prevectorchunks-core 0.1.23__py3-none-any.whl → 0.1.25__py3-none-any.whl

prevectorchunks_core/services/markdown_and_chunk_documents.py

@@ -12,9 +12,9 @@ from ..config.splitter_config import SplitterConfig
 
 from dotenv import load_dotenv
 
-from chunk_documents_crud_vdb import chunk_documents
-from chunk_to_all_content_mapper import ChunkMapper
-from core.prevectorchunks_core.utils.file_loader import SplitType
+from .chunk_documents_crud_vdb import chunk_documents
+from .chunk_to_all_content_mapper import ChunkMapper
+from ..utils.file_loader import SplitType
 
 load_dotenv(override=True)
 

{prevectorchunks_core-0.1.23.dist-info → prevectorchunks_core-0.1.25.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: prevectorchunks-core
-Version: 0.1.23
+Version: 0.1.25
 Summary: A Python module that allows conversion of a document into chunks to be inserted into Pinecone vector database
 Author-email: Zul Al-Kabir <zul.developer.2023@gmail.com>
 Project-URL: Homepage, https://github.com/yourusername/mydep
@@ -187,6 +187,41 @@ Updates existing chunks in the Vector Database by document name.
 - Keeping VDB chunks up to date when documents change
 - Re-ingesting revised or corrected content
 
+---
+### 5. ``markdown_and_chunk_documents``
+```python
+from prevectorchunks_core.services.markdown_and_chunk_documents import MarkdownAndChunkDocuments
+
+markdown_processor = MarkdownAndChunkDocuments()
+mapped_chunks = markdown_processor.markdown_and_chunk_documents("example.pdf")
+```
+
+**Description**  
+This new function automatically:
+1. Converts a document (PDF, DOCX, etc.) into images using `DocuToImageConverter`.
+2. Extracts **Markdown and text** content from those images using `DocuToMarkdownExtractor` (powered by GPT).
+3. Converts the extracted markdown text into **RL-based chunks** using `ChunkMapper` and `chunk_documents`.
+4. Merges unmatched markdown segments into the final structured output.
+
+**Parameters**
+- `file_path` (*str*): Path to the document (PDF, DOCX, or image) you want to process.
+
+**Returns**
+- `mapped_chunks` (*list[dict]*): A list of markdown-based chunks with both markdown and chunked text content.
+
+**Example**
+```python
+if __name__ == "__main__":
+    markdown_processor = MarkdownAndChunkDocuments()
+    mapped_chunks = markdown_processor.markdown_and_chunk_documents("421307-nz-au-top-loading-washer-guide-shorter.pdf")
+    print(mapped_chunks)
+```
+
+**Use Cases**
+- End-to-end document-to-markdown-to-chunks pipeline
+- Automating preprocessing for RAG/LLM ingestion
+- Extracting structured markdown for semantic search or content indexing
+
 ---
 
 ## 🚀 Example Workflow

{prevectorchunks_core-0.1.23.dist-info → prevectorchunks_core-0.1.25.dist-info}/RECORD

@@ -23,7 +23,7 @@ prevectorchunks_core/services/audio_processor.py,sha256=XKNYhXHIt_77a3PT2wwKvnCS
 prevectorchunks_core/services/chunk_documents_crud_vdb.py,sha256=Md4vy7vJDnSYpvZiF0HbHCOA0StSVm62ALHAPYU2A7I,16279
 prevectorchunks_core/services/chunk_to_all_content_mapper.py,sha256=xEz2idxJTsJwyCJWMPZCk3CFcalKhbSuucFH9TPouU0,2778
 prevectorchunks_core/services/image_processor.py,sha256=2CRwTbI-czbakm9aG-kMdx908bc5H1rQETQiVCKbWd8,3518
-prevectorchunks_core/services/markdown_and_chunk_documents.py,sha256=BYwu4FcliFU-adnPoqUuqjAkRvV7mVtOvAPKS1sM6Zk,2884
+prevectorchunks_core/services/markdown_and_chunk_documents.py,sha256=vfGvvirn3rtwIVJtVK5_dJSrV3JeO0p0d0rc5BOnGx8,2862
 prevectorchunks_core/services/propositional_index.py,sha256=cVH3obhLtlcfJYA6VN4KfC3len4fe5nNcboorlouOb0,4151
 prevectorchunks_core/services/video_analyser.py,sha256=1wI38xZ8vdE8T4EBAnxWzt7Hc8vTYrdQhbA4Y5VZLeY,6651
 prevectorchunks_core/tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -32,8 +32,8 @@ prevectorchunks_core/utils/__init__.py,sha256=aez3v2dwGHXvmALXVBPR-mQgvxMqxv9NsE
 prevectorchunks_core/utils/extract_content.py,sha256=fMDT-BsjYutHLnOFebLhMFpb1UFAB8ldGldxh11FsXw,2920
 prevectorchunks_core/utils/file_loader.py,sha256=JkCKiz3M2TMw5qHoTJXhbn33PfTv5gvQ3nfrbaQOmHs,10689
 prevectorchunks_core/utils/llm_wrapper.py,sha256=7GfyM5p5PeIehi4Dj5jgC7-xi2SjZuyyPuLkWtucQzQ,1139
-prevectorchunks_core-0.1.23.dist-info/licenses/LICENCE,sha256=Ljp4XVKnncsQ59h0eMW6J5V-ylsVeqDRC8smR7UPIDs,512
-prevectorchunks_core-0.1.23.dist-info/METADATA,sha256=vKOvF3fsJY6Zn-jfY0DNUP6CljBQadByMcD8xzta2WU,9272
-prevectorchunks_core-0.1.23.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-prevectorchunks_core-0.1.23.dist-info/top_level.txt,sha256=OWJgfrUDNTh49PpKvRXHY8lVeWqzFbTr9OkDoAvpvPk,21
-prevectorchunks_core-0.1.23.dist-info/RECORD,,
+prevectorchunks_core-0.1.25.dist-info/licenses/LICENCE,sha256=Ljp4XVKnncsQ59h0eMW6J5V-ylsVeqDRC8smR7UPIDs,512
+prevectorchunks_core-0.1.25.dist-info/METADATA,sha256=MkwN6c12SBuLRwFgaWUwANwGMsno4939fo5jU9otYBc,10687
+prevectorchunks_core-0.1.25.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+prevectorchunks_core-0.1.25.dist-info/top_level.txt,sha256=OWJgfrUDNTh49PpKvRXHY8lVeWqzFbTr9OkDoAvpvPk,21
+prevectorchunks_core-0.1.25.dist-info/RECORD,,