Replies: 1 comment
-
Please provide more information: "But traing is not effective" and "but RESULTS are not good" is not particularly helpful. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Describe the bug
A clear and concise description of what the bug is.
Using the fllowing code to training the snowflake table. But traing is not effective
Hi All, I am trying train my snowflake tables but RESULTS are not good. Using ollama3,sqldb as vectordb
training_plan = vn.get_training_plan_snowflake(
filter_databases=[MY_SNOWFLAKE_DATABASE], # Optional: Filter databases
filter_schemas=[MY_SNOWFLAKE_SCHEMA], # Optional: Filter schemas
include_information_schema=False, # Optional: Include system schema
use_historical_queries=False # Optional: Include historical queries
)
print(training_plan)
# Filter the plan
filtered_plan = []
for item in training_plan._plan:
if item.item_group != '' and item.item_name in (MY_TABLE):
filtered_plan.append(item)
training_plan._plan = filtered_plan
# 1.Train the model using the generated training plan
print("----plan---" ,training_plan)
vn.train(plan=training_plan)
The ddl train as follows
id = vn.train(ddl="""CREATE TABLE IF NOT EXISTS MY_CBOT.TESTS.MY_TABLE (
TEST_DETAILS_ID NUMBER(38,0),
TEST_ID VARCHAR(50),
TEST_CLT_ID NUMBER(38,0),
TEST_CLT_NAME VARCHAR(255),
TEST_STATUS VARCHAR(255),MY_JSON VARIANT
)"""
)
To Reproduce
Steps to reproduce the behavior:
Expected behavior
A clear and concise description of what you expected to happen.
Error logs/Screenshots
If applicable, add logs/screenshots to give more information about the issue.
Desktop (please complete the following information where):
Additional context
Add any other context about the problem here.
Beta Was this translation helpful? Give feedback.
All reactions