Skip to main content

Subscribe to events using a callback and store them in PlantUML format. You can easily subscribe to events and keep them in a form that is easy to visualize and analyze.

Project description

Visualization UML diagram tool for LangChain workflows

License PyPi version lint Build status

Subscribe to events using a callback and store them in PlantUML format to easily visualize LangChain workflow in Activity Diagram and Sequence Diagram. You can easily subscribe to events and keep them in a form that is easy to visualize and analyze using PlantUML.

Activity Diagram

Sequence Diagram

Quick Start

Install this library:

pip install langchain-plantuml

Then:

  1. Add import langchain_plantuml as the first import in your Python entrypoint file
  2. Create a callback using the activity_diagram_callback function
  3. Hook into your LLM application
  4. Call the export_uml_content method of activity_diagram_callback to export the PlantUML content
  5. Save PlantUML content to a file
  6. Exporting PlantUML to PNG

Running the minimal activity diagram example.

from langchain import OpenAI, LLMChain, PromptTemplate
from langchain.memory import ConversationBufferMemory

from langchain_plantuml import diagram

template = """You are a chatbot having a conversation with a human.

{chat_history}
Human: {human_input}
Chatbot:"""

prompt = PromptTemplate(
    input_variables=["chat_history", "human_input"], template=template
)
memory = ConversationBufferMemory(memory_key="chat_history")

activity_diagram = diagram.activity_diagram_callback(note_max_length=2000)
sequence_diagram = diagram.sequence_diagram_callback(note_max_length=2000)

llm_chain = LLMChain(
    llm=OpenAI(),
    prompt=prompt,
    verbose=True,
    memory=memory,
    callbacks=[activity_diagram, sequence_diagram]
)

try:
    llm_chain.predict(human_input="What did biden say about ketanji brown jackson in the state of the union address?")
finally:
    activity_diagram.save_uml_content("example_1_activity-plantuml.puml")
    sequence_diagram.save_uml_content("example_1_sequence-plantuml.puml")

You will get the following PlantUML activity diagram

Sequence Diagram

callback_handler = diagram.sequence_diagram_callback()

Custom note max Length(default 1000)

callback_handler = diagram.activity_diagram_callback(note_max_length=2000)

Custom note wrap width(default 500)

callback_handler = diagram.activity_diagram_callback(note_wrap_width=500)

Exporting PlantUML to PNG

You can download plantuml.1.2023.10.jar

java -DPLANTUML_LIMIT_SIZE=81920 -jar plantuml-1.2023.10.jar example-activity.puml

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

langchain_plantuml-0.0.8.tar.gz (11.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

langchain_plantuml-0.0.8-py3-none-any.whl (15.4 kB view details)

Uploaded Python 3

File details

Details for the file langchain_plantuml-0.0.8.tar.gz.

File metadata

  • Download URL: langchain_plantuml-0.0.8.tar.gz
  • Upload date:
  • Size: 11.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.9.21

File hashes

Hashes for langchain_plantuml-0.0.8.tar.gz
Algorithm Hash digest
SHA256 98922ce4a388aa09e7cc93ddce9440166c634e079254802a3afb93b38e89e818
MD5 dcf52863ddaf00303cb9cbd032f09c9b
BLAKE2b-256 337e3a6468b893c2529d2d0306da2cb1225a0957843257978b70b3e3b5564ade

See more details on using hashes here.

File details

Details for the file langchain_plantuml-0.0.8-py3-none-any.whl.

File metadata

File hashes

Hashes for langchain_plantuml-0.0.8-py3-none-any.whl
Algorithm Hash digest
SHA256 7f3aea08e9e9e996de0a4d2cf7b7610030d8e55d007ece1e6734a2d759a49ff9
MD5 6ebff1c85cda807e7aa2a530f5655418
BLAKE2b-256 2b1530a92fb375ce38ab7fcca4b9460f2b23a69f11b95eb8de454521298bdda0

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page