The CombinedKnowledgeBase combines multiple knowledge bases into 1 and is used when your app needs information using multiple sources.

​
Usage

We are using a local PgVector database for this example. Make sure it’s running

knowledge_base.py
from phi.knowledge.combined import CombinedKnowledgeBase
from phi.vectordb.pgvector import PgVector2

knowledge_base = CombinedKnowledgeBase(
    sources=[
        url_pdf_knowledge_base,
        website_knowledge_base,
        local_pdf_knowledge_base,
    ],
    vector_db=PgVector2(
        # Table name: ai.combined_documents
        collection="combined_documents",
        db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
    ),
)

Then use the knowledge_base with an Assistant:

assistant.py
from phi.assistant import Assistant
from knowledge_base import knowledge_base

assistant = Assistant(
    knowledge_base=knowledge_base,
    add_references_to_prompt=True,
)
assistant.knowledge_base.load(recreate=False)

assistant.print_response("Ask me about something from the knowledge base")

​
Params

sources
List[KnowledgeBase]

List of knowledge bases.

vector_db
VectorDb

Vector Database for the Knowledge Base.

num_documents
int

Number of documents to return on search. (default: 5)

optimize_on
int

Number of documents to optimize the vector db on.

Was this page helpful?

ArXivLangChain