langroid 0.1.159__tar.gz → 0.1.160__tar.gz

{langroid-0.1.159 → langroid-0.1.160}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: langroid
-Version: 0.1.159
+Version: 0.1.160
 Summary: Harness LLMs with Multi-Agent Programming
 License: MIT
 Author: Prasad Chalasani
@@ -64,6 +64,7 @@ Requires-Dist: pytest-asyncio (>=0.21.1,<0.22.0)
 Requires-Dist: pytest-mysql (>=2.4.2,<3.0.0) ; extra == "mysql"
 Requires-Dist: pytest-postgresql (>=5.0.0,<6.0.0) ; extra == "postgres"
 Requires-Dist: pytest-redis (>=3.0.2,<4.0.0)
+Requires-Dist: python-docx (>=1.1.0,<2.0.0)
 Requires-Dist: python-dotenv (>=1.0.0,<2.0.0)
 Requires-Dist: qdrant-client (>=1.7.0,<2.0.0)
 Requires-Dist: rank-bm25 (>=0.2.2,<0.3.0)

{langroid-0.1.159 → langroid-0.1.160}/langroid/parsing/document_parser.py

@@ -62,6 +62,8 @@ class DocumentParser(Parser):
         elif DocumentParser._document_type(source) == DocumentType.DOCX:
             if config.docx.library == "unstructured":
                 return UnstructuredDocxParser(source, config)
+            elif config.docx.library == "python-docx":
+                return PythonDocxParser(source, config)
             else:
                 raise ValueError(
                     f"Unsupported DOCX library specified: {config.docx.library}"
@@ -436,3 +438,34 @@ class UnstructuredDocxParser(DocumentParser):
         """
         text = " ".join(el.text for el in page)
         return self.fix_text(text)
+
+
+class PythonDocxParser(DocumentParser):
+    """
+    Parser for processing DOCX files using the `python-docx` library.
+    """
+
+    def iterate_pages(self) -> Generator[Tuple[int, Any], None, None]:
+        """
+        Simulate iterating through pages.
+        In a DOCX file, pages are not explicitly defined,
+        so we consider each paragraph as a separate 'page' for simplicity.
+        """
+        import docx
+
+        doc = docx.Document(self.doc_bytes)
+        for i, para in enumerate(doc.paragraphs, start=1):
+            yield i, [para]
+
+    def extract_text_from_page(self, page: Any) -> str:
+        """
+        Extract text from a given 'page', which in this case is a single paragraph.
+
+        Args:
+            page (list): A list containing a single Paragraph object.
+
+        Returns:
+            str: Extracted text from the paragraph.
+        """
+        paragraph = page[0]
+        return self.fix_text(paragraph.text)

{langroid-0.1.159 → langroid-0.1.160}/langroid/parsing/parser.py

@@ -1,6 +1,6 @@
 import logging
 from enum import Enum
-from typing import Dict, List
+from typing import Dict, List, Literal
 
 import tiktoken
 from pydantic import BaseSettings
@@ -19,11 +19,13 @@ class Splitter(str, Enum):
 
 
 class PdfParsingConfig(BaseSettings):
-    library: str = "pdfplumber"
+    library: Literal[
+        "fitz", "pdfplumber", "pypdf", "unstructured", "haystack"
+    ] = "pdfplumber"
 
 
 class DocxParsingConfig(BaseSettings):
-    library: str = "unstructured"
+    library: Literal["python-docx", "unstructured"] = "unstructured"
 
 
 class ParsingConfig(BaseSettings):

{langroid-0.1.159 → langroid-0.1.160}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langroid"
-version = "0.1.159"
+version = "0.1.160"
 description = "Harness LLMs with Multi-Agent Programming"
 authors = ["Prasad Chalasani <pchalasani@gmail.com>"]
 readme = "README.md"
@@ -81,6 +81,7 @@ scrapy = "^2.11.0"
 async-generator = "^1.10"
 lancedb = "^0.4.1"
 pytest-redis = "^3.0.2"
+python-docx = "^1.1.0"
 
 [tool.poetry.extras]
 # install these using `poetry install -E [...]` where [...] is one of the extras below