Skip to main content

​
Overview

KnowledgeBase provides advanced features for intelligent document processing, including automatic loader/splitter selection, indexed processing for multiple sources, and flexible content handling.

​
Intelligent Auto-Detection

When loaders and splitters are not provided, KnowledgeBase automatically detects and creates appropriate components for each source based on file type and content analysis. 
from upsonic import Agent, Task, KnowledgeBase
from upsonic.embeddings import OpenAIEmbedding, OpenAIEmbeddingConfig
from upsonic.vectordb import ChromaProvider, ChromaConfig, ConnectionConfig, Mode

embedding = OpenAIEmbedding(OpenAIEmbeddingConfig())
vectordb = ChromaProvider(ChromaConfig(
    collection_name="auto_kb",
    vector_size=1536,
    connection=ConnectionConfig(mode=Mode.IN_MEMORY)
))

# Auto-detects loaders and splitters for each source
kb = KnowledgeBase(
    sources=["document.pdf", "code.py", "data.json"],
    embedding_provider=embedding,
    vectordb=vectordb,
    use_case="rag_retrieval",
    quality_preference="balanced"
)

# Use with Agent
agent = Agent("openai/gpt-4o")
task = Task(
    description="What are the error handling mechanisms described in the code implementation?",
    context=[kb]
)

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

​
Indexed Processing

When multiple sources are provided with multiple loaders/splitters, KnowledgeBase uses indexed processing where each source is matched with its corresponding loader and splitter by index.

​
Single Loader/Splitter (Shared)

from upsonic import Agent, Task, KnowledgeBase
from upsonic.loaders.pdf import PdfLoader
from upsonic.loaders.config import PdfLoaderConfig
from upsonic.text_splitter.recursive import RecursiveChunker, RecursiveChunkingConfig
from upsonic.embeddings import OpenAIEmbedding, OpenAIEmbeddingConfig
from upsonic.vectordb import ChromaProvider, ChromaConfig, ConnectionConfig, Mode

# Setup dependencies
embedding = OpenAIEmbedding(OpenAIEmbeddingConfig())
vectordb = ChromaProvider(ChromaConfig(
    collection_name="my_kb",
    vector_size=1536,
    connection=ConnectionConfig(mode=Mode.EMBEDDED, db_path="./chroma_db")
))

loader = PdfLoader(PdfLoaderConfig())
splitter = RecursiveChunker(RecursiveChunkingConfig())

kb = KnowledgeBase(
    sources=["doc1.pdf", "doc2.pdf", "doc3.pdf"],
    embedding_provider=embedding,
    vectordb=vectordb,
    loaders=[loader],  # Single loader used for all sources
    splitters=[splitter]  # Single splitter used for all sources
)

# Use with Agent
agent = Agent("openai/gpt-4o")
task = Task(
    description="List the safety precautions mentioned in the operating manual",
    context=[kb]
)

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

​
Multiple Loaders/Splitters (Indexed)

from upsonic import Agent, Task, KnowledgeBase
from upsonic.loaders.pdf import PdfLoader
from upsonic.loaders.markdown import MarkdownLoader
from upsonic.loaders.config import PdfLoaderConfig, MarkdownLoaderConfig
from upsonic.text_splitter.recursive import RecursiveChunker, RecursiveChunkingConfig
from upsonic.text_splitter.semantic import SemanticChunker, SemanticChunkingConfig
from upsonic.embeddings import OpenAIEmbedding, OpenAIEmbeddingConfig
from upsonic.vectordb import ChromaProvider, ChromaConfig, ConnectionConfig, Mode

# Setup dependencies
embedding = OpenAIEmbedding(OpenAIEmbeddingConfig())
vectordb = ChromaProvider(ChromaConfig(
    collection_name="my_kb",
    vector_size=1536,
    connection=ConnectionConfig(mode=Mode.EMBEDDED, db_path="./chroma_db")
))

# Different loader for each source
loaders = [
    PdfLoader(PdfLoaderConfig()),
    MarkdownLoader(MarkdownLoaderConfig()),
    PdfLoader(PdfLoaderConfig())
]

# Different splitter for each source
splitters = [
    RecursiveChunker(RecursiveChunkingConfig(chunk_size=512)),
    SemanticChunker(SemanticChunkingConfig(embedding_provider=embedding)),
    RecursiveChunker(RecursiveChunkingConfig(chunk_size=1024))
]

kb = KnowledgeBase(
    sources=["doc1.pdf", "guide.md", "doc2.pdf"],
    embedding_provider=embedding,
    vectordb=vectordb,
    loaders=loaders,  # Index 0 -> doc1.pdf, Index 1 -> guide.md, Index 2 -> doc2.pdf
    splitters=splitters  # Index 0 -> doc1.pdf, Index 1 -> guide.md, Index 2 -> doc2.pdf
)

# Use with Agent
agent = Agent("openai/gpt-4o")
task = Task(
    description="What are the dependencies listed in the markdown file versus the build script?",
    context=[kb]
)

result = agent.do(task)
print(result)
Important: When using multiple loaders/splitters, the count must match the number of file sources (string content sources don’t need loaders).

