Spring/spring-ai
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
380 Commits 62 Branches 0 Tags
596f2b06c06f6c0fa8dfd3da5a2d92ca3cfcee67
Commit Graph

14 Commits

Author SHA1 Message Date
Mark Pollack
596f2b06c0 Move native hints into individual modules 
* Use aot.factories approach for registration
* Add tests
* final tweaks- Thanks Josh!
 2024-02-20 14:23:40 -05:00
Christian Tzolov
7b38cc3a88 Improve pdf paragraph constrains 
The ParagraphPdfDocumentReader relies on a PDF object called 'outline' (e.g. TOC) to be present in the document.
If the pdf was not generated with TOC, the other options in Spring AI are PagePdfDocumentReader and TikaDocumentReader.

 Resolves #59
 2024-01-13 12:16:14 +01:00
Mark Pollack
72af42d0d8 remove extraneous logback.xml file. Fixes #159 2023-12-14 11:08:41 -05:00
Christian Tzolov
6d3c429e95 remove the occurances of 'experimenta' in the git urls and docs 2023-12-12 17:48:11 +01:00
Mark Pollack
8cc941d5ad move to 0.8.0-SNAPSHOT 2023-12-11 11:53:06 -05:00
Mark Pollack
f6dc8f6bd8 Move documentation that was in README.md into Antora. 
* Add minimal ETL pipeline docs

Fixes #137
 2023-12-05 21:21:06 -05:00
Christian Tzolov
952ff6c319 Simplify VectorStore interface 
- Collapses all VectorStore similiaritySearch methdos into one with SearchRequest builder.
 - Fix all affected code and tests.
 - Bump the project version to 0.7.1.
 - Add tests
 - Add autoconfigurations for milvus, pinecone and pgvecor stores.
 - Improve and unify the VectorStore ITs.
 - Make use of TrasformersEmbeddingClient for auto-configurations ITs.
 2023-11-14 15:39:01 -05:00
Christian Tzolov
001ee990b3 Suppress pdfbox excessive logging 2023-10-31 14:21:50 +01:00
Toshiaki Maki
6aecf03059 Exclude commons-logging 
that conflicts spring-jcl
 2023-10-31 13:54:00 +01:00
Christian Tzolov
f9ca032cb3 Apache Tika based reader for all kinds of documents 
- Provides a rudimentary text extractions for multitude of document formats,
   including PDF, Word Doc/Docx PowerPoint ppt/pptx and many more.
 - Generates a single Document for the extracted text.
 - No pre or post processing and cleansing for the text.
 - Move the ExtractedTextFormatter from pdf reader to the core reader to enable reusability. Improve the tika reader
 2023-10-30 16:33:26 -04:00
Toshiaki Maki
72dfc1b50d Fix wrong description in PdfDocumentReaderConfig javadoc (#62) 2023-10-30 16:09:46 +01:00
Christian Tzolov
90117fe504 Move the version properties from the children to the parent POM 2023-10-18 16:50:31 +02:00
Christian Tzolov
e5693f7e60 Convert the PdfTestUtils into a generic FileDocumentWriter 2023-10-17 11:56:29 +02:00
Christian Tzolov
1266c04b6d Add PDF Document Readers 
- Add a set of PDF readers fro per-page (PagePdfDocumentReader) and per-paragraph (ParagraphPdfDocumentReader) readers.
  - Use a PDFLayoutTextStripper fork and PDFLayoutTextStripperByArea extension to preserve the structure of the extracted document.
  - PdfDocumentReaderConfig and PageExtractedTextFormatter in standalone classes.
  - Craeate a new document-readers top level model and the pdf-reader under.
 2023-10-16 09:45:15 -04:00