Quickstart¶

In this tutorial you will learn how to use pycelonis_llm, a client library that allows you to seamlessly integrate LLMs offered by Celonis with your ML Workbench code.

⚠️ Warning: pycelonis_llm is currently still in beta. If you are interested in getting early access please create a ticket with customer support including a description of your use case.

With pycelonis_llm you can implement a wide variety of LLM use cases such as:

• Extracting information from free-text fields
• Summarizing documents
• Sentiment analysis
• Retrieval-augmented generation (RAG)
• Translation
• ...

You will learn in more detail how to use the following common LLM libraries with the LLMs provided by Celonis:

• LiteLLM
• LangChain
• LlamaIndex

Prerequisites¶

• You need to install pycelonis_llm to execute the tutorial code.
• An LLM needs to be assigned to your workbench (can be done in creation/edit dialog of your ML Workbench).

Tutorial¶

First, you need to import pycelonis_llm which will automatically patch the supported LLM libraries to be compatible with Celonis offered LLMs:

In [1]:

import pycelonis_llm

import pycelonis_llm

1. LiteLLM¶

LiteLLM is a Python library that simplifies the process of integrating various LLM APIs. With pycelonis_llm you can use the LiteLLM interface to generate basic chat completions.

To use the LLM assigned to your ML Workbench, simply call the completion function and pass the messages parameter to get a response from the model (pycelonis_llm automatically sets the model to the LLM assigned to your ML workbench).

Note: It is not possible to adjust the LLM offered by Celonis through the LiteLLM model parameter. Changing the LLM always needs to be performed through the ML Workbench creation/update dialog.

For more information on LiteLLM, take a look at their documentation.

In [9]:

from litellm import completion

question = "Are LLMs going to replace humans soon?"
messages = [
    {"role": "system", "content": "Your objective is to respond to questions in one sentence."},
    {"role": "user", "content": question},
]
response = completion(messages=messages, max_tokens=100)

print(f"Question:\t{question}\nLLM Response:\t{response.choices[0].message.content}")

from litellm import completion question = "Are LLMs going to replace humans soon?" messages = [ {"role": "system", "content": "Your objective is to respond to questions in one sentence."}, {"role": "user", "content": question}, ] response = completion(messages=messages, max_tokens=100) print(f"Question:\t{question}\nLLM Response:\t{response.choices[0].message.content}")

Question:	Are LLMs going to replace humans soon?
LLM Response:	No, LLMs are tools designed to assist humans, not replace them.

By default, LiteLLM debug logs are suppressed by pycelonis_llm. You can enable them using:

import litellm

litellm.suppress_debug_info = False

2. LangChain¶

LangChain is a framework to build use cases with LLMs by chaining interoperable components.

It has a modular design with a focus on constructing and orchestrating sequences of operations by leveraging its chains, prompts, models, memory, and agents. Some example use cases are retrieving information from documents and interacting with databases to write, analyze, and optimize queries. Furthermore, it supports:

• Agents
• Tool calling
• Chatbots
• ...

For more information on LangChain, take a look at their documentation.

You need the langchain-community package alongside pycelonis_llm to use the LangChain integration. To install it, run:

In [ ]:

%pip install langchain-community

%pip install langchain-community

Then, you can use LangChain with the the CelonisLangChain model which automatically uses the LLM assigned to your ML Workbench.

In [10]:

from pycelonis_llm.integrations.langchain import CelonisLangChain
from langchain_core.messages import HumanMessage, SystemMessage

chat = CelonisLangChain()

question = "What is the answer to the ultimate question of life, the universe and everything?"
messages = [
    SystemMessage(content="Your objective is to respond to questions in one sentence."),
    HumanMessage(content=question),
]
response = chat.invoke(messages)

print(f"Question:\t{question}\nLLM Response:\t{response.content}")

from pycelonis_llm.integrations.langchain import CelonisLangChain from langchain_core.messages import HumanMessage, SystemMessage chat = CelonisLangChain() question = "What is the answer to the ultimate question of life, the universe and everything?" messages = [ SystemMessage(content="Your objective is to respond to questions in one sentence."), HumanMessage(content=question), ] response = chat.invoke(messages) print(f"Question:\t{question}\nLLM Response:\t{response.content}")

Question:	What is the answer to the ultimate question of life, the universe and everything?
LLM Response:	The answer to the ultimate question of life, the universe, and everything is 42.

3. LLamaIndex¶

LLamaIndex is an open source framework to support LLM application development. Compared to LangChain it is more focused on retrieval-augmented generation use cases. It allows to ingest data which can then be queried using natural language. Furthermore, it supports:

• Question-Answering (RAG)
• Chatbots
• Agents
• ...

For more information on LlamaIndex, take a look at their documentation.

You need the llama-index and llama-index-llms-litellm package alongside pycelonis_llm to use the LlamaIndex integration. To install it, run:

In [ ]:

%pip install llama-index llama-index-llms-litellm

%pip install llama-index llama-index-llms-litellm

Then, you can use LlamaIndex with the CelonisLlamaIndex model which automatically uses the LLM assigned to your ML Workbench.

In [21]:

from pycelonis_llm.integrations.llama_index import CelonisLlamaIndex
from llama_index.core.llms import ChatMessage

llm = CelonisLlamaIndex()

question = "Explain Celonis to a 5-year-old."
messages = [
    ChatMessage(role="system", content="Your objective is to respond to questions in one sentence."),
    ChatMessage(role="user", content=question),
]
response = llm.chat(messages)

print(f"Question:\t{question}\nLLM Response:\t{response.message.content}")

from pycelonis_llm.integrations.llama_index import CelonisLlamaIndex from llama_index.core.llms import ChatMessage llm = CelonisLlamaIndex() question = "Explain Celonis to a 5-year-old." messages = [ ChatMessage(role="system", content="Your objective is to respond to questions in one sentence."), ChatMessage(role="user", content=question), ] response = llm.chat(messages) print(f"Question:\t{question}\nLLM Response:\t{response.message.content}")

Question:	Explain Celonis to a 5-year-old.
LLM Response:	Celonis is like a super-smart detective for businesses, helping them find and fix problems to work better and faster.

Conclusion¶

Congratulations! You have learned how to utilise common LLM frameworks such as LangChain and LlamaIndex with the LLMs offered by Celonis.

Next, we recommend the other PyCelonis tutorials (for example Data Integration - Introduction to learn how to access your data model from the ML Workbench and query your data which combined with pycelonis_llm can be used to build a RAG based application).