agno 2.3.15__py3-none-any.whl → 2.3.16__py3-none-any.whl

agno/knowledge/reader/csv_reader.py

@@ -47,17 +47,16 @@ class CSVReader(Reader):
                 if not file.exists():
                     raise FileNotFoundError(f"Could not find file: {file}")
                 log_debug(f"Reading: {file}")
-                file_content = file.open(newline="", mode="r", encoding=self.encoding or "utf-8")
+                csv_name = name or file.stem
+                file_content: Union[io.TextIOWrapper, io.StringIO] = file.open(
+                    newline="", mode="r", encoding=self.encoding or "utf-8"
+                )
             else:
-                log_debug(f"Reading retrieved file: {name or file.name}")
+                log_debug(f"Reading retrieved file: {getattr(file, 'name', 'BytesIO')}")
+                csv_name = name or getattr(file, "name", "csv_file").split(".")[0]
                 file.seek(0)
-                file_content = io.StringIO(file.read().decode("utf-8"))  # type: ignore
+                file_content = io.StringIO(file.read().decode("utf-8"))
 
-            csv_name = name or (
-                Path(file.name).stem
-                if isinstance(file, Path)
-                else (getattr(file, "name", "csv_file").split(".")[0] if hasattr(file, "name") else "csv_file")
-            )
             csv_content = ""
             with file_content as csvfile:
                 csv_reader = csv.reader(csvfile, delimiter=delimiter, quotechar=quotechar)
@@ -109,16 +108,12 @@ class CSVReader(Reader):
                 async with aiofiles.open(file, mode="r", encoding="utf-8", newline="") as file_content:
                     content = await file_content.read()
                     file_content_io = io.StringIO(content)
+                csv_name = name or file.stem
             else:
                 log_debug(f"Reading retrieved file async: {getattr(file, 'name', 'BytesIO')}")
                 file.seek(0)
                 file_content_io = io.StringIO(file.read().decode("utf-8"))
-
-            csv_name = name or (
-                Path(file.name).stem
-                if isinstance(file, Path)
-                else (getattr(file, "name", "csv_file").split(".")[0] if hasattr(file, "name") else "csv_file")
-            )
+                csv_name = name or getattr(file, "name", "csv_file").split(".")[0]
 
             file_content_io.seek(0)
             csv_reader = csv.reader(file_content_io, delimiter=delimiter, quotechar=quotechar)
@@ -161,4 +156,4 @@ class CSVReader(Reader):
             return documents
         except Exception as e:
             log_error(f"Error reading async: {getattr(file, 'name', str(file)) if isinstance(file, IO) else file}: {e}")
-            return []
+            return []

agno/knowledge/reader/docx_reader.py

@@ -47,11 +47,9 @@ class DocxReader(Reader):
                 docx_document = DocxDocument(str(file))
                 doc_name = name or file.stem
             else:
-                log_debug(f"Reading uploaded file: {getattr(file, 'name', 'docx_file')}")
+                log_debug(f"Reading uploaded file: {getattr(file, 'name', 'BytesIO')}")
                 docx_document = DocxDocument(file)
-                doc_name = name or (
-                    getattr(file, "name", "docx_file").split(".")[0] if hasattr(file, "name") else "docx_file"
-                )
+                doc_name = name or getattr(file, "name", "docx_file").split(".")[0]
 
             doc_content = "\n\n".join([para.text for para in docx_document.paragraphs])
 

agno/knowledge/reader/field_labeled_csv_reader.py

@@ -106,17 +106,15 @@ class FieldLabeledCSVReader(Reader):
                 if not file.exists():
                     raise FileNotFoundError(f"Could not find file: {file}")
                 log_debug(f"Reading: {file}")
-                file_content = file.open(newline="", mode="r", encoding=self.encoding or "utf-8")
+                csv_name = name or file.stem
+                file_content: Union[io.TextIOWrapper, io.StringIO] = file.open(
+                    newline="", mode="r", encoding=self.encoding or "utf-8"
+                )
             else:
-                log_debug(f"Reading retrieved file: {name or file.name}")
+                log_debug(f"Reading retrieved file: {getattr(file, 'name', 'BytesIO')}")
+                csv_name = name or getattr(file, "name", "csv_file").split(".")[0]
                 file.seek(0)
-                file_content = io.StringIO(file.read().decode("utf-8"))  # type: ignore
-
-            csv_name = name or (
-                Path(file.name).stem
-                if isinstance(file, Path)
-                else (getattr(file, "name", "csv_file").split(".")[0] if hasattr(file, "name") else "csv_file")
-            )
+                file_content = io.StringIO(file.read().decode("utf-8"))
 
             documents = []
 
