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

Suggest integrating AGE as a 'Graph Store' in LlamaIndex for AI/RAG applications #1783

Open
ztor2 opened this issue Apr 24, 2024 · 7 comments
Labels
enhancement New request

Comments

@ztor2
Copy link

ztor2 commented Apr 24, 2024

Since graph-based RAG frameworks have gained attention recently, I propose integrating AGE into AI development frameworks such as LangChain or LlamaIndex to increase AGE's utility in the AI industry.

Below are graph stores already registered with LlamaIndex's Graph Store.
https://docs.llamaindex.ai/en/stable/community/integrations/graph_stores/

I've already asked LlamaIndex for AGE integration and received the following response and template.
run-llama/llama_index#12517
run-llama/llama_index/blob/main/llama-index-core/llama_index/core/graph_stores/types.py

In addition, several dedicated contributors have listed Apache AGE on LangChain.
https://python.langchain.com/docs/integrations/graphs/apache_age/

I've been conducting test for integration, but I'm worried it might take a while.
I look forward to hearing your ideas, comments and suggestions for collaboration. thanks.

@ztor2 ztor2 added the enhancement New request label Apr 24, 2024
@markgomer
Copy link
Contributor

Surely integrating Apache AGE with these frameworks could enhance AGE's visibility in the AI sector, which could bring more contributors.

@ztor2
Copy link
Author

ztor2 commented Apr 25, 2024

@markgomer Thanks for you opinion. Existing graph stores included in these frameworks are commercial or difficult to use. AGE will be in high demand as a open source.

@ztor2
Copy link
Author

ztor2 commented Apr 29, 2024

to @eyab ,

I would like to propose to create a sub-project of 'Integrate AGE with open-source projects' for this issue.
For now, me and another contributor will be working on the project.
Here's a brief project description, referencing the project template:

Description

Integrating Apache AGE as a 'Graph Store' in LlamaIndex

Required Skills

  • Mainly Python
  • Some background and experience with RAG or LLM, and an understanding of LlamaIndex.

TODO

Main required attributes:

  • connect to graph stores
  • ETL of triplet information from graph databases(get, get_rel_map, upsert, etc.)
  • save graph information as file(by using fsspec)
  • get schema of graph stores

Additional Details

https://docs.llamaindex.ai/en/stable/community/integrations/graph_stores/
run-llama/llama_index#12517
https://github.com/run-llama/llama_index/blob/main/llama-index-core/llama_index/core/graph_stores/types.py
https://python.langchain.com/docs/integrations/graphs/apache_age/

@eyab
Copy link
Member

eyab commented May 6, 2024

@ztor2

Thank you for proposing to integrate Apache AGE with LlamaIndex. Your suggestion sounds like a valuable addition to our project, and I am excited to see how it develops.

I have created a designated space for you to work on the project.
https://github.com/orgs/apache/projects/357

@ztor2
Copy link
Author

ztor2 commented May 8, 2024

@eyab

Thank you for your response and for creating the project.
I will soon discuss and comment on the assignment for each task with the volunteer contributor.

@dsvisualized
Copy link

I'm excited about this project and would love to contribute. I'm a database engineer with experience in python. Let me know which tasks I can assist with or in general how I can help.

@ztor2
Copy link
Author

ztor2 commented May 11, 2024

@eyab

Please refer to previous comment, and can you assign me( @ztor2 ) to task 1 and @dsvisualized to task 2 in the project each?
https://github.com/orgs/apache/projects/357

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New request
Projects
None yet
Development

No branches or pull requests

4 participants