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

Dev/llm info extract #481

Merged
merged 40 commits into from
Nov 15, 2024
Merged

Dev/llm info extract #481

merged 40 commits into from
Nov 15, 2024

Conversation

BeachWang
Copy link
Collaborator

@BeachWang BeachWang commented Nov 11, 2024

Add information extraction OPs, including:

  1. text_chunk_mapper: split text into chunks.
  2. extract_entity_attribute_mapper: extract given attribute from the text.
  3. extract_entity_relation_mapper: modified from lightRAG, extract entities and relations for knowledge graph from text.
  4. extract_event_mapper: extract events and relevant characters from text.
  5. extract_keyword_mapper: extract keywords from text, prompt is modified from lightRAG.
  6. extract_nickname_mapper: extract nicknames from the text.

Minor fix:

  1. add retry_num for parsing fail for LLM API calling.
  2. default model_params and sampling_params to be {}, since ** operator is invalid for None.

@BeachWang BeachWang self-assigned this Nov 11, 2024
@BeachWang BeachWang added documentation Improvements or additions to documentation dj:op issues/PRs about some specific OPs agent related to agent labels Nov 11, 2024
@drcege drcege requested a review from zhijianma November 12, 2024 03:31
@drcege drcege requested review from drcege and DavdGao November 13, 2024 04:07
@drcege drcege merged commit c279a3d into main Nov 15, 2024
3 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
agent related to agent dj:op issues/PRs about some specific OPs documentation Improvements or additions to documentation
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants