imbajin commented on issue #183: URL: https://github.com/apache/incubator-hugegraph-ai/issues/183#issuecomment-2690318285
> [@Aryankb](https://github.com/Aryankb?rgh-link-date=2025-02-28T07%3A12%3A17.000Z) I think most of the people won't be proficient enough to write their own queries I have worked quite a bit with graph rag in my intern and at first even I had a bit trouble in writing those. So, I would suggest that we can get a description for the knowledge that the user will be providing us if they don't, we will by default use a LLM to get what the knowledge or text is about and then make an agent write the query for us and use that query ? [@imbajin](https://github.com/imbajin?rgh-link-date=2025-02-28T07%3A12%3A17.000Z) sir what is your opinion on this? @chiruu12 @Aryankb First, regarding the `text2gql` part, it is an independent matter, and I understand that it is not strongly related to the selection of agentic frame or workflow impl. Here is a brief description of the actual situation. Our implementation and approach earlier was to use both model fine-tuning and **user templates** simultaneously. (see it ↓ By default, we use the GQL query template to optimize the effect of text2gql.) <img width="1610" alt="Image" src="https://github.com/user-attachments/assets/fc278898-4cbf-46b4-8d4d-90dcf0e7df6d"; /> General encoder model fine-tuning for `7-14B` can be a significant task, especially when it comes to how to generate GQL corpus (HG uses Gremlin queries by default and is compatible with most of the Cypher syntax), refer [wiki](https://github.com/apache/incubator-hugegraph-ai/wiki/HugeGraph-LLM-Roadmap#4-graph-query-core-1) to get more context -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
