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

chore(wren-ai-service): add README about how to integrate dspy into wrenAI #892

Closed
wants to merge 1 commit into from

Conversation

tedyyan
Copy link
Contributor

@tedyyan tedyyan commented Nov 9, 2024

Related PRs

Added Readme and fixed a new exception.

@tedyyan tedyyan marked this pull request as ready for review November 9, 2024 19:59
@cyyeh cyyeh changed the title add README about how to integrate dspy into wrenAI chore(wren-ai-service): add README about how to integrate dspy into wrenAI Nov 11, 2024
@cyyeh cyyeh self-requested a review November 11, 2024 01:16
@cyyeh cyyeh added module/ai-service ai-service related ci/ai-service ai-service related labels Nov 11, 2024
@@ -68,6 +68,58 @@ The evaluation results will be presented on Langfuse as follows:

![shallow_trace_example](../docs/imgs/shallow_trace_example.png)


## How to use Dspy in Wren AI
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

should be DSPy

## How to use Dspy in Wren AI
### Step 1: Generate evaluation dataset

Please use eval.py and the spider2 v1 dataset to train an optimized dspy module (https://github.com/taoyds/spider/tree/master/evaluation_examples/examples)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

  • what is eval.py?
  • should be Spider v1 dataset
  • is there relevant command here?

Please use eval.py and the spider2 v1 dataset to train an optimized dspy module (https://github.com/taoyds/spider/tree/master/evaluation_examples/examples)
The `prediction_eval_ask_9df57d69-250c-4a10-b6a5-6595509fed6b_2024_10_23_132136.toml` is a predict dataset generated without dspy

```
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

please make sure the given command is executable

@@ -175,16 +175,16 @@ async def _task(result: Dict[str, str]):
valid_generation_results.append(
{
"sql": quoted_sql,
"correlation_id": addition.get("correlation_id", ""),
"correlation_id": addition.get("correlation_id", "") if isinstance(addition, dict) else addition
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I am curious the reason of modification here

Copy link
Member

@cyyeh cyyeh left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for contribution, and I've left some comments here

@tedyyan tedyyan mentioned this pull request Nov 12, 2024
@tedyyan
Copy link
Contributor Author

tedyyan commented Nov 12, 2024

because dspy code was removed from main. so move to eat/ai-service/dspy branch. close the PR see the follow-up #902

@tedyyan tedyyan closed this Nov 12, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ci/ai-service ai-service related module/ai-service ai-service related
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants