Now, as we have defined our system message, let's utilize the Langchain's Prompt Templates. Prompt templates in Langchain allow you to define a general prompt structure with placeholders for specific information. These placeholders are then filled in at runtime with the relevant values for your use case.
Importing Libraries:
from langchain.prompts import (
SystemMessagePromptTemplate,
PromptTemplate,
ChatPromptTemplate,
HumanMessagePromptTemplate
)
Define a function get_prompt that creates a Langchain Prompt Template:
--
def get_prompt():
prompt = ChatPromptTemplate(
input_variables=['context', 'question', 'chat_history', 'organization_name', 'organization_info', 'contact_info'],
messages=[
SystemMessagePromptTemplate(
prompt=PromptTemplate(
input_variables=['context', 'chat_history', 'organization_name', 'organization_info', 'contact_info'],
template=system_prompt, template_format='f-string',
validate_template=True
), additional_kwargs={}
),
HumanMessagePromptTemplate(
prompt=PromptTemplate(
input_variables=['question'],
template='{question}\nHelpful Answer:', template_format='f-string',
validate_template=True
), additional_kwargs={}
)
]
)
return prompt
Note - Having trouble with the assessment engine? Follow the steps listed here
Loading comments...