Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Error during Docker Compose Up with Custom Google BigQuery Integration #143

Open
ashish-cheruku opened this issue Sep 30, 2024 · 0 comments

Comments

@ashish-cheruku
Copy link

I am currently using langraph studio woriking for one of my project using the repo datavisualization_langgraph trying to integrate Google BigQuery into the LangGraph project as a replacement for SQLite. After making necessary modifications to the backend files, I encounter an error when executing docker compose up for setting up the backend.

During the Docker build process, the following error is encountered:

failed to solve: process "/bin/sh -c PYTHONDONTWRITEBYTECODE=1 pip install -c /api/constraints.txt -e /deps/" did not complete successfully: exit code: 1
ERROR: /deps/ is not a valid editable requirement. It should either be a path to a local project or a VCS URL.

• OS: macOS Sonoma V 14.6.1
• Docker version: Docker Engine v27.2.0

I have modified my backend_py and frontend to include Google BigQuery libraries and updated the requirements.txt as per the needs for Google BigQuery integration. Below are the excerpts from the backend_py and other relevant configuration details:

➣ Installed relevant dependencies
➣ Made changes in .env file to support bigquery
➣ Created a BigQueryManager.py file insted of DatabaseManager.py file to handle bigquery
here's BigQueryManager.py file

from google.cloud import bigquery
class BigQueryManager:
def init(self):
self.client = bigquery.Client()

def execute_query(self, query: str):
query_job = self.client.query(query)
results = query_job.result()
return [dict(row.items()) for row in results]

def get_schema(self, dataset_id: str, table_id: str):
dataset_ref = self.client.dataset(dataset_id)
table_ref = dataset_ref.table(table_id)
table = self.client.get_table(table_ref)
return [{"name": field.name, "type": field.field_type} for field in table.schema]
➣ Modified SQLagent.py file

from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import JsonOutputParser
from my_agent.BigQueryManager import BigQueryManager
from my_agent.LLMManager import LLMManager

Also changed db manager as bigquery instead of SQLlite

I would appreciate guidance on how to correctly specify the path or configure the Docker environment so that the build process successfully recognizes and installs the required packages from /deps/*. Any suggestions on alternative approaches or corrections in the Backend file would also be highly beneficial.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant