Skip to main content
This guide covers common issues encountered during migration. For breaking changes and migration steps, see the Migration Guide.

​
Common Issues and Solutions

​
Issue: LLM Not Found

Problem: ModuleNotFoundError: No module named 'pandasai.llm' Solution: Install the appropriate LLM extension 
pip install pandasai-litellm

​
Issue: Skills Not Working

Problem: Skills not being recognized Solution: Use the new @pai.skill() decorator 
# v2
from pandasai.skills import skill
@skill
def my_skill():
    pass

# v3
import pandasai as pai
@pai.skill()
def my_skill():
    "doc string"
    pass

​
Issue: Configuration Not Applied

Problem: Configuration settings not taking effect Solution: Use global configuration 
# v2
df = SmartDataframe(data, config=config)

# v3
pai.config.set(config)
df = pai.DataFrame(data)

​
Issue: Agent Methods Not Found

Problem: AttributeError: 'Agent' object has no attribute 'clarification_questions' (or rephrase_query, explain) Solution: These methods have been removed in v3. Use alternatives: 
# v2 - These methods are removed
agent.clarification_questions('What is the GDP?')
agent.rephrase_query('What is the GDP?')
agent.explain()

# v3 - Use these instead
response = agent.chat('What is the GDP?')
follow_up = agent.follow_up('What about last year?')  # Maintains context

​
Get Support

​
Community Support

If you need help with migration or have questions, join our Discord community where you can get support from other PandasAI users and contributors.

​
Enterprise Support

Enterprise customers should contact their dedicated account manager via Slack or through the dedicated support channel selected at purchase. Enterprise support includes priority assistance with migration, custom implementation guidance, and direct access to the engineering team.