Fix pandas DataFrame input support in crew.kickoff()

- Add automatic serialization of unsupported types in interpolate_only
- Support pandas DataFrames and other complex objects via to_serializable
- Add comprehensive tests for DataFrame inputs
- Maintain backward compatibility with existing input types

Fixes #2925

Co-Authored-By: João <joao@crewai.com>
This commit is contained in:
Devin AI
2025-05-31 19:41:21 +00:00
parent 1da2fd2a5c
commit acd5aadfd1
3 changed files with 207 additions and 21 deletions

View File

@@ -4566,3 +4566,96 @@ def test_reset_agent_knowledge_with_only_agent_knowledge(researcher,writer):
mock_reset_agent_knowledge.assert_called_once_with([mock_ks_research,mock_ks_writer])
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_kickoff_with_pandas_dataframe():
"""Test that crew.kickoff works with pandas DataFrame inputs."""
import pandas as pd
df = pd.DataFrame({
"name": ["Alice", "Bob", "Charlie"],
"age": [25, 30, 35],
"city": ["New York", "London", "Tokyo"]
})
agent = Agent(
role="Data Analyst",
goal="Analyze the provided data",
backstory="You are an expert data analyst",
)
task = Task(
description="Analyze this dataset: {data}",
expected_output="A brief summary of the data",
agent=agent,
)
crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff(inputs={"data": df})
assert result is not None
assert "Alice" in str(result) or "Bob" in str(result)
def test_crew_inputs_interpolate_with_dataframe():
"""Test that input interpolation works with pandas DataFrames."""
import pandas as pd
df = pd.DataFrame({"col1": [1, 2], "col2": [3, 4]})
agent = Agent(
role="Analyst",
goal="Process {data_type} data",
backstory="Expert in {data_type} analysis",
)
task = Task(
description="Process this data: {dataset}",
expected_output="Analysis of {dataset}",
agent=agent,
)
crew = Crew(agents=[agent], tasks=[task])
inputs = {"data_type": "tabular", "dataset": df}
crew._interpolate_inputs(inputs=inputs)
assert "tabular" in crew.agents[0].goal
assert "tabular" in crew.agents[0].backstory
assert str(df) in crew.tasks[0].description
assert str(df) in crew.tasks[0].expected_output
def test_crew_inputs_interpolate_mixed_types_with_dataframe():
"""Test input interpolation with mixed types including DataFrames."""
import pandas as pd
df = pd.DataFrame({"values": [10, 20, 30]})
agent = Agent(
role="{role_name}",
goal="Analyze {count} records",
backstory="Expert with {dataset}",
)
task = Task(
description="Process {dataset} with {count} records",
expected_output="{count} insights from {dataset}",
agent=agent,
)
crew = Crew(agents=[agent], tasks=[task])
inputs = {
"role_name": "Data Scientist",
"count": 3,
"dataset": df
}
crew._interpolate_inputs(inputs=inputs)
assert crew.agents[0].role == "Data Scientist"
assert "3" in crew.agents[0].goal
assert str(df) in crew.agents[0].backstory
assert str(df) in crew.tasks[0].description
assert "3" in crew.tasks[0].expected_output

View File

@@ -1,6 +1,7 @@
from typing import Any, Dict, List, Union
import pytest
import pandas as pd
from crewai.utilities.string_utils import interpolate_only
@@ -184,4 +185,81 @@ class TestInterpolateOnly:
with pytest.raises(ValueError) as excinfo:
interpolate_only(template, inputs)
assert "inputs dictionary cannot be empty" in str(excinfo.value).lower()
def test_interpolate_only_with_dataframe(self):
"""Test that interpolate_only handles pandas DataFrames correctly."""
df = pd.DataFrame({"name": ["Alice", "Bob"], "age": [25, 30]})
result = interpolate_only("Data: {data}", {"data": df})
assert "Alice" in result
assert "Bob" in result
assert "25" in result
assert "30" in result
def test_interpolate_only_mixed_types_with_dataframe(self):
"""Test interpolate_only with mixed input types including DataFrame."""
df = pd.DataFrame({"col": [1, 2, 3]})
inputs = {
"text": "hello",
"number": 42,
"flag": True,
"data": df,
"items": [1, 2, 3]
}
template = "Text: {text}, Number: {number}, Flag: {flag}, Data: {data}, Items: {items}"
result = interpolate_only(template, inputs)
assert "hello" in result
assert "42" in result
assert "True" in result
assert "col" in result
assert "[1, 2, 3]" in result
def test_interpolate_only_unsupported_type_error(self):
"""Test that interpolate_only handles unsupported types gracefully."""
class CustomObject:
def __str__(self):
raise Exception("Cannot serialize")
with pytest.raises(ValueError, match="Unable to serialize CustomObject"):
interpolate_only("Value: {obj}", {"obj": CustomObject()})
def test_interpolate_only_complex_dataframe(self):
"""Test interpolate_only with more complex DataFrame structures."""
df = pd.DataFrame({
"product": ["Widget A", "Widget B", "Widget C"],
"sales": [100, 150, 200],
"region": ["North", "South", "East"]
})
result = interpolate_only("Sales report: {report}", {"report": df})
assert "Widget A" in result
assert "100" in result
assert "North" in result
assert "sales" in result
assert "product" in result
def test_interpolate_only_backward_compatibility(self):
"""Test that existing supported types still work correctly."""
inputs = {
"text": "hello",
"number": 42,
"float_val": 3.14,
"flag": True,
"nested": {"key": "value"},
"items": [1, 2, 3]
}
template = "Text: {text}, Number: {number}, Float: {float_val}, Flag: {flag}, Nested: {nested}, Items: {items}"
result = interpolate_only(template, inputs)
assert "hello" in result
assert "42" in result
assert "3.14" in result
assert "True" in result
assert "key" in result
assert "[1, 2, 3]" in result