Feat: CSV Url Knowledgebase

phi/document/reader/csv_reader.py

@@ -48,3 +48,21 @@ def read(self, file: Union[Path, IO[Any]], delimiter: str = ",", quotechar: str
         except Exception as e:
             logger.error(f"Error reading: {file.name if isinstance(file, IO) else file}: {e}")
             return []
+
+
+class CSVUrlReader(Reader):
+    """Reader for CSV files"""
+
+    def read(self, url: str) -> List[Document]:
+        if not url:
+            raise ValueError("No URL provided")
+
+        try:
+            import httpx
+        except ImportError:
+            raise ImportError("`httpx` not installed")
+
+        logger.info(f"Reading: {url}")
+        response = httpx.get(url)
+
+        return CSVReader().read(file=io.StringIO(response.text))

phi/knowledge/csv.py

@@ -2,7 +2,7 @@
 from typing import Union, List, Iterator
 
 from phi.document import Document
-from phi.document.reader.csv_reader import CSVReader
+from phi.document.reader.csv_reader import CSVReader, CSVUrlReader
 from phi.knowledge.agent import AgentKnowledge
 
 
@@ -26,3 +26,13 @@ def document_lists(self) -> Iterator[List[Document]]:
                 yield self.reader.read(file=_csv)
         elif _csv_path.exists() and _csv_path.is_file() and _csv_path.suffix == ".csv":
             yield self.reader.read(file=_csv_path)
+
+
+class CSVUrlKnowledgeBase(AgentKnowledge):
+    url: List[str]
+    reader: CSVUrlReader = CSVUrlReader()
+
+    @property
+    def document_lists(self) -> Iterator[List[Document]]:
+        for url in self.url:
+            yield self.reader.read(url=url)