@@ -189,16 +187,12 @@ class FieldLabeledCSVReader(Reader):
                 async with aiofiles.open(file, mode="r", encoding=self.encoding or "utf-8", newline="") as file_content:
                     content = await file_content.read()
                     file_content_io = io.StringIO(content)
+                csv_name = name or file.stem
             else:
-                log_debug(f"Reading retrieved file async: {name or file.name}")
+                log_debug(f"Reading retrieved file async: {getattr(file, 'name', 'BytesIO')}")
+                csv_name = name or getattr(file, "name", "csv_file").split(".")[0]
                 file.seek(0)
-                file_content_io = io.StringIO(file.read().decode("utf-8"))  # type: ignore
-
-            csv_name = name or (
-                Path(file.name).stem
-                if isinstance(file, Path)
-                else (getattr(file, "name", "csv_file").split(".")[0] if hasattr(file, "name") else "csv_file")
-            )
+                file_content_io = io.StringIO(file.read().decode("utf-8"))
 
             file_content_io.seek(0)
             csv_reader = csv.reader(file_content_io, delimiter=delimiter, quotechar=quotechar)
@@ -287,4 +281,4 @@ class FieldLabeledCSVReader(Reader):
 
         except Exception as e:
             log_error(f"Error reading async: {getattr(file, 'name', str(file)) if isinstance(file, IO) else file}: {e}")
-            return []
+            return []

agno/knowledge/reader/json_reader.py

@@ -1,6 +1,5 @@
 import asyncio
 import json
-from io import BytesIO
 from pathlib import Path
 from typing import IO, Any, List, Optional, Union
 from uuid import uuid4
@@ -42,17 +41,15 @@ class JSONReader(Reader):
                 if not path.exists():
                     raise FileNotFoundError(f"Could not find file: {path}")
                 log_debug(f"Reading: {path}")
-                json_name = name or path.name.split(".")[0]
-                json_contents = json.loads(path.read_text(self.encoding or "utf-8"))
-
-            elif isinstance(path, BytesIO):
-                json_name = name or path.name.split(".")[0]
-                log_debug(f"Reading uploaded file: {json_name}")
+                json_name = name or path.stem
+                json_contents = json.loads(path.read_text(encoding=self.encoding or "utf-8"))
+            elif hasattr(path, "seek") and hasattr(path, "read"):
+                log_debug(f"Reading uploaded file: {getattr(path, 'name', 'BytesIO')}")
+                json_name = name or getattr(path, "name", "json_file").split(".")[0]
                 path.seek(0)
                 json_contents = json.load(path)
-
             else:
-                raise ValueError("Unsupported file type. Must be Path or BytesIO.")
+                raise ValueError("Unsupported file type. Must be Path or file-like object.")
 
             if isinstance(json_contents, dict):
                 json_contents = [json_contents]
@@ -72,17 +69,12 @@ class JSONReader(Reader):
                     chunked_documents.extend(self.chunk_document(document))
                 return chunked_documents
             return documents
+        except (FileNotFoundError, ValueError, json.JSONDecodeError):
+            raise
         except Exception as e:
             log_error(f"Error reading: {path}: {e}")
             raise
 
     async def async_read(self, path: Union[Path, IO[Any]], name: Optional[str] = None) -> List[Document]:
-        """Asynchronously read JSON files.
-
-        Args:
-            path (Union[Path, IO[Any]]): Path to a JSON file or a file-like object
-
-        Returns:
-            List[Document]: List of documents from the JSON file
-        """
-        return await asyncio.to_thread(self.read, path, name)
+        """Asynchronously read JSON files."""
+        return await asyncio.to_thread(self.read, path, name)

agno/knowledge/reader/markdown_reader.py

@@ -69,8 +69,8 @@ class MarkdownReader(Reader):
                 file_name = name or file.stem
                 file_contents = file.read_text(encoding=self.encoding or "utf-8")
             else:
-                log_debug(f"Reading uploaded file: {file.name}")
-                file_name = name or file.name.split(".")[0]
+                log_debug(f"Reading uploaded file: {getattr(file, 'name', 'BytesIO')}")
+                file_name = name or getattr(file, "name", "file").split(".")[0]
                 file.seek(0)
                 file_contents = file.read().decode(self.encoding or "utf-8")
 
