Spaces:
Sleeping
Sleeping
Commit History
Included exact/fuzzy phrase matching. Updated packages and added basic logging.
dbad462
Cognito authorisation option added to app, some other minor changes.
759001a
Changed embedding model to MiniLM-L6 as faster. Compressed embeddings are now int8. General improvements to API mode
ea0dd40
General code improvements and refinements.
a95ef9f
Some package updates and minor changes
2754a2b
Fixed cleaning for semantic search. Handles text with backslashes in (if cleaned). Updated packages. requirements file for only keyword search added.
8466e45
Gradio 4.21. Limitations on file size and creating embeddings. Added AWS integration
e0fe055
Updated to latest Gradio version that hopefully solved root_url issues. Added ssl_verify=False to launch
813f823
Sean-Case
commited on
set gradio version to 4.18.0, before root path issue reappears
8ba34be
Sean-Case
commited on
Added highlight search term functionality to keyword search output
36a404e
Updated to Gradio 4.16.0. Now works correctly with BGE embeddings
2bcd818
Upgraded to Gradio 4.16.0. Added Spacy fuzzy search functionality.
4ce2224
Sean-Case
commited on
Changed requirements to download correct spacy model version
4e77f14
Sean-Case
commited on
Cut out semantic search temporarily while issues with Jina gated model resolved. Improved error/progress tracking and messaging. Placeholder for Spacy fuzzy search.
739b386
Switch back to Gradio version 3.50.2 as 4 is not working with pyinstaller app creation yet
c6dc87d
Sean-Case
commited on
Better error checking. Doesn't load in embeddings file twice now.
63049fe
Sean-Case
commited on
Added accelerate to requirements. Minor doc changes
f2db299
Many changes to code organisation. More efficient searches from using intermediate outputs. Version 0.1
99d6fba
Added polars to requirements
25489e9
Added semantic search using Jina
ceb8617
Faster embedding with GPU, fast document split, writes to chromadb file correctly. No longer needs FAISS or langchain
2cb9977
Added to requirements: transformers
acfac99
Sean-Case
commited on
Initial commit
a9c2120
Sean-Case
commited on