-4-5")
task = Task(
    description="What are the key points?",
    context=[kb]
)
result = agent.do(task)