Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add image support and show sources after upload #147

Merged
merged 18 commits into from
May 19, 2023
Merged

Add image support and show sources after upload #147

merged 18 commits into from
May 19, 2023

Conversation

pseudotensor
Copy link
Collaborator

@pseudotensor pseudotensor commented May 18, 2023 •
edited
Loading 

============================================================================================= short test summary info =============================================================================================
FAILED tests/test_manual_test.py::test_chat_context - NotImplementedError: MANUAL TEST FOR NOW
FAILED tests/test_manual_test.py::test_upload_one_file - NotImplementedError: MANUAL TEST FOR NOW -- do and ask query of file
FAILED tests/test_manual_test.py::test_upload_multiple_file - NotImplementedError: MANUAL TEST FOR NOW -- do and ask query of files
FAILED tests/test_manual_test.py::test_upload_url - NotImplementedError: MANUAL TEST FOR NOW -- do and ask query of content of url
FAILED tests/test_manual_test.py::test_upload_pasted_text - NotImplementedError: MANUAL TEST FOR NOW -- do and see test code for what to try
=================================================================== 5 failed, 29 passed, 8 skipped, 1 xpassed, 10 warnings in 456.55s (0:07:36) ===================================================================
(h2ollm) jon@pseudotensor:~/h2o-llm$ 

(h2ollm) jon@pseudotensor:~/h2o-llm$

image

image

image

@pseudotensor pseudotensor changed the title Add image support Add image support and show sources after upload May 18, 2023
@pseudotensor
Deal with preloading BLIP for image caption, so forking avoided.
1e81149 
Separate out image and non-image to handle BLIP forking.
Related, if fast tokenizer loaded, and then fork, complains and can hang, but not always.
From tests can hang, so avoid fast there, but in gradio no problems uploading large zip with many pdfs and embedding those and doing more files after that in parallel.

Note some easy PDFs can be empty/garbage.

Don't reload chroma db after created.

Don't give no sources if making db, chroma doesn't handle empty case and just fails.

Fix docx/doc in list.

Avoid upload file button, just rely upon box.
@pseudotensor
Fix name of var
b473e7c
@pseudotensor
Use path_to_docs when uploading from gradio, so can handle multiple t…
5138aec 
…ypes of inputs, including multiple file upload from gradio, not just single file.
@pseudotensor
Show sources added with new lines so easier to read
623109c
@pseudotensor
For testing, avoid fork so no cuda forked from parent
8a63010
@pseudotensor
Bit stricter for MyData search so less irrelevant results -- needs im…
a48f11d 
…provement
@pseudotensor
More manual tests
d8ae43d
@pseudotensor
Handle text/url after change to path_to_docs
704d255
@pseudotensor
Copy link
Collaborator Author

good enough: https://stackoverflow.com/questions/61342714/how-to-add-vertical-scrollbar-to-the-table-sent-by-python-email-module

could do: #150

@pseudotensor pseudotensor merged commit 5371c17 into main May 19, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@pseudotensor