PDF Knowledge Base - Phidata

The PDFKnowledgeBase reads local PDF files, converts them into vector embeddings and loads them to a vector databse.

Usage

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

pip install pypdf

knowledge_base.py

from phi.knowledge.pdf import PDFKnowledgeBase, PDFReader
from phi.vectordb.pgvector import PgVector

pdf_knowledge_base = PDFKnowledgeBase(
    path="data/pdfs",
    # Table name: ai.pdf_documents
    vector_db=PgVector(
        table_name="pdf_documents",
        db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
    ),
    reader=PDFReader(chunk=True),
)

Then use the knowledge_base with an Agent:

agent.py

from phi.agent import Agent
from knowledge_base import knowledge_base

agent = Agent(
    knowledge=knowledge_base,
    search_knowledge=True,
)
agent.knowledge.load(recreate=False)

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

Params

Parameter	Type	Default	Description
`path`	`Union[str, Path]`	-	Path to `PDF` files. Can point to a single PDF file or a directory of PDF files.
`vector_db`	`VectorDb`	-	Vector Database for the Knowledge Base. Example: `PgVector`
`reader`	`Union[PDFReader, PDFImageReader]`	`PDFReader()`	A `PDFReader` that converts the `PDFs` into `Documents` for the vector database.
`num_documents`	`int`	`5`	Number of documents to return on search.
`optimize_on`	`int`	-	Number of documents to optimize the vector db on. For Example: Create an index for `PgVector`.
`chunking_strategy`	`ChunkingStrategy`	`FixedSizeChunking`	The chunking strategy to use.