langroid 0.1.159__py3-none-any.whl → 0.1.160__py3-none-any.whl

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/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.dist-info → langroid-0.1.160.dist-info}/METADATA

@@ -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.dist-info → langroid-0.1.160.dist-info}/RECORD

@@ -59,10 +59,10 @@ langroid/parsing/agent_chats.py,sha256=sbZRV9ujdM5QXvvuHVjIi2ysYSYlap-uqfMMUKulr
 langroid/parsing/code-parsing.md,sha256=--cyyNiSZSDlIwcjAV4-shKrSiRe2ytF3AdSoS_hD2g,3294
 langroid/parsing/code_parser.py,sha256=BbDAzp35wkYQ9U1dpf1ARL0lVyi0tfqEc6_eox2C090,3727
 langroid/parsing/config.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-langroid/parsing/document_parser.py,sha256=YC3IXQ9ErpBGBZh6Be9gfJWHcTwGTSMfNQMT5ARrj5g,14615
+langroid/parsing/document_parser.py,sha256=Msv8acFzVDex-nKPNxyGOvTw4eNKswrSQluYOa1qfAE,15670
 langroid/parsing/json.py,sha256=KfIIma_6IurQ09WTUyBn3mbSK67QeXZ8eHGDxGlOsv0,2551
 langroid/parsing/para_sentence_split.py,sha256=AJBzZojP3zpB-_IMiiHismhqcvkrVBQ3ZINoQyx_bE4,2000
-langroid/parsing/parser.py,sha256=BwVJboobG71N08w5LC7Tu36LI4pEJoSgAdiBSLChWGY,10251
+langroid/parsing/parser.py,sha256=0QDDfRrcO9jUwEj9WQiWi8ayVZ19MRC1xjwTLDrCKwg,10372
 langroid/parsing/repo_loader.py,sha256=hhMfQBBSo-HvsZDQEcgmk_idKQQAeDQ_MMPd38x2ACU,29338
 langroid/parsing/search.py,sha256=xmQdAdTIwZ0REEUeQVFlGZlqf7k8Poah7-ALuyW7Ov0,8440
 langroid/parsing/spider.py,sha256=w_mHR1B4KOmxsBLoVI8kMkMTEbwTzeK3ath9fOMJrTk,3043
@@ -103,7 +103,7 @@ langroid/vector_store/meilisearch.py,sha256=d2huA9P-NoYRuAQ9ZeXJmMKr7ry8u90RUSR2
 langroid/vector_store/momento.py,sha256=j6Eo6oIDN2fe7lsBOlCXJn3uvvERHHTFL5QJfeREeOM,10044
 langroid/vector_store/qdrant_cloud.py,sha256=3im4Mip0QXLkR6wiqVsjV1QvhSElfxdFSuDKddBDQ-4,188
 langroid/vector_store/qdrantdb.py,sha256=qt7Dye6rcgoe0551WzmOxRGIlJfL87D4MX7HdqxuEok,13393
-langroid-0.1.159.dist-info/LICENSE,sha256=EgVbvA6VSYgUlvC3RvPKehSg7MFaxWDsFuzLOsPPfJg,1065
-langroid-0.1.159.dist-info/METADATA,sha256=-qIZRl58PZFOsLnKyeFFktfjVedKKQufuogeH6TN2qw,42701
-langroid-0.1.159.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
-langroid-0.1.159.dist-info/RECORD,,
+langroid-0.1.160.dist-info/LICENSE,sha256=EgVbvA6VSYgUlvC3RvPKehSg7MFaxWDsFuzLOsPPfJg,1065
+langroid-0.1.160.dist-info/METADATA,sha256=C2tjQ0HKr3e3x0iWWa6vrbraLd9qgHZuslb1nrN5ERA,42745
+langroid-0.1.160.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
+langroid-0.1.160.dist-info/RECORD,,