feat: add support for arxiv identifier in ArxivAPIWrapper() #9318
Conversation
ArxivAPIWrapper
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎ 1 Ignored Deployment
|
dosubot
bot
added
the
🤖:improvement
|
lgtm, cc @leo-gan |
|
I've tried I don't think we need special treatment for multiple paper IDs because it works right now. |
|
Hi, If the version number is specified in the query (e.g. 2212.00794v2), no results will be returned. So I think there is a need to handle the arxiv identifier separately. |
OK. Then, please add unit tests to work with Ids. |
|
Hi @leo-gan, I've committed new unit tests. You can check that |
| @@ -54,6 +58,14 @@ class ArxivAPIWrapper(BaseModel): | |||
| load_all_available_meta: bool = False | |||
| doc_content_chars_max: Optional[int] = 4000 | |||
|
|
|||
| def is_arxiv_identifier(self, query: str) -> bool: | |||
There was a problem hiding this comment.
could we add a few simple unit tests for this method
There was a problem hiding this comment.
sure, I will add it soon
There was a problem hiding this comment.
@LMC117 Looks great! LGTM
|
thanks @LMC117! |
baskaryan
added
the
lgtm
|
@LMC117 Hi , could you, please, resolve the merging issues? After that ping me and I push this PR for the review. Thanks! |
|
@leo-gan hi I resolved that the merging issue |
| ).results() | ||
| if self.is_arxiv_identifier(query): | ||
| results = self.arxiv_search( | ||
| id_list=query[: self.ARXIV_MAX_QUERY_LENGTH].split(), |
There was a problem hiding this comment.
i think we dont want to do self.ARXIV_MAX_QUERY_LENGTH right?
…n-ai#9318) - Description: this PR adds the support for arxiv identifier of the ArxivAPIWrapper. I modified the `run()` and `load()` functions in `arxiv.py`, using regex to recognize if the query is in the form of arxiv identifier (see [https://info.arxiv.org/help/find/index.html](https://info.arxiv.org/help/find/index.html)). If so, it will directly search the paper corresponding to the arxiv identifier. I also modified and added tests in `test_arxiv.py`. - Issue: langchain-ai#9047 - Dependencies: N/A - Tag maintainer: N/A --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
run()andload()functions inarxiv.py, using regex to recognize if the query is in the form of arxiv identifier (see https://info.arxiv.org/help/find/index.html). If so, it will directly search the paper corresponding to the arxiv identifier. I also modified and added tests intest_arxiv.py.