Learn how to filter knowledge base searches using Pdf documents with user-specific metadata.
from agno.agent import Agent
from agno.knowledge.pdf import PDFKnowledgeBase
from agno.utils.media import (
SampleDataFileExtension,
download_knowledge_filters_sample_data,
)
from agno.vectordb.lancedb import LanceDb
# Download all sample CVs and get their paths
downloaded_cv_paths = download_knowledge_filters_sample_data(
num_files=5, file_extension=SampleDataFileExtension.PDF
)
# Initialize LanceDB
# By default, it stores data in /tmp/lancedb
vector_db = LanceDb(
table_name="recipes",
uri="tmp/lancedb", # You can change this path to store data elsewhere
)
# Step 1: Initialize knowledge base with documents and metadata
knowledge_base = PDFKnowledgeBase(
path=[
{
"path": downloaded_cv_paths[0],
"metadata": {
"user_id": "jordan_mitchell",
"document_type": "cv",
"year": 2025,
},
},
{
"path": downloaded_cv_paths[1],
"metadata": {
"user_id": "taylor_brooks",
"document_type": "cv",
"year": 2025,
},
},
{
"path": downloaded_cv_paths[2],
"metadata": {
"user_id": "morgan_lee",
"document_type": "cv",
"year": 2025,
},
},
{
"path": downloaded_cv_paths[3],
"metadata": {
"user_id": "casey_jordan",
"document_type": "cv",
"year": 2025,
},
},
{
"path": downloaded_cv_paths[4],
"metadata": {
"user_id": "alex_rivera",
"document_type": "cv",
"year": 2025,
},
},
],
vector_db=vector_db,
)
# Load all documents into the vector database
knowledge_base.load(recreate=True)
# Step 2: Query the knowledge base with different filter combinations
# Option 1: Filters on the Agent
agent = Agent(
knowledge=knowledge_base,
search_knowledge=True,
)
agent.print_response(
"Tell me about Jordan Mitchell's experience and skills",
knowledge_filters={"user_id": "jordan_mitchell"},
markdown=True,
)
Install libraries
pip install -U agno openai lancedb
Run the example
python cookbook/agent_concepts/knowledge/filters/pdf/filtering.py
Was this page helpful?
Learn how to filter knowledge base searches using Pdf documents with user-specific metadata.
from agno.agent import Agent
from agno.knowledge.pdf import PDFKnowledgeBase
from agno.utils.media import (
SampleDataFileExtension,
download_knowledge_filters_sample_data,
)
from agno.vectordb.lancedb import LanceDb
# Download all sample CVs and get their paths
downloaded_cv_paths = download_knowledge_filters_sample_data(
num_files=5, file_extension=SampleDataFileExtension.PDF
)
# Initialize LanceDB
# By default, it stores data in /tmp/lancedb
vector_db = LanceDb(
table_name="recipes",
uri="tmp/lancedb", # You can change this path to store data elsewhere
)
# Step 1: Initialize knowledge base with documents and metadata
knowledge_base = PDFKnowledgeBase(
path=[
{
"path": downloaded_cv_paths[0],
"metadata": {
"user_id": "jordan_mitchell",
"document_type": "cv",
"year": 2025,
},
},
{
"path": downloaded_cv_paths[1],
"metadata": {
"user_id": "taylor_brooks",
"document_type": "cv",
"year": 2025,
},
},
{
"path": downloaded_cv_paths[2],
"metadata": {
"user_id": "morgan_lee",
"document_type": "cv",
"year": 2025,
},
},
{
"path": downloaded_cv_paths[3],
"metadata": {
"user_id": "casey_jordan",
"document_type": "cv",
"year": 2025,
},
},
{
"path": downloaded_cv_paths[4],
"metadata": {
"user_id": "alex_rivera",
"document_type": "cv",
"year": 2025,
},
},
],
vector_db=vector_db,
)
# Load all documents into the vector database
knowledge_base.load(recreate=True)
# Step 2: Query the knowledge base with different filter combinations
# Option 1: Filters on the Agent
agent = Agent(
knowledge=knowledge_base,
search_knowledge=True,
)
agent.print_response(
"Tell me about Jordan Mitchell's experience and skills",
knowledge_filters={"user_id": "jordan_mitchell"},
markdown=True,
)
Install libraries
pip install -U agno openai lancedb
Run the example
python cookbook/agent_concepts/knowledge/filters/pdf/filtering.py
Was this page helpful?