@@ -101,16 +101,16 @@ class MarkdownReader(Reader):
                         file_contents = await f.read()
                 except ImportError:
                     log_warning("aiofiles not installed, using synchronous file I/O")
-                    file_contents = file.read_text(self.encoding or "utf-8")
+                    file_contents = file.read_text(encoding=self.encoding or "utf-8")
             else:
-                log_debug(f"Reading uploaded file asynchronously: {file.name}")
-                file_name = name or file.name.split(".")[0]
+                log_debug(f"Reading uploaded file asynchronously: {getattr(file, 'name', 'BytesIO')}")
+                file_name = name or getattr(file, "name", "file").split(".")[0]
                 file.seek(0)
                 file_contents = file.read().decode(self.encoding or "utf-8")
 
             document = Document(
                 name=file_name,
-                id=str(uuid.uuid4()),  # Fixed an issue with the id creation
+                id=str(uuid.uuid4()),
                 content=file_contents,
             )
 

agno/knowledge/reader/pdf_reader.py

@@ -218,16 +218,13 @@ class BasePDFReader(Reader):
 
     def _get_doc_name(self, pdf_source: Union[str, Path, IO[Any]], name: Optional[str] = None) -> str:
         """Determines the document name from the source or a provided name."""
-        try:
-            if name:
-                return name
-            if isinstance(pdf_source, str):
-                return pdf_source.split("/")[-1].split(".")[0].replace(" ", "_")
-            # Assumes a file-like object with a .name attribute
-            return pdf_source.name.split(".")[0]
-        except Exception:
-            # The original code had a bug here, it should check `name` first.
-            return name or "pdf"
+        if name:
+            return name
+        if isinstance(pdf_source, str):
+            return Path(pdf_source).stem.replace(" ", "_")
+        if isinstance(pdf_source, Path):
+            return pdf_source.stem.replace(" ", "_")
+        return getattr(pdf_source, "name", "pdf_file").split(".")[0].replace(" ", "_")
 
     def _decrypt_pdf(self, doc_reader: DocumentReader, doc_name: str, password: Optional[str] = None) -> bool:
         if not doc_reader.is_encrypted:
@@ -341,8 +338,14 @@ class PDFReader(BasePDFReader):
         return [ContentType.PDF]
 
     def read(
-        self, pdf: Union[str, Path, IO[Any]], name: Optional[str] = None, password: Optional[str] = None
+        self,
+        pdf: Optional[Union[str, Path, IO[Any]]] = None,
+        name: Optional[str] = None,
+        password: Optional[str] = None,
     ) -> List[Document]:
+        if pdf is None:
+            log_error("No pdf provided")
+            return []
         doc_name = self._get_doc_name(pdf, name)
         log_debug(f"Reading: {doc_name}")
 

agno/knowledge/reader/pptx_reader.py

@@ -47,11 +47,9 @@ class PPTXReader(Reader):
                 presentation = Presentation(str(file))
                 doc_name = name or file.stem
             else:
-                log_debug(f"Reading uploaded file: {getattr(file, 'name', 'pptx_file')}")
+                log_debug(f"Reading uploaded file: {getattr(file, 'name', 'BytesIO')}")
                 presentation = Presentation(file)
-                doc_name = name or (
-                    getattr(file, "name", "pptx_file").split(".")[0] if hasattr(file, "name") else "pptx_file"
-                )
+                doc_name = name or getattr(file, "name", "pptx_file").split(".")[0]
 
             # Extract text from all slides
             slide_texts = []

agno/knowledge/reader/s3_reader.py

@@ -53,29 +53,20 @@ class S3Reader(Reader):
         try:
             log_debug(f"Reading S3 file: {s3_object.uri}")
 
