Clean up parsers imports

py/core/parsers/media/audio_parser.py

@@ -3,6 +3,8 @@
 import tempfile
 from typing import AsyncGenerator
 
+from litellm import atranscription
+
 from core.base.parsers.base_parser import AsyncParser
 from core.base.providers import (
     CompletionProvider,
@@ -25,15 +27,7 @@ def __init__(
         self.database_provider = database_provider
         self.llm_provider = llm_provider
         self.config = config
-        try:
-            from litellm import atranscription
-
-            self.atranscription = atranscription
-        except ImportError:
-            logger.error("Failed to import LiteLLM transcription")
-            raise ImportError(
-                "Please install the `litellm` package to use the AudioParser."
-            )
+        self.atranscription = atranscription
 
     async def ingest(  # type: ignore
         self, data: bytes, **kwargs

py/core/parsers/media/doc_parser.py

@@ -3,6 +3,8 @@
 from io import BytesIO
 from typing import AsyncGenerator
 
+import olefile
+
 from core.base.parsers.base_parser import AsyncParser
 from core.base.providers import (
     CompletionProvider,
@@ -23,16 +25,7 @@ def __init__(
         self.database_provider = database_provider
         self.llm_provider = llm_provider
         self.config = config
-
-        try:
-            import olefile
-
-            self.olefile = olefile
-        except ImportError:
-            raise ImportError(
-                "Error: 'olefile' is required to run DOCParser. "
-                "Please install it using pip: pip install olefile"
-            )
+        self.olefile = olefile
 
     async def ingest(
         self, data: str | bytes, **kwargs

py/core/parsers/media/docx_parser.py

@@ -1,6 +1,8 @@
 from io import BytesIO
 from typing import AsyncGenerator
 
+from docx import Document
+
 from core.base.parsers.base_parser import AsyncParser
 from core.base.providers import (
     CompletionProvider,
@@ -21,15 +23,7 @@ def __init__(
         self.database_provider = database_provider
         self.llm_provider = llm_provider
         self.config = config
-
-        try:
-            from docx import Document
-
-            self.Document = Document
-        except ImportError:
-            raise ValueError(
-                "Error, `python-docx` is required to run `DOCXParser`. Please install it using `pip install python-docx`."
-            )
+        self.Document = Document
 
     async def ingest(self, data: str | bytes, *args, **kwargs) -> AsyncGenerator[str, None]:  # type: ignore
         """Ingest DOCX data and yield text from each paragraph."""

py/core/parsers/media/img_parser.py

@@ -4,6 +4,9 @@
 from io import BytesIO
 from typing import AsyncGenerator
 
+import pillow_heif
+from PIL import Image
+
 from core.base.abstractions import GenerationConfig
 from core.base.parsers.base_parser import AsyncParser
 from core.base.providers import (
@@ -26,21 +29,9 @@ def __init__(
         self.llm_provider = llm_provider
         self.config = config
         self.vision_prompt_text = None
-
-        try:
-            import pillow_heif  # for HEIC support
-            from litellm import supports_vision
-            from PIL import Image
-
-            self.supports_vision = supports_vision
-            self.Image = Image
-            self.pillow_heif = pillow_heif
-            self.pillow_heif.register_heif_opener()
-        except ImportError as e:
-            logger.error(f"Failed to import required packages: {str(e)}")
-            raise ImportError(
-                "Please install the required packages: litellm, Pillow, pillow-heif"
-            )
+        self.Image = Image
+        self.pillow_heif = pillow_heif
+        self.pillow_heif.register_heif_opener()
 
     def _is_heic(self, data: bytes) -> bool:
         """More robust HEIC detection using magic numbers and patterns."""

py/core/parsers/media/odt_parser.py

@@ -1,4 +1,6 @@
 # type: ignore
+import xml.etree.ElementTree as ET
+import zipfile
 from typing import AsyncGenerator
 
 from core.base.parsers.base_parser import AsyncParser
@@ -19,15 +21,8 @@ def __init__(
         self.database_provider = database_provider
         self.llm_provider = llm_provider
         self.config = config
-
-        try:
-            import xml.etree.ElementTree as ET
-            import zipfile
-
-            self.zipfile = zipfile
-            self.ET = ET
-        except ImportError:
-            raise ImportError("XML parsing libraries not available")
+        self.zipfile = zipfile
+        self.ET = ET
 
     async def ingest(
         self, data: str | bytes, **kwargs

py/core/parsers/media/pdf_parser.py

@@ -4,20 +4,17 @@
 import asyncio
 import base64
 import logging
-import os
 import string
-import tempfile
 import time
 import unicodedata
-import uuid
 from io import BytesIO
 from typing import AsyncGenerator
 
 # Third-party imports
-import aiofiles
 from pdf2image import convert_from_bytes, convert_from_path
 from pdf2image.exceptions import PDFInfoNotInstalledError
 from PIL import Image
+from pypdf import PdfReader
 
 # Local application imports
 from core.base.abstractions import GenerationConfig
@@ -46,16 +43,6 @@ def __init__(
         self.config = config
         self.vision_prompt_text = None
 
