TXT2KG w/ hotpot_qa.pyGraph Retrieval Example and tech_qa.py HybridRAG e2e workflow example
#9992
Conversation
for more information, see https://pre-commit.ci
…eometric into rebase-txt2kg
for more information, see https://pre-commit.ci
…eometric into rebase-txt2kg
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
…eometric into rebase-txt2kg
for more information, see https://pre-commit.ci
…eometric into rebase-txt2kg
Co-authored-by: riship <[email protected]>
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
|
@rusty1s @akihironitta this is mostly ready for review, except i need to cleanup for the CI linters, but any early reviews would help getting this merged once those cleanups are done. |
puririshi98
changed the title
TXT2KG w/ hotpot_qa.pyGraph Retrieval Example and tech_qa.py HybridRAG e2e workflow exampleTXT2KG w/ hotpot_qa.pyGraph Retrieval Example and tech_qa.py HybridRAG e2e workflow example
for more information, see https://pre-commit.ci
| # We use NIMs since most PyG users may not be able to run a 70B+ model | ||
| from openai import OpenAI | ||
| global CLIENT | ||
| CLIENT = OpenAI(base_url="https://integrate.api.nvidia.com/v1", |
There was a problem hiding this comment.
Would be nice to expose base_url through argparse
There was a problem hiding this comment.
i agree, could you submit a PR into my branch that does this for txt2kg and llmjudge and tests it out with some openAI model(s) and icnlude the results in the PR description. would be cool to see how nemotron70b compares to using any openAI model(s) you choose. i dont have an openai api account set up so this would be great help and good benchmark. Zack will also be submitting PRs to my branch so we will all just be co-authors of this super PR which i'll push through after a few PRs from zack and this one from you
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
Co-authored-by: riship <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
https://pytorch-geometric--9992.org.readthedocs.build/en/9992/modules/nn.html?highlight=txt2kg#torch_geometric.nn.nlp.TXT2KG
TXT2kg docs before their merged into main^