microsoft / microsoft/KBLaM

Question about dataset

Open
#52 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Jupyter Notebook
Stars
1.5k
Forks
125
Avg merge
22d 8m
Merged PRs (30d)
1

Description

  1. Why call api_call_chat twice ? https://github.com/microsoft/KBLaM/blob/65262680386c5e0218928ed6dd7fcf4736fc8043/dataset_generation/gen_synthetic_data.py#L183
    https://github.com/microsoft/KBLaM/blob/65262680386c5e0218928ed6dd7fcf4736fc8043/dataset_generation/gen_synthetic_data.py#L185

  2. To generate dataset we should provide a AzureOpenAI endpoint_url, could I use other llm instead of self.OA_client ?
    I see we can use all-MiniLM-L6-v2 to generate kb embedding instead of using GPT class.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with dataset_generation/gen_synthetic_data.py at the two api_call_chat references on lines 183 and 185, then trace how AzureOpenAI and self.OA_client are used. Check the dataset-generation instructions and embedding setup. Done means documenting why the calls are repeated and whether alternative LLM or embedding clients are supported.

Written by the indexing model from the issue text.

Assessment

Tech stack
azure, python
Domain
data, machine-learning
Issue type
Documentation
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.