This client library allows you to interact with Phantasm's receiver server from your Python codebase. It provides a simple and easy-to-use interface complete with type hints and documentation. Here's a quick example to get you started adding an approval workflow to your function:
from phantasmpy import Phantasm
phantasm = Phantasm()
# Replace with your own function.
@phantasm.require_approval()
def schedule_meeting(...):
pass
schedule_meeting(...)
Advanced Usage With LangChain
In real-world applications, you may want to use Phantasm with LangChain to utilize the full power of LangChain's features. For the sake of simplicity, we will be using OpenAI's GPT model as our language model. Here's how you can build a tool-powered AI agent with human-in-the-loop capabilities:
Requirements:
pip install langchain langchain-openai phantasmpy
import os
from langchain_core.tools import tool
from langchain_core.messages import AIMessage
from langchain_openai import ChatOpenAI
from phantasmpy import Phantasm
os.environ["OPENAI_API_KEY"] = "xxx"
llm = ChatOpenAI(model="gpt-4o-mini")
@tool
def publish_blog(topic: str):
# Add code to draft and publish the blog post.
print(f"A blog post ({topic}) is published.")
@tool
def send_email(to: str, subject: str, body: str):
# Add code to send an email using an email API.
print(f"An email is sent to {to}.")
tools = [publish_blog, send_email]
llm_with_tools = llm.bind_tools(tools)
phantasm = Phantasm()
def call_tools(message: AIMessage):
tool_map = {tool.name: tool for tool in tools}
for tool_call in message.tool_calls:
name, args = tool_call["name"], tool_call["args"]
response = phantasm.get_approval(name=name, parameters=args)
if response.approved:
tool_map[name].invoke(response.parameters)
else:
print(f"Tool call {name} is rejected.")
chain = llm_with_tools | call_tools
chain.invoke("Remind elon@x.com about the Monday meeting at 9AM")
Metadata
Release files for phantasmpy 0.1.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| phantasmpy-0.1.3.tar.gz | 5.8 kB | Without provenance | Details for phantasmpy-0.1.3.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| phantasmpy-0.1.3-py3-none-any.whl | Python 3 | none | any | Details for phantasmpy-0.1.3-py3-none-any.whl |
Total release size: 13.4 kB
Release files / phantasmpy-0.1.3.tar.gz
| Download URL | phantasmpy-0.1.3.tar.gz |
|---|---|
| Size | 5.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
0d7c0fde0270931fba482e416c8fe9244276c0b2e49a17bc7cc9b6cc116515cd
|
|
BLAKE2b-256 checksum How to use checksums |
f2de9c85fd75c9fbdcb2275c3a7a9440688c589cba083f8ed20514e0c0980dda
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.8.4 CPython/3.12.7 Linux/6.5.0-1025-azure
|
Release files / phantasmpy-0.1.3-py3-none-any.whl
| Download URL | phantasmpy-0.1.3-py3-none-any.whl |
|---|---|
| Size | 7.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
571403d8f5cf366ad408a45fd63acfaa7896864352ec09fdf163b20adf45c923
|
|
BLAKE2b-256 checksum How to use checksums |
e755de0890668d07a4ac86d1806f63af65dcbfadd3387fe3fbb0e28112586975
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.8.4 CPython/3.12.7 Linux/6.5.0-1025-azure
|
Security for phantasmpy 0.1.3
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.