Try Gemini 1.5 models, our newest multimodal models in Vertex AI, and see what you can build with a 1M token context window. Try Gemini 1.5 models, our newest multimodal models in Vertex AI, and see what you can build with a 1M token context window.

Troubleshoot developing an application

This document describes how to resolve errors that you might encounter when developing an application.

Content generation errors

Issue:

You receive an error message similar to the following:

ValueError: Cannot get the Candidate text.
Response candidate content part has no text.

Possible cause:

This error might be caused by using a version of langchain-google-vertexai that's not compatible with google-cloud-aiplatform. Version 1.0.2 or later of langchain-google-vertexai is required. To check which version you're using, run the following command in your terminal:

pip show langchain-google-vertexai

Recommended solution:

Install version 1.0.2 of langchain-google-vertexai. This version includes the LangChain tool-calling updates that are required to work with google-cloud-aiplatform. To update your version of langchain-google-vertexai, run the following command in your terminal:

pip install langchain-google-vertexai --upgrade

After running the update command, verify that you're using version 1.0.2 or later by running the following command in your terminal:

pip show langchain-google-vertexai

If you're in a notebook instance (for example, Jupyter or Colab or Workbench), you might need to restart your runtime to use the updated packages.