1 of 1

Storage

Agents use storage to persist sessions by storing them in a database.

Agents come with built-in memory, but it only lasts while the session is active. To continue conversations across sessions, we store agent sessions in a database like PostgreSQL.

The general syntax for adding storage to an Agent looks like:

Example

Run Postgres

Install docker desktop and run Postgres on port 5532 using:

Create an Agent with Storage

Create a file agent_with_storage.py with the following contents

Run the agent

Install libraries

MacWindows

Run the agent

Now the agent continues across sessions. Ask a question:

Then message bye to exit, start the app again and ask:

Start a new run

Run the agent_with_storage.py file with the --new flag to start a new run.

Params

Parameter

Type

Default

Description

Storage

Agents use storage to persist sessions by storing them in a database.

Agents come with built-in memory, but it only lasts while the session is active. To continue conversations across sessions, we store agent sessions in a database like PostgreSQL.

The general syntax for adding storage to an Agent looks like:

from bitca.agent import Agent
from bitca.model.openai import OpenAIChat
from bitca.tools.duckduckgo import DuckDuckGo
from bitca.storage.agent.postgres import PgAgentStorage

agent = Agent(
    model=OpenAIChat(id="gpt-4o"),
    storage=PgAgentStorage(table_name="agent_sessions", db_url="postgresql+psycopg://ai:ai@localhost:5532/ai"),
    tools=[DuckDuckGo()],
    show_tool_calls=True,
    add_history_to_messages=True,
)
agent.print_response("How many people live in Canada?")
agent.print_response("What is their national anthem called?")
agent.print_response("Which country are we speaking about?")

Example

Run Postgres

Install docker desktop and run Postgres on port 5532 using:

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 \
  bitca/pgvector:16

Create an Agent with Storage

Create a file agent_with_storage.py with the following contents

Run the agent

Install libraries

MacWindows

Run the agent

Now the agent continues across sessions. Ask a question:

Then message bye to exit, start the app again and ask:

Start a new run

Run the agent_with_storage.py file with the --new flag to start a new run.

Params

Parameter

Type

Default

Description

from bitca.agent import Agent
from bitca.model.openai import OpenAIChat
from bitca.tools.duckduckgo import DuckDuckGo
from bitca.storage.agent.postgres import PgAgentStorage

agent = Agent(
    model=OpenAIChat(id="gpt-4o"),
    storage=PgAgentStorage(table_name="agent_sessions", db_url="postgresql+psycopg://ai:ai@localhost:5532/ai"),
    tools=[DuckDuckGo()],
    show_tool_calls=True,
    add_history_to_messages=True,
)
agent.print_response("How many people live in Canada?")
agent.print_response("What is their national anthem called?")
agent.print_response("Which country are we speaking about?")

import typer
from typing import Optional, List
from bitca.agent import Agent
from bitca.storage.agent.postgres import PgAgentStorage
from bitca.knowledge.pdf import PDFUrlKnowledgeBase
from bitca.vectordb.pgvector import PgVector, SearchType

db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"
knowledge_base = PDFUrlKnowledgeBase(
    urls=["https://bitca-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 after first run
knowledge_base.load(upsert=True)
storage = PgAgentStorage(table_name="pdf_agent", db_url=db_url)

def pdf_agent(new: bool = False, user: str = "user"):
    session_id: Optional[str] = None

    if not new:
        existing_sessions: List[str] = storage.get_all_session_ids(user)
        if len(existing_sessions) > 0:
            session_id = existing_sessions[0]

    agent = Agent(
        session_id=session_id,
        user_id=user,
        knowledge=knowledge_base,
        storage=storage,
        # Show tool calls in the response
        show_tool_calls=True,
        # Enable the agent to read the chat history
        read_chat_history=True,
        # We can also automatically add the chat history to the messages sent to the model
        # But giving the model the chat history is not always useful, so we give it a tool instead
        # to only use when needed.
        # add_history_to_messages=True,
        # Number of historical responses to add to the messages.
        # num_history_responses=3,
    )
    if session_id is None:
        session_id = agent.session_id
        print(f"Started Session: {session_id}\n")
    else:
        print(f"Continuing Session: {session_id}\n")

    # Runs the agent as a cli app
    agent.cli_app(markdown=True)


if __name__ == "__main__":
    typer.run(pdf_agent)

import typer
from typing import Optional, List
from bitca.agent import Agent
from bitca.storage.agent.postgres import PgAgentStorage
from bitca.knowledge.pdf import PDFUrlKnowledgeBase
from bitca.vectordb.pgvector import PgVector, SearchType

db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"
knowledge_base = PDFUrlKnowledgeBase(
    urls=["https://bitca-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 after first run
knowledge_base.load(upsert=True)
storage = PgAgentStorage(table_name="pdf_agent", db_url=db_url)

def pdf_agent(new: bool = False, user: str = "user"):
    session_id: Optional[str] = None

    if not new:
        existing_sessions: List[str] = storage.get_all_session_ids(user)
        if len(existing_sessions) > 0:
            session_id = existing_sessions[0]

    agent = Agent(
        session_id=session_id,
        user_id=user,
        knowledge=knowledge_base,
        storage=storage,
        # Show tool calls in the response
        show_tool_calls=True,
        # Enable the agent to read the chat history
        read_chat_history=True,
        # We can also automatically add the chat history to the messages sent to the model
        # But giving the model the chat history is not always useful, so we give it a tool instead
        # to only use when needed.
        # add_history_to_messages=True,
        # Number of historical responses to add to the messages.
        # num_history_responses=3,
    )
    if session_id is None:
        session_id = agent.session_id
        print(f"Started Session: {session_id}\n")
    else:
        print(f"Continuing Session: {session_id}\n")

    # Runs the agent as a cli app
    agent.cli_app(markdown=True)


if __name__ == "__main__":
    typer.run(pdf_agent)