To Help Look Up The Best Intent Based On Intent Responses.
To help look up the best intent based on intent responses.
Given a user utterance from {question}, the system will perform the following steps to determine the most appropriate intent from list {intent_list} using this {context} and criteria:
- Extract key phrases and terms from the user's utterance that indicate their need or the action they want to perform.
- Distinguish if the {question} is related to retail department, photo department, pharmacy department or is vague. Use that information to find right intent.
- Compare these key phrases and terms to the purpose and utility descriptions of each intent in the database.
- Assess which intent's service path aligns most closely with the extracted key phrases and terms.
- Evaluate the purpose and utility of each intent to determine how well it matches the user's implied goals.
- Rank the intents based on the degree of match with the user's utterance.
- Select the top two intents from this {intent_list} that are most relevant to the user's needs. Remember, only select IntentName from the the intent list.
The system will then generate a JSON output with the following structure:
"CustomerUnderstanding": "The system's interpretation of the user's utterance based on key terms and overall context.",
"IntentName1": "The name of the first pertinent Intent that best matches the user's needs.",
"IntentName2": "The name of the second pertinent Intent that also aligns with the user's requirements but to a lesser extent.",
"IntentClarification": "A detailed explanation of why the chosen intents are relevant to the customer's issue, including how specific elements of the service path and purpose/utility match the user's utterance."
How to Use
Use with LangChain: hub.pull("duxxfast/rag_best_intent_lookup")
Related Prompts
More prompts in Data & Analytics
Sql Agent System Prompt
LangChain Hub prompt: langchain-ai/sql-agent-system-prompt
Buyer Persona Legend
Generate detailed User Personas for your Business with data neatly organized into a table.
Prompt For Text To SQL
Prompt for text-to-SQL
Unlock Etsy Success 2024
This prompt will help you take your Etsy store to the next level.
A Prompt To Generate Multiple Variations Of A Vector Store Query For Use In A MultiQueryRetriever
A prompt to generate multiple variations of a vector store query for use in a MultiQueryRetriever
Text To Postgres Sql
LangChain Hub prompt: jacob/text-to-postgres-sql