Filtering on SurrealDB

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.surrealdb import SurrealDb
from surrealdb import Surreal

# SurrealDB connection parameters
SURREALDB_URL = "ws://localhost:8000"
SURREALDB_USER = "root"
SURREALDB_PASSWORD = "root"
SURREALDB_NAMESPACE = "test"
SURREALDB_DATABASE = "test"

# Download all sample CVs and get their paths
downloaded_cv_paths = download_knowledge_filters_sample_data(
    num_files=5, file_extension=SampleDataFileExtension.PDF
)

# Create a client
client = Surreal(url=SURREALDB_URL)
client.signin({"username": SURREALDB_USER, "password": SURREALDB_PASSWORD})
client.use(namespace=SURREALDB_NAMESPACE, database=SURREALDB_DATABASE)

vector_db = SurrealDb(
    client=client,
    collection="recipes",  # Collection name for storing documents
    efc=150,  # HNSW construction time/accuracy trade-off
    m=12,  # HNSW max number of connections per element
    search_ef=40,  # HNSW search time/accuracy trade-off
)


# Step 1: Initialize knowledge base with documents and metadata
# ------------------------------------------------------------------------------
# When initializing the knowledge base, we can attach metadata that will be used for filtering
# This metadata can include user IDs, document types, dates, or any other attributes

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
# Initialize the Agent with the knowledge base and filters
agent = Agent(
    knowledge=knowledge_base,
    search_knowledge=True,
    debug_mode=True,
)

agent.print_response(
    "Tell me about Jordan Mitchell's experience and skills",
    knowledge_filters={"user_id": "jordan_mitchell"},
    markdown=True,
)