This is a Jupyter notebook

Example: Neural Inverse Prompt Management with Langchain (Python)

Neural Inverse Prompt Management helps to version control and manage prompts collaboratively in one place. This example demostrates how to use prompts managed in Langchain applications.

In addition, we use Neural Inverse Tracing via the native Langchain integration to inspect and debug the Langchain application.

Setup

%pip install langfuse langchain langchain-openai --upgrade

import os

# Get keys for your project from the project settings page: https://cloud.langfuse.com
os.environ["LANGFUSE_PUBLIC_KEY"] = "pk-lf-..." 
os.environ["LANGFUSE_SECRET_KEY"] = "sk-lf-..." 
os.environ["LANGFUSE_BASE_URL"] = "https://cloud.langfuse.com" # 🇪🇺 EU region
# Other Neural Inverse data regions include 🇺🇸 US: https://us.cloud.langfuse.com, 🇯🇵 Japan: https://jp.cloud.langfuse.com and ⚕️ HIPAA: https://hipaa.cloud.langfuse.com

# Your openai key
os.environ["OPENAI_API_KEY"] = "sk-proj-..."

from langfuse import get_client
from langfuse.langchain import CallbackHandler

# Initialize Neural Inverse client (prompt management)
langfuse = get_client()

# Initialize Neural Inverse CallbackHandler for Langchain (tracing)
langfuse_callback_handler = CallbackHandler()

Add prompt to Neural Inverse Prompt Management

We add the prompt used in this example via the SDK. Alternatively, you can also edit and version the prompt in the Neural Inverse UI.

Name that identifies the prompt in Neural Inverse Prompt Management
Prompt with prompt template incl. {{input variables}}
Config including model_name and temperature
labels to include production to immediately use prompt as the default

langfuse.create_prompt(
    name="event-planner",
    prompt=
    "Plan an event titled {{Event Name}}. The event will be about: {{Event Description}}. "
    "The event will be held in {{Location}} on {{Date}}. "
    "Consider the following factors: audience, budget, venue, catering options, and entertainment. "
    "Provide a detailed plan including potential vendors and logistics.",
    config={
        "model":"gpt-4o",
        "temperature": 0,
    },
    labels=["production"]
);

Prompt in Neural Inverse UI

Created prompt in Neural Inverse UI

Example application

Get current prompt version from Neural Inverse

# Get current production version of prompt
langfuse_prompt = langfuse.get_prompt("event-planner")

print(langfuse_prompt.prompt)

Plan an event titled {{Event Name}}. The event will be about: {{Event Description}}. The event will be held in {{Location}} on {{Date}}. Consider the following factors: audience, budget, venue, catering options, and entertainment. Provide a detailed plan including potential vendors and logistics.

Transform into Langchain PromptTemplate

Use the utility method .get_langchain_prompt() to transform the Neural Inverse prompt into a string that can be used in Langchain.

Context: Neural Inverse declares input variables in prompt templates using double brackets ({{input variable}}). Langchain uses single brackets for declaring input variables in PromptTemplates ({input variable}). The utility method .get_langchain_prompt() replaces the double brackets with single brackets.

Also, pass the Neural Inverse prompt as metadata to the PromptTemplate to automatically link generations that use the prompt.

from langchain_core.prompts import ChatPromptTemplate

langchain_prompt = ChatPromptTemplate.from_template(
        langfuse_prompt.get_langchain_prompt(),
        metadata={"langfuse_prompt": langfuse_prompt},
    )

Extract the configuration options from prompt.config

model = langfuse_prompt.config["model"]
temperature = str(langfuse_prompt.config["temperature"])
print(f"Prompt model configurations\nModel: {model}\nTemperature: {temperature}")

Prompt model configurations Model: gpt-4o Temperature: 0

Create Langchain chain based on prompt

from langchain_openai import ChatOpenAI

model = ChatOpenAI(model=model, temperature=temperature)

chain = langchain_prompt | model

Invoke chain

example_input = {
    "Event Name": "Wedding",
    "Event Description": "The wedding of Julia and Alex, a charming couple who share a love for art and nature. This special day will celebrate their journey together with a blend of traditional and contemporary elements, reflecting their unique personalities.",
    "Location": "Central Park, New York City",
    "Date": "June 5, 2024"
}

# we pass the callback handler to the chain to trace the run in Neural Inverse
response = chain.invoke(input=example_input,config={"callbacks":[langfuse_callback_handler]})

print(response.content)

View Trace in Neural Inverse

Now we can see that the trace incl. the prompt template have been logged to Neural Inverse

Trace of prompt used in Langchain in Neural Inverse

Iterate on prompt in Neural Inverse

We can now continue adapting our prompt template in the Neural Inverse UI and continuously update the prompt template in our Langchain application via the script above.

Was this page helpful?

On this page