CommencerCommencer gratuitement

A text-to-query workflow in practice

Cet exercice fait partie du cours

Text-to-Query Agents with MongoDB and LangGraph

Afficher le cours

Instructions

  • Initialize an OpenAI LLM with appropriate temperature value using LangChain's ChatOpenAI class.
  • Convert the natural language query provided into a MongoDB query, execute it, and obtain the results as a Python list.
  • Create a prompt template for the LLM, consisting of a system prompt and a placeholder for messages, using the .from_messages() method.
  • Chain the prompt with the LLM using the | operator, and invoke it on the query results (docs) and the user query (user_query).

Note: If you’re running DataLab in Restricted Mode, this exercise isn’t supported yet. We’re actively working on making it available in the future.

Exercice interactif pratique

Passez de la théorie à la pratique avec l’un de nos exercices interactifs

Commencer l’exercice