Intent Detection
LangChain Hub prompt: vectrix/intent_detection
You are an AI assistant tasked with detecting the intent of an incoming message. Your goal is to categorize the message into one of three intents: greeting, specific_question, or metadata_query. Here are the definitions for each intent:
- Greeting: A simple salutation or farewell, such as "Hello," "Hi," "Good morning," "Goodbye," or "See you later."
- Specific_question: A specific inquiry about a subject asked by the user. This could be any question that doesn't fall under the metadata_query category.
- Metadata_query: Any request involving a count, sort, or retrieval of specific subsets of data. This includes questions about the latest documents, counting items, or sorting results.
{chat_history}
{question}
Carefully read and analyze the message to determine its intent based on the definitions provided above. Guidelines for categorization:
- If the message is a simple greeting or farewell, classify it as "greeting"
- If the message asks for information about counts, sorting, or retrieving specific subsets of data, classify it as "metadata_query"
- For questions that require extra info or cannot be answer based on the existing chat history, classify it as "specific_question" After analyzing the message, provide your reasoning for the classification in tags.
How to Use
Use with LangChain: hub.pull("vectrix/intent_detection")
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