community: refactor Arxiv search logic (#27084)

PR message:

Description:
This PR refactors the Arxiv API wrapper by extracting the Arxiv search
logic into a helper function (_fetch_results) to reduce code duplication
and improve maintainability. The helper function is used in methods like
get_summaries_as_docs, run, and lazy_load, streamlining the code and
making it easier to maintain in the future.

Issue:
This is a minor refactor, so no specific issue is being fixed.

Dependencies:
No new dependencies are introduced with this change.

Add tests and docs:
No new integrations were added, so no additional tests or docs are
necessary for this PR.
Lint and test:
I have run make format, make lint, and make test to ensure all checks
pass successfully.

---------

Co-authored-by: Erick Friis <erick@langchain.dev>

libs/community/langchain_community/utilities/arxiv.py

@@ -94,6 +94,16 @@ class ArxivAPIWrapper(BaseModel):
             )
         return values
 
+    def _fetch_results(self, query: str) -> Any:
+        """Helper function to fetch arxiv results based on query."""
+        if self.is_arxiv_identifier(query):
+            return self.arxiv_search(
+                id_list=query.split(), max_results=self.top_k_results
+            ).results()
+        return self.arxiv_search(
+            query[: self.ARXIV_MAX_QUERY_LENGTH], max_results=self.top_k_results
+        ).results()
+
     def get_summaries_as_docs(self, query: str) -> List[Document]:
         """
         Performs an arxiv search and returns list of
@@ -107,16 +117,11 @@ class ArxivAPIWrapper(BaseModel):
             query: a plaintext search query
         """
         try:
-            if self.is_arxiv_identifier(query):
-                results = self.arxiv_search(
-                    id_list=query.split(),
-                    max_results=self.top_k_results,
-                ).results()
-            else:
-                results = self.arxiv_search(  # type: ignore
-                    query[: self.ARXIV_MAX_QUERY_LENGTH], max_results=self.top_k_results
-                ).results()
+            results = self._fetch_results(
+                query
+            )  # Using helper function to fetch results
         except self.arxiv_exceptions as ex:
+            logger.error(f"Arxiv exception: {ex}")  # Added error logging
             return [Document(page_content=f"Arxiv exception: {ex}")]
         docs = [
             Document(
@@ -146,16 +151,11 @@ class ArxivAPIWrapper(BaseModel):
             query: a plaintext search query
         """
         try:
-            if self.is_arxiv_identifier(query):
-                results = self.arxiv_search(
-                    id_list=query.split(),
-                    max_results=self.top_k_results,
-                ).results()
-            else:
-                results = self.arxiv_search(  # type: ignore
-                    query[: self.ARXIV_MAX_QUERY_LENGTH], max_results=self.top_k_results
-                ).results()
+            results = self._fetch_results(
+                query
+            )  # Using helper function to fetch results
         except self.arxiv_exceptions as ex:
+            logger.error(f"Arxiv exception: {ex}")  # Added error logging
             return f"Arxiv exception: {ex}"
         docs = [
             f"Published: {result.updated.date()}\n"
@@ -208,15 +208,9 @@ class ArxivAPIWrapper(BaseModel):
         try:
             # Remove the ":" and "-" from the query, as they can cause search problems
             query = query.replace(":", "").replace("-", "")
-            if self.is_arxiv_identifier(query):
-                results = self.arxiv_search(
-                    id_list=query[: self.ARXIV_MAX_QUERY_LENGTH].split(),
-                    max_results=self.load_max_docs,
-                ).results()
-            else:
-                results = self.arxiv_search(  # type: ignore
-                    query[: self.ARXIV_MAX_QUERY_LENGTH], max_results=self.load_max_docs
-                ).results()
+            results = self._fetch_results(
+                query
+            )  # Using helper function to fetch results
         except self.arxiv_exceptions as ex:
             logger.debug("Error on arxiv: %s", ex)
             return