Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs-v1.agno.com/llms.txt

Use this file to discover all available pages before exploring further.

​
Setup

docker run -d \
  -e POSTGRES_DB=ai \
  -e POSTGRES_USER=ai \
  -e POSTGRES_PASSWORD=ai \
  -e PGDATA=/var/lib/postgresql/data/pgdata \
  -v pgvolume:/var/lib/postgresql/data \
  -p 5532:5432 \
  --name pgvector \
  agnohq/pgvector:16

​
Example

agent_with_knowledge.py
from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.knowledge.pdf_url import PDFUrlKnowledgeBase
from agno.vectordb.pgvector import PgVector, SearchType

db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"
knowledge_base = PDFUrlKnowledgeBase(
    urls=["https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"],
    vector_db=PgVector(table_name="recipes", db_url=db_url, search_type=SearchType.hybrid),
)
# Load the knowledge base: Comment out after first run
knowledge_base.load(recreate=True, upsert=True)

agent = Agent(
    model=OpenAIChat(id="gpt-4o"),
    knowledge=knowledge_base,
    # Add a tool to read chat history.
    read_chat_history=True,
    show_tool_calls=True,
    markdown=True,
    # debug_mode=True,
)
agent.print_response("How do I make chicken and galangal in coconut milk soup", stream=True)
agent.print_response("What was my last question?", stream=True)

Async Support ⚡

PgVector also supports asynchronous operations, enabling concurrency and leading to better performance.

async_pgvector.py
import asyncio

from agno.agent import Agent
from agno.knowledge.pdf_url import PDFUrlKnowledgeBase
from agno.vectordb.pgvector import PgVector

db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"

vector_db = PgVector(table_name="recipes", db_url=db_url)

knowledge_base = PDFUrlKnowledgeBase(
    urls=["https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"],
    vector_db=vector_db,
)

agent = Agent(knowledge=knowledge_base, show_tool_calls=True)

if __name__ == "__main__":
    # Comment out after first run
    asyncio.run(knowledge_base.aload(recreate=False))

    # Create and use the agent
    asyncio.run(agent.aprint_response("How to make Tom Kha Gai", markdown=True))
Use aload() and aprint_response() methods with asyncio.run() for non-blocking operations in high-throughput applications.

​
PgVector Params

ParameterTypeDefaultDescription
table_namestr-The name of the table to use.
schemastr-The schema to use.
db_urlstr-The database URL to connect to.
db_engineEngine-The database engine to use.
embedderEmbedder-The embedder to use.
search_typeSearchTypevectorThe search type to use.
vector_indexUnion[Ivfflat, HNSW]-The vector index to use.
distanceDistancecosineThe distance to use.
prefix_matchbool-Whether to use prefix matching.
vector_score_weightfloat0.5Weight for vector similarity in hybrid search. Must be between 0 and 1.
content_languagestr-The content language to use.
schema_versionint-The schema version to use.
auto_upgrade_schemabool-Whether to auto upgrade the schema.

​
Developer Resources