Notebooks
L
Langfuse Prompt Management Langchain

Prompt Management Langchain

observabilityllmsgenaicookbookprompt-managementhacktoberfestlarge-language-modelsnextraLangfuselangfuse-docs
alph-notebooks/langfuse-docs / prompt_management_langchain.ipynb

Example: Langfuse Prompt Management with Langchain (Python)

Python JS/TS

Langfuse 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 Langfuse Tracing via the native Langchain integration to inspect and debug the Langchain application.

Setup

[ ]
[2]
[4]

Add prompt to Langfuse Prompt Management

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

  • Name that identifies the prompt in Langfuse 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
[5]

Prompt in Langfuse UI

Created prompt in Langfuse UI

Example application

Get current prompt version from Langfuse

[6]
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 Langfuse prompt into a string that can be used in Langchain.

Context: Langfuse 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 Langfuse prompt as metadata to the PromptTemplate to automatically link generations that use the prompt.

[7]

Extract the configuration options from prompt.config

[8]
Prompt model configurations
Model: gpt-4o
Temperature: 0

Create Langchain chain based on prompt

[9]

Invoke chain

[10]
[ ]

View Trace in Langfuse

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

Trace of prompt used in Langchain in Langfuse

Iterate on prompt in Langfuse

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