​
Direct Content Support

KnowledgeBase can process direct string content without requiring loaders. String content is automatically detected and converted to documents. 
from upsonic import Agent, Task, KnowledgeBase
from upsonic.embeddings import OpenAIEmbedding, OpenAIEmbeddingConfig
from upsonic.vectordb import ChromaProvider, ChromaConfig, ConnectionConfig, Mode

# Setup dependencies
embedding = OpenAIEmbedding(OpenAIEmbeddingConfig())
vectordb = ChromaProvider(ChromaConfig(
    collection_name="my_kb",
    vector_size=1536,
    connection=ConnectionConfig(mode=Mode.EMBEDDED, db_path="./chroma_db")
))

kb = KnowledgeBase(
    sources=[
        "document.pdf",  # File path - needs loader
        "This is direct content that will be processed without a loader.",  # String - no loader needed
        "data/"  # Directory - files inside need loaders
    ],
    embedding_provider=embedding,
    vectordb=vectordb
)

# Use with Agent
agent = Agent("openai/gpt-4o")
task = Task(
    description="What is the specific error code mentioned in the log snippet?",
    context=[kb]
)

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

​
Quality Preferences

Control the speed vs quality trade-off for intelligent splitter selection:
  • "fast": Optimized for speed, may sacrifice some quality
  • "balanced": Good balance between speed and quality (default)
  • "quality": Optimized for quality, may be slower
from upsonic import Agent, Task, KnowledgeBase
from upsonic.embeddings import OpenAIEmbedding, OpenAIEmbeddingConfig
from upsonic.vectordb import ChromaProvider, ChromaConfig, ConnectionConfig, Mode

# Setup dependencies
embedding = OpenAIEmbedding(OpenAIEmbeddingConfig())
vectordb = ChromaProvider(ChromaConfig(
    collection_name="my_kb",
    vector_size=1536,
    connection=ConnectionConfig(mode=Mode.EMBEDDED, db_path="./chroma_db")
))

kb = KnowledgeBase(
    sources=["document.pdf"],
    embedding_provider=embedding,
    vectordb=vectordb,
    quality_preference="quality"  # Prioritize chunking quality
)

# Use with Agent
agent = Agent("openai/gpt-4o")
task = Task(
    description="Extract the exact definition of 'force majeure' from the contract",
    context=[kb]
)

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

​
Use Cases

Optimize chunking strategy for specific use cases:
  • "rag_retrieval": Optimized for RAG retrieval (default)
  • Other use cases may be added in future versions
from upsonic import Agent, Task, KnowledgeBase
from upsonic.embeddings import OpenAIEmbedding, OpenAIEmbeddingConfig
from upsonic.vectordb import ChromaProvider, ChromaConfig, ConnectionConfig, Mode

# Setup dependencies
embedding = OpenAIEmbedding(OpenAIEmbeddingConfig())
vectordb = ChromaProvider(ChromaConfig(
    collection_name="my_kb",
    vector_size=1536,
    connection=ConnectionConfig(mode=Mode.EMBEDDED, db_path="./chroma_db")
))

kb = KnowledgeBase(
    sources=["document.pdf"],
    embedding_provider=embedding,
    vectordb=vectordb,
    use_case="rag_retrieval"
)

# Use with Agent
agent = Agent("openai/gpt-4o")
task = Task(
    description="What are the specific prerequisites for the cloud deployment?",
    context=[kb]
)

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

​
Configuration Options

Pass configuration options to loaders and splitters via loader_config and splitter_config: 
from upsonic import Agent, Task, KnowledgeBase
from upsonic.embeddings import OpenAIEmbedding, OpenAIEmbeddingConfig
from upsonic.vectordb import ChromaProvider, ChromaConfig, ConnectionConfig, Mode

# Setup dependencies
embedding = OpenAIEmbedding(OpenAIEmbeddingConfig())
vectordb = ChromaProvider(ChromaConfig(
    collection_name="my_kb",
    vector_size=1536,
    connection=ConnectionConfig(mode=Mode.EMBEDDED, db_path="./chroma_db")
))

kb = KnowledgeBase(
    sources=["document.pdf"],
    embedding_provider=embedding,
    vectordb=vectordb,
    loader_config={"chunk_size": 1000},
    splitter_config={"chunk_overlap": 200, "chunk_size": 512}
)

# Use with Agent
agent = Agent("openai/gpt-4o")
task = Task(
    description="Find the detailed parameter description for the 'initialize' function",
    context=[kb]
)

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