+            doc_name = name or s3_object.name.split("/")[-1].split(".")[0].replace("/", "_").replace(" ", "_")
+
             # Read PDF files
             if s3_object.uri.endswith(".pdf"):
                 object_resource = s3_object.get_resource()
                 object_body = object_resource.get()["Body"]
-                doc_name = (
-                    s3_object.name.split("/")[-1].split(".")[0].replace("/", "_").replace(" ", "_")
-                    if name is None
-                    else name
-                )
                 return PDFReader().read(pdf=BytesIO(object_body.read()), name=doc_name)
 
             # Read text files
             else:
-                doc_name = (
-                    s3_object.name.split("/")[-1].split(".")[0].replace("/", "_").replace(" ", "_")
-                    if name is None
-                    else name
-                )
                 obj_name = s3_object.name.split("/")[-1]
                 temporary_file = Path("storage").joinpath(obj_name)
                 s3_object.download(temporary_file)
                 documents = TextReader().read(file=temporary_file, name=doc_name)
-
                 temporary_file.unlink()
                 return documents
 

agno/knowledge/reader/text_reader.py

@@ -39,16 +39,10 @@ class TextReader(Reader):
                     raise FileNotFoundError(f"Could not find file: {file}")
                 log_debug(f"Reading: {file}")
                 file_name = name or file.stem
-                file_contents = file.read_text(self.encoding or "utf-8")
+                file_contents = file.read_text(encoding=self.encoding or "utf-8")
             else:
-                # Handle BytesIO and other file-like objects that may not have a name attribute
-                if name:
-                    file_name = name
-                elif hasattr(file, "name") and file.name is not None:
-                    file_name = file.name.split(".")[0]
-                else:
-                    file_name = "text_file"
-                log_debug(f"Reading uploaded file: {file_name}")
+                log_debug(f"Reading uploaded file: {getattr(file, 'name', 'BytesIO')}")
+                file_name = name or getattr(file, "name", "text_file").split(".")[0]
                 file.seek(0)
                 file_contents = file.read().decode(self.encoding or "utf-8")
 
@@ -85,16 +79,10 @@ class TextReader(Reader):
                         file_contents = await f.read()
                 except ImportError:
                     log_warning("aiofiles not installed, using synchronous file I/O")
-                    file_contents = file.read_text(self.encoding or "utf-8")
+                    file_contents = file.read_text(encoding=self.encoding or "utf-8")
             else:
-                # Handle BytesIO and other file-like objects that may not have a name attribute
-                if name:
-                    file_name = name
-                elif hasattr(file, "name") and file.name is not None:
-                    file_name = file.name.split(".")[0]
-                else:
-                    file_name = "text_file"
-                log_debug(f"Reading uploaded file asynchronously: {file_name}")
+                log_debug(f"Reading uploaded file asynchronously: {getattr(file, 'name', 'BytesIO')}")
+                file_name = name or getattr(file, "name", "text_file").split(".")[0]
                 file.seek(0)
                 file_contents = file.read().decode(self.encoding or "utf-8")
 

agno/knowledge/reader/web_search_reader.py

@@ -263,21 +263,17 @@ class WebSearchReader(Reader):
 
         log_debug(f"Starting async web search reader for query: {query}")
 
-        # Perform web search (synchronous operation)
         search_results = self._perform_web_search(query)
         if not search_results:
             logger.warning(f"No search results found for query: {query}")
             return []
 
-        # Create tasks for fetching content from each URL
         async def fetch_url_async(result: Dict[str, str]) -> Optional[Document]:
             url = result.get("url", "")
 
-            # Skip if URL is invalid or already visited
             if not self._is_valid_url(url):
                 return None
 
-            # Mark URL as visited
             self._visited_urls.add(url)
 
             try:
@@ -292,32 +288,25 @@ class WebSearchReader(Reader):
                     else:
                         content = response.text
 
-                    document = self._create_document_from_url(url, content, result)
-                    return document
+                    return self._create_document_from_url(url, content, result)
 
             except Exception as e:
                 logger.warning(f"Error fetching {url}: {e}")
                 return None
 