-        try:
-            from litellm import supports_vision
-
-            self.supports_vision = supports_vision
-        except ImportError:
-            logger.error("Failed to import LiteLLM vision support")
-            raise ImportError(
-                "Please install the litellm package to use the VLMPDFParser."
-            )
-
     async def convert_pdf_to_images(
         self, data: str | bytes
     ) -> list[Image.Image]:
@@ -229,14 +216,7 @@ def __init__(
         self.database_provider = database_provider
         self.llm_provider = llm_provider
         self.config = config
-        try:
-            from pypdf import PdfReader
-
-            self.PdfReader = PdfReader
-        except ImportError:
-            raise ValueError(
-                "Error, `pypdf` is required to run `PyPDFParser`. Please install it using `pip install pypdf`."
-            )
+        self.PdfReader = PdfReader
 
     async def ingest(
         self, data: str | bytes, **kwargs
@@ -293,12 +273,6 @@ def __init__(
 
         except ImportError as e:
             logger.error("PDFParserUnstructured ImportError :  ", e)
-            logger.error(
-                """Please install missing modules using :
-            pip install unstructured  unstructured_pytesseract  unstructured_inference
-            pip install pdfplumber   matplotlib   pillow_heif  toml
-            """
-            )
 
     async def ingest(
         self,

py/core/parsers/media/ppt_parser.py

@@ -3,6 +3,8 @@
 from io import BytesIO
 from typing import AsyncGenerator
 
+import olefile
+
 from core.base.parsers.base_parser import AsyncParser
 from core.base.providers import (
     CompletionProvider,
@@ -23,16 +25,7 @@ def __init__(
         self.database_provider = database_provider
         self.llm_provider = llm_provider
         self.config = config
-
-        try:
-            import olefile
-
-            self.olefile = olefile
-        except ImportError:
-            raise ImportError(
-                "Error: 'olefile' is required to run PPTParser. "
-                "Please install it using pip: pip install olefile"
-            )
+        self.olefile = olefile
 
     def _extract_text_from_record(self, data: bytes) -> str:
         """Extract text from a PPT text record."""

py/core/parsers/media/pptx_parser.py

@@ -2,6 +2,8 @@
 from io import BytesIO
 from typing import AsyncGenerator
 
+from pptx import Presentation
+
 from core.base.parsers.base_parser import AsyncParser
 from core.base.providers import (
     CompletionProvider,
@@ -22,14 +24,7 @@ def __init__(
         self.database_provider = database_provider
         self.llm_provider = llm_provider
         self.config = config
-        try:
-            from pptx import Presentation
-
-            self.Presentation = Presentation
-        except ImportError:
-            raise ValueError(
-                "Error, `python-pptx` is required to run `PPTXParser`. Please install it using `pip install python-pptx`."
-            )
+        self.Presentation = Presentation
 
     async def ingest(self, data: str | bytes, **kwargs) -> AsyncGenerator[str, None]:  # type: ignore
         """Ingest PPT data and yield text from each slide."""

py/core/parsers/media/rtf_parser.py

@@ -1,6 +1,8 @@
 # type: ignore
 from typing import AsyncGenerator
 
+from striprtf.striprtf import rtf_to_text
+
 from core.base.parsers.base_parser import AsyncParser
 from core.base.providers import (
     CompletionProvider,
@@ -21,16 +23,7 @@ def __init__(
         self.database_provider = database_provider
         self.llm_provider = llm_provider
         self.config = config
-
-        try:
-            from striprtf.striprtf import rtf_to_text
-
-            self.striprtf = rtf_to_text
-        except ImportError:
-            raise ImportError(
-                "Error: 'striprtf' is required to run RTFParser. "
-                "Please install it using pip: pip install striprtf"
-            )
+        self.striprtf = rtf_to_text
 
     async def ingest(
         self, data: str | bytes, **kwargs

py/core/parsers/structured/epub_parser.py

@@ -2,6 +2,8 @@
 import logging
 from typing import AsyncGenerator
 
+import epub
+
 from core.base.parsers.base_parser import AsyncParser
 from core.base.providers import (
     CompletionProvider,
@@ -24,16 +26,7 @@ def __init__(
         self.database_provider = database_provider
         self.llm_provider = llm_provider
         self.config = config
-
-        try:
-            import epub
-
-            self.epub = epub
-        except ImportError:
-            raise ImportError(
-                "Error: 'epub' is required to run EPUBParser. "
-                "Please install it using pip: pip install epub"
-            )
+        self.epub = epub
 
     def _safe_get_metadata(self, book, field: str) -> str | None:
         """Safely extract metadata field from epub book."""

py/core/parsers/structured/msg_parser.py

@@ -1,6 +1,8 @@
 # type: ignore
 from typing import AsyncGenerator
 
+import extract_msg
+
 from core.base.parsers.base_parser import AsyncParser
 from core.base.providers import (
     CompletionProvider,
@@ -21,16 +23,7 @@ def __init__(
         self.database_provider = database_provider
         self.llm_provider = llm_provider
         self.config = config
-
-        try:
-            import extract_msg
-
-            self.extract_msg = extract_msg
-        except ImportError:
-            raise ImportError(
-                "Error: 'extract-msg' is required to run MSGParser. "
-                "Please install it using pip: pip install extract-msg"
-            )
+        self.extract_msg = extract_msg
 
     async def ingest(
         self, data: str | bytes, **kwargs

py/core/parsers/structured/org_parser.py

@@ -1,6 +1,8 @@
 # type: ignore
 from typing import AsyncGenerator
 
+import orgparse
+
 from core.base.parsers.base_parser import AsyncParser
 from core.base.providers import (
     CompletionProvider,
@@ -21,16 +23,7 @@ def __init__(
         self.database_provider = database_provider
         self.llm_provider = llm_provider
         self.config = config
-
-        try:
-            import orgparse
-
-            self.orgparse = orgparse
-        except ImportError:
-            raise ImportError(
-                "Error: 'orgparse' is required to run ORGParser. "
-                "Please install it using pip: pip install orgparse"
-            )
+        self.orgparse = orgparse
 
     def _process_node(self, node) -> list[str]:
         """Process an org-mode node and return its content."""