Hugging Face's logo

Spaces:
geekyrakshit
/
medrag
Running

App Files Community
medrag / medrag_multi_modal

Commit History

add: utility for torch backend
70d9de4

geekyrakshit commited on

update: get_wandb_artifact
96bca50

geekyrakshit commited on

remove: load_image.py
475fb67

geekyrakshit commited on

resolve: merge conflict
4344d0d

geekyrakshit commited on

bugfix: prevent model load on every extraction
ff75fe0

mratanusarkar commited on

chore: address review points
2691833

mratanusarkar commited on

add: ContrieverRetriever
b82a487

geekyrakshit commited on

upfate: CalPaliRetriever methods to align with other retrievers
c063304

geekyrakshit commited on

add: two modules on fitz to handle img extractions
f9d44bd

mratanusarkar commited on

temp: attempt - force to png with pillow
3d948a1

mratanusarkar commited on

temp: attempt - all format img extraction from pdf
5406446

mratanusarkar commited on

fix: catch byaldi import
3bd446c

geekyrakshit commited on

fix: catch byaldi import
353a440

geekyrakshit commited on

update: decouple Byaldi from pyproject.toml because of conflict with adapters and mentioned the same in relevant docs as well
8f9e28d

geekyrakshit commited on

add: basic workflow to check code format and lint
4069faf

geekyrakshit commited on

fix: bug wrt result unpacking in BM25sRetriever.retrieve
86ac070

geekyrakshit commited on

add: docs for BM25sRetriever
b5a3ebb

geekyrakshit commited on

add: hacky impl of img extraction with pdfplumber
4fd52cf

mratanusarkar commited on

add: example usage for marker and pdf2img loaders
bf0f2e5

mratanusarkar commited on

add: marker image loader + docs + corrections
331f289

mratanusarkar commited on

chore: improve doc + code formatting
f37090a

mratanusarkar commited on

add: docs for base img loader + pdf2image
cc5cebc

mratanusarkar commited on

add: base image loader + pdf2img from load_image
5c74069

mratanusarkar commited on

update: BM25sRetriever
7f98acf

geekyrakshit commited on

update: BM25sRetriever
88a5bcf

geekyrakshit commited on

add: BM25sRetriever
4ea2b30

geekyrakshit commited on

refactor: colpali retrieval
21537b7

geekyrakshit commited on

add: SemanticChunker
ace03e3

geekyrakshit commited on

add: SemanticChunker
49d583d

geekyrakshit commited on

update: codebase addressing review comments
a24da3d

mratanusarkar commited on

add: kwargs to interact with underlying library
6526b2f

mratanusarkar commited on

update: convert _process_page to extract_page_data
e31ec78

mratanusarkar commited on

add: docs & docstrings for marker text loader
fc27062

mratanusarkar commited on

add: marker pdf text loader
fb5095f

mratanusarkar commited on

add: docs & docstrings for pdfplumber text loader
d647546

mratanusarkar commited on

add: pdfplumber text loader
be6fbc6

mratanusarkar commited on

add: docs & docstrings for pypdf2 text loader
419f968

mratanusarkar commited on

add: pypdf2 loader text loader
391b2f3

mratanusarkar commited on

chore: format & linting + __init__ + fix: imports
e0aff18

mratanusarkar commited on

chore: remove old load_text
78dd8e8

mratanusarkar commited on

add: docs & docstrings for base + pymupdf4llm
4304db6

mratanusarkar commited on

add: base text loader and pymupdf4llm loader
9761deb

mratanusarkar commited on

add: MultiModalRetriever.predict
d197e7f

geekyrakshit commited on

update: colpali index syncs with wandb artifact
abd20d0

geekyrakshit commited on

update: docuementation with installation instructions
24e7c59

geekyrakshit commited on

add: MultiModalRetriever
7df75ff

geekyrakshit commited on

update: ImageLoader
a7ff122

geekyrakshit commited on