Loading and Rendering Prompts

Use load_prompt to retrieve prompts from the Patronus platform and render them with dynamic variables.

Loading prompts

Basic loading

import patronus
from patronus.prompts import load_prompt
 
patronus.init()
 
# Load the latest version
prompt = load_prompt(name="content/writing/blog-instructions")
rendered = prompt.render()
print(rendered)

Async loading

from patronus.prompts import aload_prompt
 
prompt = await aload_prompt(name="content/writing/blog-instructions")

Loading specific versions

By revision number

# Load a specific revision
prompt = load_prompt(name="content/blog/technical-explainer", revision=3)

By label

# Load by label (e.g., production environment)
prompt = load_prompt(name="legal/contracts/privacy-policy", label="production")

Rendering prompts

Render prompts with variables using keyword arguments:

prompt = load_prompt(name="support/troubleshooting/diagnostic")
 
rendered = prompt.render(
    user_query="How do I optimize database performance?",
    expertise_level="intermediate",
    product_version="v2.3"
)

Template engines

Patronus supports multiple template engines for rendering prompts.

F-string (default)

# F-string templating uses Python's f-string syntax
rendered = prompt.with_engine("f-string").render(**kwargs)

Mustache

# Mustache templating uses {{variable}} syntax
rendered = prompt.with_engine("mustache").render(**kwargs)

Jinja2

# Jinja2 templating uses {{variable}} syntax with advanced features
rendered = prompt.with_engine("jinja2").render(**kwargs)

Setting default engine

Configure the default template engine during initialization:

import patronus
 
patronus.init(
    prompt_templating_engine="mustache"
)

Using multiple prompts

Complex applications often combine multiple prompts:

import patronus
from patronus.prompts import load_prompt
import openai
 
patronus.init()
 
# Load different prompt components
system_prompt = load_prompt(name="support/chat/system")
user_query_template = load_prompt(name="support/chat/user-message")
response_formatter = load_prompt(name="support/chat/response-format")
 
# Create OpenAI client
client = openai.OpenAI()
 
# Combine prompts in a chat completion
response = client.chat.completions.create(
    model="gpt-4",
    messages=[
        {"role": "system", "content": system_prompt.render(
            product_name="CloudWorks Pro",
            available_features=["file sharing", "collaboration", "automation"],
            knowledge_cutoff="2024-05-01"
        )},
        {"role": "user", "content": user_query_template.render(
            user_name="Alex",
            user_tier="premium",
            user_query="How do I share files with external users?"
        )}
    ],
    temperature=0.7,
    max_tokens=500
)
 
# Post-process the response
formatted_response = response_formatter.render(
    raw_response=response.choices[0].message.content,
    user_name="Alex",
    add_examples=True
)

Using with LLM providers

OpenAI

import openai
from patronus.prompts import load_prompt
 
system_prompt = load_prompt(name="support/chat/system")
 
client = openai.OpenAI()
response = client.chat.completions.create(
    model="gpt-4",
    messages=[
        {"role": "system", "content": system_prompt.render(
            product_name="CloudWorks",
            user_tier="enterprise"
        )},
        {"role": "user", "content": "How do I configure SSO?"}
    ]
)

Anthropic

import anthropic
from patronus.prompts import load_prompt
 
system_prompt = load_prompt(name="support/knowledge-base/technical-assistance")
 
client = anthropic.Anthropic()
response = client.messages.create(
    model="claude-3-opus-20240229",
    system=system_prompt.render(
        product_name="CloudWorks Pro",
        user_tier="enterprise",
        available_features=["advanced monitoring", "auto-scaling"]
    ),
    messages=[
        {"role": "user", "content": "How do I configure the load balancer?"}
    ]
)

Loading and Rendering Prompts

On this page