tangger/Search-R1
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update features

Browse Source
This commit is contained in:
PeterGriffinJin
2025-04-07 18:28:05 +00:00
parent 5eccb5fa14
commit bfc61e90fa
1 changed files with 7 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
README.md
View File

@@ -20,6 +20,7 @@ You can refer to this [link](https://github.com/PeterGriffinJin/Search-R1/tree/m
- [Inference](#inference) - [Inference](#inference)
- [Use your own dataset](#use-your-own-dataset) - [Use your own dataset](#use-your-own-dataset)
- [Use your own search engine](#use-your-own-search-engine) - [Use your own search engine](#use-your-own-search-engine)
- [Features](#features)
- [Ackowledge](#acknowledge) - [Ackowledge](#acknowledge)
- [Citations](#citations) - [Citations](#citations)
@@ -171,11 +172,13 @@ The LLM can call the search engine by calling the search API (e.g., "http://127.
You can refer to ```search_r1/search/retriever_server.py``` for an example of launching a local retriever server. You can refer to ```search_r1/search/retriever_server.py``` for an example of launching a local retriever server.
## To do ## Features
- Support local sparse retrievers (e.g., BM25). ✔️
- Support local dense retrievers (both flat indexing and ANN indexing) ✔️
- Support google search / bing search / brave search API and others. ✔️ - Support google search / bing search / brave search API and others. ✔️
- Support LoRA tuning. - Support off-the-shelf neural rerankers.
- Support supervised finetuning. - Support different RL methods (e.g., PPO, GRPO, reinforce). ✔️
- Support off-the-shelf rerankers. - Support different LLMs (e.g., llama3, Qwen2.5, etc). ✔️
## Acknowledge ## Acknowledge