Introduced a simple demo of mixed index and text2gremlin demonstration.

[vichayturen]

Main changes:

1. Modified the configuration method.
2. Added vector index for RAG, supported mixed-retrieving and reranking.
3. Introduced embedding configuration.
4. Introduced index operation and document operation.
5. Added task of transferring natural language to gremlin and its demonstration.
6. Simplified the use and modify the usage in README.

---

TODOs (add them later) 🔢

• [ ] connection check (GraphDB & LLM Server)
  • [x] openai check
  • [ ] qianfan/wenxin check (use auth-api?)
  • [ ] local llm check
• [x] graph error handle
  • [x] print request & response url + body in py-client
  • [x] wrapper some exception (don't throw Error detail directly)
• [x] fix github security alert
• [x] radio (Selection)
• [x] configs improvement (remove duplicate items)
• [x] support uploading file in UI (text type)
• [x] allow users to modify prompt template (BASIC)
• [x] add a one-click graph clean button? (use clear api) ... (check the latest doc)

[imbajin]

Now we could use log.xx(msg) to print the log: ↓

[ChenZiHong-Gavin]

Now the .config file instead of json file can be generated with command like python -m hugegraph_llm.config.generate --dir_path=./