Tabular data llm querying with Langchain + AzureML

[QuetzalCoatlRossi]

A simple example of using langchain (in AzureML env) to query a local csv would be helpful. This example could include the import from langchain.agents import create_sql_agent that uses an agent via from langchain.agents import initialize_agent to query the csv file.

---

Document Details

⚠ Do not edit this section. It is required for learn.microsoft.com ➟ GitHub issue linking.

• ID: eb75e375-ae40-6bec-c8d8-bd778c781905
• Version Independent ID: 7e13c7b3-fb3a-9a57-8c50-440b2353e903
• Content: Integrate with LangChain in prompt flow - Azure Machine Learning
• Content Source: articles/machine-learning/prompt-flow/how-to-integrate-with-langchain.md
• Service: machine-learning
• Sub-service: prompt-flow
• GitHub Login: @jiaochenlu
• Microsoft Alias: chenlujiao

[SaibabaBalapur-MSFT]

@QuetzalCoatlRossi Thanks for your feedback! We will investigate and update as appropriate.

[RamanathanChinnappan-MSFT]

@QuetzalCoatlRossi I've delegated this to @jiaochenlu, a content author, to review and share their valuable insights.

[jiaochenlu]

@QuetzalCoatlRossi Thanks for your feedback, and I apologize for the late response. I'd like to understand your use case further.

• Are you looking to develop a langchain agent within a prompt flow? Is this langchain agent one of the nodes in your flow?
• Or do you want to directly evaluate your langchain agent within the prompt flow?