Skip to main content
Knowledge bases can be added to tasks to provide RAG (Retrieval-Augmented Generation) capabilities, allowing the agent to access and use external knowledge sources.

​
Basic Knowledge Base Integration

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

# Create embedding provider
embedding_provider = OpenAIEmbedding()

# Create ChromaDB config
chroma_config = ChromaConfig(
    collection_name="my_knowledge_base",
    vector_size=1536,  # OpenAI ada-002 embedding size
    connection=ConnectionConfig(mode=Mode.IN_MEMORY)  # or Mode.EMBEDDED with db_path
)

# Create vector database with config
vectordb = ChromaProvider(config=chroma_config)

# Create knowledge base
knowledge_base = KnowledgeBase(
    sources=["document1.pdf", "document2.txt"],
    embedding_provider=embedding_provider,
    vectordb=vectordb
)

# Task with knowledge base context
task = Task(
    description="Answer questions about the uploaded documents",
    context=[knowledge_base]
)

agent = Agent(model="openai/gpt-4o")

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

​
Multiple Knowledge Bases

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

# Create embedding provider and vector database
embedding_provider = OpenAIEmbedding()
chroma_config = ChromaConfig(
    collection_name="multi_kb",
    vector_size=1536,
    connection=ConnectionConfig(mode=Mode.IN_MEMORY)
)
vectordb = ChromaProvider(config=chroma_config)

# Create multiple knowledge bases
kb1 = KnowledgeBase(
    sources=["technical_docs/"],
    embedding_provider=embedding_provider,
    vectordb=vectordb,
    name="Technical Documentation"
)

kb2 = KnowledgeBase(
    sources=["company_policies.pdf"],
    embedding_provider=embedding_provider,
    vectordb=vectordb,
    name="Company Policies"
)

# Task with multiple knowledge bases
agent = Agent(model="openai/gpt-4o")
task = Task(
    description="Find information about both technical procedures and company policies",
    context=[kb1, kb2]
)

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

​
Knowledge Base with Direct Content

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

embedding_provider = OpenAIEmbedding()
chroma_config = ChromaConfig(collection_name="content_kb", vector_size=1536, connection=ConnectionConfig(mode=Mode.IN_MEMORY))
vectordb = ChromaProvider(config=chroma_config)

# Knowledge base with direct string content
knowledge_base = KnowledgeBase(
    sources=["This is important information about our product features and capabilities."],
    embedding_provider=embedding_provider,
    vectordb=vectordb
)

agent = Agent(model="openai/gpt-4o")
task = Task(
    description="What are the key features mentioned in the product information?",
    context=[knowledge_base]
)

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

​
Knowledge Base Configuration

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

embedding_provider = OpenAIEmbedding()
chroma_config = ChromaConfig(collection_name="advanced_kb", vector_size=1536, connection=ConnectionConfig(mode=Mode.IN_MEMORY))
vectordb = ChromaProvider(config=chroma_config)

# Advanced knowledge base configuration
knowledge_base = KnowledgeBase(
    sources=["data/"],
    embedding_provider=embedding_provider,
    vectordb=vectordb,
    name="Custom Knowledge Base",
    use_case="rag_retrieval",
    quality_preference="balanced",
    loader_config={"skip_empty_content": True},
    splitter_config={"chunk_overlap": 200}
)

agent = Agent(model="openai/gpt-4o")
task = Task(description="Search the knowledge base for relevant information", context=[knowledge_base])
result = agent.do(task)
print(result)

​
Vector Search Filters

Filter vector search results when using knowledge bases: 
from upsonic import Task, KnowledgeBase, Agent
from upsonic.embeddings import OpenAIEmbedding
from upsonic.vectordb import ChromaProvider, ChromaConfig, ConnectionConfig, Mode

embedding_provider = OpenAIEmbedding()
chroma_config = ChromaConfig(collection_name="filter_kb", vector_size=1536, connection=ConnectionConfig(mode=Mode.IN_MEMORY))
vectordb = ChromaProvider(config=chroma_config)

knowledge_base = KnowledgeBase(
    sources=["documents/"],
    embedding_provider=embedding_provider,
    vectordb=vectordb
)

agent = Agent(model="openai/gpt-4o")

# Task with search filter
task = Task(
    description="Find information about Q4 sales",
    context=[knowledge_base],
    vector_search_filter={"department": "sales", "year": 2024}
)

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

​
Supported Sources

Knowledge bases support various source types:
  • File Paths: Individual files (PDF, TXT, DOCX, etc.)
  • Directories: Recursive directory scanning
  • Direct Content: String content passed directly
  • Mixed Sources: Combination of files and content
from upsonic import KnowledgeBase, Task, Agent
from upsonic.embeddings import OpenAIEmbedding
from upsonic.vectordb import ChromaProvider, ChromaConfig, ConnectionConfig, Mode

embedding_provider = OpenAIEmbedding()
chroma_config = ChromaConfig(collection_name="mixed_kb", vector_size=1536, connection=ConnectionConfig(mode=Mode.IN_MEMORY))
vectordb = ChromaProvider(config=chroma_config)

# Mixed sources example
knowledge_base = KnowledgeBase(
    sources=[
        "documents/",  # Directory
        "important.pdf",  # Single file
        "Key insight: Our product is revolutionary"  # Direct content
    ],
    embedding_provider=embedding_provider,
    vectordb=vectordb
)

agent = Agent(model="openai/gpt-4o")
task = Task(description="What insights can you find in the knowledge base?", context=[knowledge_base])
result = agent.do(task)
print(result)

​
Best Practices

  • Source Organization: Organize your sources logically for better retrieval
  • Embedding Provider: Choose appropriate embedding providers for your use case
  • Vector Database: Select vector databases that match your scale requirements
  • Chunking Strategy: Configure chunking parameters based on your content type
  • Quality vs Speed: Balance quality_preference based on your performance needs
  • Naming: Use descriptive names for knowledge bases to avoid confusion