-        # Create tasks for all URLs
-        tasks = [fetch_url_async(result) for result in search_results]
-
-        # Execute all tasks concurrently with delays
         documents = []
-        for i, task in enumerate(tasks):
-            if i > 0:  # Add delay between requests (except for the first one)
+        for i, result in enumerate(search_results):
+            if i > 0:
                 await asyncio.sleep(self.delay_between_requests)
 
-            doc = await task
+            doc = await fetch_url_async(result)
             if doc is not None:
-                # Apply chunking if enabled
                 if self.chunk:
                     chunked_docs = await self.chunk_documents_async([doc])
                     documents.extend(chunked_docs)
                 else:
                     documents.append(doc)
 
-                # Stop if we've reached max_results
                 if len(documents) >= self.max_results:
                     break
 

{agno-2.3.15.dist-info → agno-2.3.16.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agno
-Version: 2.3.15
+Version: 2.3.16
 Summary: Agno: a lightweight library for building Multi-Agent Systems
 Author-email: Ashpreet Bedi <ashpreet@agno.com>
 Project-URL: homepage, https://agno.com

{agno-2.3.15.dist-info → agno-2.3.16.dist-info}/RECORD

@@ -154,19 +154,19 @@ agno/knowledge/embedder/voyageai.py,sha256=E6RjQRaa5d2BHmkW09QG68ncrgBV2Vqq25ZR8
 agno/knowledge/reader/__init__.py,sha256=edjnCwyDjM9Q5JPMi4K9mll8a3CdV52iagUKAgGiaas,159
 agno/knowledge/reader/arxiv_reader.py,sha256=PtqP3bB4eZAYUlK9_ytPCFiy4icvMj7bIZNNVlBgY6U,2735
 agno/knowledge/reader/base.py,sha256=GLfOoy0W7rv8fgjVRUpVmInRgFFvFrPVsok_iJ9aSQ0,3780
-agno/knowledge/reader/csv_reader.py,sha256=aCGhFKTkSy4UJFFpPAWNot-9r0_n_2M2oucELaEOV9I,6468
-agno/knowledge/reader/docx_reader.py,sha256=edtri5z4PcdiVgjupxbmLmGnsMkvjFFAcnqOrZmWthU,3308
-agno/knowledge/reader/field_labeled_csv_reader.py,sha256=yVdfFGTkb7bhM3cpEukgeANu6UB2yrjU7T3BfWlXv0k,11605
+agno/knowledge/reader/csv_reader.py,sha256=I_6Sczz4mvgXinkhHuzUAn33CARATx3DWJxliQThHPU,6321
+agno/knowledge/reader/docx_reader.py,sha256=X6N0XSCP9g1YQ1FQ9l_fwib0AqK1TVEDC1nULs3W4KM,3224
+agno/knowledge/reader/field_labeled_csv_reader.py,sha256=Y8pKgQz6yoMv1mhgfAIsrO-co21K_pu4YvZg1_GEAl0,11456
 agno/knowledge/reader/firecrawl_reader.py,sha256=SCbcRLkMrUb2WiC6SPuAoZULtHITa2VAmBtZlGmamGM,6855
-agno/knowledge/reader/json_reader.py,sha256=mh_SZE7jPaDO5KleFM0X7LsrYCSTimQ7qbvqh2YR8RE,3317
-agno/knowledge/reader/markdown_reader.py,sha256=QDg9oZTTRZkXf7D8eFrZ12t5gfXd5KWmJeH43HqNCHo,5284
-agno/knowledge/reader/pdf_reader.py,sha256=utUJiXhS9SXSZfsDg5dOo5Fr1PS8ODtOA5exTcS6LbY,17187
