Add SubgraphRAG model and example #10000
Draft
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
for more information, see https://pre-commit.ci
Kh4L
force-pushed
the
add_subgraphrag
branch
from
7bb45bf to
caf7d7a
Compare
puririshi98
requested changes
Feb 28, 2025
| @@ -264,11 +494,17 @@ class WebQSPDataset(KGQABaseDataset): | |||
| (default: :obj:`False`) | |||
| use_pcst (bool, optional): Whether to preprocess the dataset's graph | |||
| with PCST or return the full graphs. (default: :obj:`True`) | |||
| subgraphrag (bool, optional): Whether to preprocess the dataset | |||
| into the format expected by SubgraphRAG. The dataset the full | |||
There was a problem hiding this comment.
"The dataset the full..." needs a rewrite
| @@ -285,8 +521,14 @@ class CWQDataset(KGQABaseDataset): | |||
| (default: :obj:`False`) | |||
| use_pcst (bool, optional): Whether to preprocess the dataset's graph | |||
| with PCST or return the full graphs. (default: :obj:`True`) | |||
| subgraphrag (bool, optional): Whether to preprocess the dataset | |||
| into the format expected by SubgraphRAG. The dataset the full | |||
|
|
||
|
|
||
| def reason(pred_dict, model_name, K_triplets, max_tokens=4096): | ||
| llm = LLM(model_name=model_name, backend='openai') |
There was a problem hiding this comment.
needs NIM api key passed, probs pass in through argparser
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR adds a E2E implementation of Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation
Reproducing
to add
Results
Metrics with
topk=100andmodel_name=meta-llama/Llama-3.1-8BAblation study, no triplets (question only):
Hit@1: 0.3547Bigger LLM (
meta-llama/Llama-3.1-70B-Instruct) doesn't improve the hit rate:Hit@1: 0.7608