Skip to main content

do-cap-utils

A library to simplify your use case with chat bot with LLMs. Perfect for Common AI Platform.

Installation

uv add do-cap-utils

Usage

See example.py and example_multiagents.py.

General

from do_cap_utils.agent.base import BaseAgent
from do_cap_utils.agent.prebuilt import SummariserAgent
from do_cap_utils.tool import tool


# --------------------------------------------
# Create and run your own agent with some tool
# --------------------------------------------
@tool
def add_numbers(a: int, b: int):
    """Adds two numbers together"""
    return a + b


agent = BaseAgent(
    system_prompt="You are a helpful assistant that answers everything nicely (only that you can do or know)",
    tools=[add_numbers],
)
r = agent.chat_each_message("hello")
r = agent.chat_each_message("add two numbers for me")
r = agent.chat_each_message("2 and 4")
print(r)  # Inpect the output
print()

# You can use `chat_interact()` method to have an interactive session
agent.chat_interact()

Now, if you use self.chat_interact(), save the file and run this file in the command line.

uv run your_file.py

Or activate your python environment and run

python your_file.py

Example output:

================================ Human Message =================================

hello
================================== Ai Message ==================================

Hello! How can I assist you today?
================================ Human Message =================================

add two numbers for me
================================== Ai Message ==================================

Of course! Please provide the two numbers you'd like to add.
================================ Human Message =================================

2 and 4
================================== Ai Message ==================================
Tool Calls:
  add_numbers (call_kGDJ89gTwG6cTZFT7cWr1dBs)
 Call ID: call_kGDJ89gTwG6cTZFT7cWr1dBs
  Args:
    a: 2
    b: 4
================================= Tool Message =================================
Name: add_numbers

6
================================== Ai Message ==================================

The sum of 2 and 4 is 6.

Metadata

Release files for do-cap-utils 0.2.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for do-cap-utils 0.2.1
File Size Uploaded Provenance Actions
do_cap_utils-0.2.1.tar.gz 93.6 kB Without provenance Details for do_cap_utils-0.2.1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for do-cap-utils 0.2.1
File Interpreter ABI Platform Actions
do_cap_utils-0.2.1-py3-none-any.whl Python 3 none any Details for do_cap_utils-0.2.1-py3-none-any.whl

Total release size: 101.2 kB

Release files / do_cap_utils-0.2.1.tar.gz

Download URL do_cap_utils-0.2.1.tar.gz
Size 93.6 kB
Tags Source
SHA-256 checksum
How to use checksums
e9768609142d31939f6abdbc7f6ebd84e2acb36a4b01605b9521fc8a06224e58
BLAKE2b-256 checksum
How to use checksums
320a29d4f4e58ff5d8695bbee78f7f616f0988394ef33f3f34af9e8296efffd7
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.5.11

Release files / do_cap_utils-0.2.1-py3-none-any.whl

Download URL do_cap_utils-0.2.1-py3-none-any.whl
Size 7.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
1c3972ff67158c77bc6ef30ffa8677e3ce225d4c0908fa27e6e79eb4496b0833
BLAKE2b-256 checksum
How to use checksums
6eb2a594613bad4b63899dce2f32a9bc8fe37202eca80e90c48f2ab33a4884f4
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.5.11

Security for do-cap-utils 0.2.1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.2.1 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page