-agno/knowledge/reader/pptx_reader.py,sha256=_UQZlDf8XtA62uwYDqlJcU7X-KQ00lu4ZevXDCPnZ6k,3929
+agno/knowledge/reader/json_reader.py,sha256=waMaL1V9X-8SzLmmqR14MRyPxzoerA9G5rTMTkvx0xc,3263
+agno/knowledge/reader/markdown_reader.py,sha256=jvmeuRCfwI4eakMBB1MwVasfc7-FsKdXmbANmlfiLB0,5340
+agno/knowledge/reader/pdf_reader.py,sha256=hETLLyy_pk2qIaMj4hqSyN_o22cO4v_pVr2XdoHSb-M,17200
+agno/knowledge/reader/pptx_reader.py,sha256=yokphgHFZCGl_0XPEUmf6g5kJJq2wd015PooeEx9WpY,3845
 agno/knowledge/reader/reader_factory.py,sha256=1VGnZ4lpGiwa45dqfOyXmVB1dGb_4tOXpsKN9Vaqazs,11408
-agno/knowledge/reader/s3_reader.py,sha256=8tBUGw586m72FQReMux0iJoz8FhhLjpH5lxYamEilHk,3549
+agno/knowledge/reader/s3_reader.py,sha256=3rB5PtCjYIck8v8hYhgsVnKp5TkQETE2T63HW8Ffl-E,3234
 agno/knowledge/reader/tavily_reader.py,sha256=kwQXj3QWSW-snv7R3VPValmEngc862UkhSo9lQrjXCk,7183
-agno/knowledge/reader/text_reader.py,sha256=pRsboWTo8RGt0tU_2T1poDpLb0jLaSj4i_kNMW9eqs4,5036
-agno/knowledge/reader/web_search_reader.py,sha256=QacYjE5u36zsUzdPdpXzLi0Zj550UhKltzG9HScgb7I,12598
+agno/knowledge/reader/text_reader.py,sha256=2bmwxMaR88Xzh-y_SD61SbUo7KG05g0l1ixOAFUekco,4570
+agno/knowledge/reader/web_search_reader.py,sha256=WDa0yXlqqIjHaLaN7SymHLqaQsrKtzzYyBDYhBPTjfA,12073
 agno/knowledge/reader/website_reader.py,sha256=8R_71uVjx_tHAWhvvHNQqyc4nysV6HksJBMLZITpwS8,19349
 agno/knowledge/reader/wikipedia_reader.py,sha256=HXcp17xMnSFSYMrvBQDVKWqzoitlHuWZIQtYUqnE818,3092
 agno/knowledge/reader/youtube_reader.py,sha256=z0Udminq7XkUpob129Oq_8w8SvmRVn0CkXHp2S0KUg4,2986
@@ -608,8 +608,8 @@ agno/workflow/step.py,sha256=voTmWWihLKDAMeLgYoie96KLCiVpxPFrZoFHEMhA6QM,75046
 agno/workflow/steps.py,sha256=rbfue2M4qYEkgHueojCY1-cB4i1MFjO-jX6uTxyoKwk,27118
 agno/workflow/types.py,sha256=OJXn4sYQ1VQ1H7UO_BwOO3_6q-OgcDX2XLDw3H4LIx0,20508
 agno/workflow/workflow.py,sha256=ylRulasAlJXDC90BpPaFxXNnlO_xcf5LxAbmcTU-Ltg,193481
-agno-2.3.15.dist-info/licenses/LICENSE,sha256=QwcOLU5TJoTeUhuIXzhdCEEDDvorGiC6-3YTOl4TecE,11356
-agno-2.3.15.dist-info/METADATA,sha256=b8wMpod_FDa0Q7AxuquuiY36XHIQojsIzFu6zhfj82A,31588
-agno-2.3.15.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-agno-2.3.15.dist-info/top_level.txt,sha256=MKyeuVesTyOKIXUhc-d_tPa2Hrh0oTA4LM0izowpx70,5
-agno-2.3.15.dist-info/RECORD,,
+agno-2.3.16.dist-info/licenses/LICENSE,sha256=QwcOLU5TJoTeUhuIXzhdCEEDDvorGiC6-3YTOl4TecE,11356
+agno-2.3.16.dist-info/METADATA,sha256=yC4XU3rJgtlQKQi7UwuaHiizC6G9aoGuMiZw5FiCmqo,31588
+agno-2.3.16.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+agno-2.3.16.dist-info/top_level.txt,sha256=MKyeuVesTyOKIXUhc-d_tPa2Hrh0oTA4LM0izowpx70,5
+agno-2.3.16.dist-info/RECORD,,