googleapis / googleapis/python-aiplatform

[Reasoning Engine] LangchainAgent.stream_query attempts to import from deprecated langchain.load path

Open
#6,397 0 comments 0 reactions 0 assignees View on GitHub
api: vertex-ai
Dominant language
Python
Stars
905
Forks
465
Avg merge
1d 13h
Merged PRs (30d)
44

Description

#### Environment details

- OS type and version: Ubuntu 24.04.4 LTS
- Python version: `3.12.10`
- pip version: `25.2`
- `google-cloud-aiplatform` version: `Latest from main`

#### Steps to reproduce

1. Initialize a `LangchainAgent` or `LanggraphAgent` from the agent engine or reasoning engine templates.
2. Call the `query` or `stream_query` method.
3. Observe that it fails with an `ImportError` because it attempts to import from `langchain.load` instead of `langchain_core.load`.

#### Code example

```python
from vertexai.agent_engines.templates.langchain import LangchainAgent

# Initialize agent
agent = LangchainAgent(model="gemini-1.5-flash-001")
agent.set_up()

# Both query and stream_query are affected
result = agent.query(input="Hello")

for chunk in agent.stream_query(input="Hello"):
print(chunk)
```

#### Stack trace
```
Traceback (most recent call last):
File "example.py", line 8, in
for chunk in agent.stream_query(input="Hello"):
File ".../vertexai/agent_engines/templates/langchain.py", line 665, in stream_query
from langchain.load import dump as langchain_load_dump
ImportError: cannot import name 'dump' from 'langchain.load'
```

#### Affected files

The same deprecated import (`from langchain.load import dump`) exists in both `query()` and `stream_query()` across all 4 template modules:

- `vertexai/agent_engines/templates/langchain.py`
- `vertexai/agent_engines/templates/langgraph.py`
- `vertexai/preview/reasoning_engines/templates/langchain.py`
- `vertexai/preview/reasoning_engines/templates/langgraph.py`

Making sure to follow these steps will guarantee the quickest resolution possible.

Thanks!

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.