chore: remove langchain in tools (#3247)

api/core/tools/provider/builtin/arxiv/tools/arxiv_search.py

@@ -1,11 +1,92 @@
-from typing import Any
+import logging
+from typing import Any, Optional
 
-from langchain.utilities import ArxivAPIWrapper
+import arxiv
 from pydantic import BaseModel, Field
 
 from core.tools.entities.tool_entities import ToolInvokeMessage
 from core.tools.tool.builtin_tool import BuiltinTool
 
+logger = logging.getLogger(__name__)
+class ArxivAPIWrapper(BaseModel):
+    """Wrapper around ArxivAPI.
+
+    To use, you should have the ``arxiv`` python package installed.
+    https://lukasschwab.me/arxiv.py/index.html
+    This wrapper will use the Arxiv API to conduct searches and
+    fetch document summaries. By default, it will return the document summaries
+    of the top-k results.
+    It limits the Document content by doc_content_chars_max.
+    Set doc_content_chars_max=None if you don't want to limit the content size.
+
+    Args:
+        top_k_results: number of the top-scored document used for the arxiv tool
+        ARXIV_MAX_QUERY_LENGTH: the cut limit on the query used for the arxiv tool.
+        load_max_docs: a limit to the number of loaded documents
+        load_all_available_meta:
+            if True: the `metadata` of the loaded Documents contains all available
+            meta info (see https://lukasschwab.me/arxiv.py/index.html#Result),
+            if False: the `metadata` contains only the published date, title,
+            authors and summary.
+        doc_content_chars_max: an optional cut limit for the length of a document's
+            content
+
+    Example:
+        .. code-block:: python
+
+            arxiv = ArxivAPIWrapper(
+                top_k_results = 3,
+                ARXIV_MAX_QUERY_LENGTH = 300,
+                load_max_docs = 3,
+                load_all_available_meta = False,
+                doc_content_chars_max = 40000
+            )
+            arxiv.run("tree of thought llm)
+    """
+
+    arxiv_search = arxiv.Search  #: :meta private:
+    arxiv_exceptions = (
+        arxiv.ArxivError,
+        arxiv.UnexpectedEmptyPageError,
+        arxiv.HTTPError,
+    )  # :meta private:
+    top_k_results: int = 3
+    ARXIV_MAX_QUERY_LENGTH = 300
+    load_max_docs: int = 100
+    load_all_available_meta: bool = False
+    doc_content_chars_max: Optional[int] = 4000
+
+    def run(self, query: str) -> str:
+        """
+        Performs an arxiv search and A single string
+        with the publish date, title, authors, and summary
+        for each article separated by two newlines.
+
+        If an error occurs or no documents found, error text
+        is returned instead. Wrapper for
+        https://lukasschwab.me/arxiv.py/index.html#Search
+
+        Args:
+            query: a plaintext search query
+        """  # noqa: E501
+        try:
+            results = self.arxiv_search(  # type: ignore
+                query[: self.ARXIV_MAX_QUERY_LENGTH], max_results=self.top_k_results
+            ).results()
+        except self.arxiv_exceptions as ex:
+            return f"Arxiv exception: {ex}"
+        docs = [
+            f"Published: {result.updated.date()}\n"
+            f"Title: {result.title}\n"
+            f"Authors: {', '.join(a.name for a in result.authors)}\n"
+            f"Summary: {result.summary}"
+            for result in results
+        ]
+        if docs:
+            return "\n\n".join(docs)[: self.doc_content_chars_max]
+        else:
+            return "No good Arxiv Result was found"
+
 
 class ArxivSearchInput(BaseModel):
     query: str = Field(..., description="Search query.")