use instructor embedding, and add migration of embeddings if ever changes, at least for chroma

[pseudotensor]

No description provided.

[pseudotensor]

============================================================================================================ short test summary info ============================================================================================================
FAILED tests/test_cli.py::test_cli_langchain_llamacpp - assert 'It is sitting on a window and looking out at the view' in '\nThe cat is sitting on a window seat and looking out the window at the view of the city outside.\n\nSources [Score | Link]:<p><ul><li>0.85 | <a href="file/user_path_tes...
FAILED tests/test_client_calls.py::test_client_chat_stream_langchain_steps - AssertionError: assert ('Whisper is a secure messaging app that allows' in 'h2oGPTSources [Score | Link]:0.72 | user_path_test/./README.md0.7 | user_path_test/./FAQ.mdEnd Sources')
FAILED tests/test_client_calls.py::test_client_chat_stream_langchain_steps2 - AssertionError: assert ('speech recognition system' in '')
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 -- put in URL box https://github.com/h2oai/h2ogpt/ (and ask what is h2ogpt?). Ensure can go to source links
FAILED tests/test_manual_test.py::test_upload_arxiv - NotImplementedError: MANUAL TEST FOR NOW -- paste in arxiv:1706.03762 and ask who wrote attention paper. Ensure can go to source links
FAILED tests/test_manual_test.py::test_upload_pasted_text - NotImplementedError: MANUAL TEST FOR NOW -- do and see test code for what to try
FAILED tests/test_manual_test.py::test_no_db_dirs - NotImplementedError: MANUAL TEST FOR NOW -- Remove db_dirs, ensure can still start up and use in MyData Mode.
FAILED tests/test_manual_test.py::test_upload_unsupported_file - NotImplementedError: MANUAL TEST FOR NOW -- e.g. json, ensure error correct and reasonable, no cascades
FAILED tests/test_manual_test.py::test_upload_to_UserData_and_MyData - NotImplementedError: MANUAL TEST FOR NOW Upload to each when enabled, ensure no failures
FAILED tests/test_manual_test.py::test_chat_control - NotImplementedError: MANUAL TEST FOR NOW save chat, select chats, clear chat, export, import, etc.
FAILED tests/test_manual_test.py::test_subset_only - NotImplementedError: MANUAL TEST FOR NOW UserData, Select Only for subset, then put in whisper.  Ensure get back only chunks of data with url links to data sources.
FAILED tests/test_manual_test.py::test_add_new_doc - NotImplementedError: MANUAL TEST FOR NOW UserData, add new pdf or file to user_path and see if pushing refresh sources updates and shows new file in list, then ask question about that new doc
=========================================================================== 15 failed, 89 passed, 35 skipped, 1 xfailed, 1 xpassed, 9 warnings in 1900.78s (0:31:40) ============================================================================
(h2ollm) jon@pseudotensor:~/h2ogpt$ 

[pseudotensor]

============================================================================================================ 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 -- put in URL box https://github.com/h2oai/h2ogpt/ (and ask what is h2ogpt?). Ensure can go to source links
FAILED tests/test_manual_test.py::test_upload_arxiv - NotImplementedError: MANUAL TEST FOR NOW -- paste in arxiv:1706.03762 and ask who wrote attention paper. Ensure can go to source links
FAILED tests/test_manual_test.py::test_upload_pasted_text - NotImplementedError: MANUAL TEST FOR NOW -- do and see test code for what to try
FAILED tests/test_manual_test.py::test_no_db_dirs - NotImplementedError: MANUAL TEST FOR NOW -- Remove db_dirs, ensure can still start up and use in MyData Mode.
FAILED tests/test_manual_test.py::test_upload_unsupported_file - NotImplementedError: MANUAL TEST FOR NOW -- e.g. json, ensure error correct and reasonable, no cascades
FAILED tests/test_manual_test.py::test_upload_to_UserData_and_MyData - NotImplementedError: MANUAL TEST FOR NOW Upload to each when enabled, ensure no failures
FAILED tests/test_manual_test.py::test_chat_control - NotImplementedError: MANUAL TEST FOR NOW save chat, select chats, clear chat, export, import, etc.
FAILED tests/test_manual_test.py::test_subset_only - NotImplementedError: MANUAL TEST FOR NOW UserData, Select Only for subset, then put in whisper.  Ensure get back only chunks of data with url links to data sources.
FAILED tests/test_manual_test.py::test_add_new_doc - NotImplementedError: MANUAL TEST FOR NOW UserData, add new pdf or file to user_path and see if pushing refresh sources updates and shows new file in list, then ask question about that new doc
=========================================================================== 12 failed, 92 passed, 35 skipped, 1 xfailed, 1 xpassed, 9 warnings in 2308.04s (0:38:28) ============================================================================
(h2ollm) jon@pseudotensor:~/h2ogpt$ 

[pseudotensor]

more for steps2

============================================================================================================ 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 -- put in URL box https://github.com/h2oai/h2ogpt/ (and ask what is h2ogpt?). Ensure can go to source links
FAILED tests/test_manual_test.py::test_upload_arxiv - NotImplementedError: MANUAL TEST FOR NOW -- paste in arxiv:1706.03762 and ask who wrote attention paper. Ensure can go to source links
FAILED tests/test_manual_test.py::test_upload_pasted_text - NotImplementedError: MANUAL TEST FOR NOW -- do and see test code for what to try
FAILED tests/test_manual_test.py::test_no_db_dirs - NotImplementedError: MANUAL TEST FOR NOW -- Remove db_dirs, ensure can still start up and use in MyData Mode.
FAILED tests/test_manual_test.py::test_upload_unsupported_file - NotImplementedError: MANUAL TEST FOR NOW -- e.g. json, ensure error correct and reasonable, no cascades
FAILED tests/test_manual_test.py::test_upload_to_UserData_and_MyData - NotImplementedError: MANUAL TEST FOR NOW Upload to each when enabled, ensure no failures
FAILED tests/test_manual_test.py::test_chat_control - NotImplementedError: MANUAL TEST FOR NOW save chat, select chats, clear chat, export, import, etc.
FAILED tests/test_manual_test.py::test_subset_only - NotImplementedError: MANUAL TEST FOR NOW UserData, Select Only for subset, then put in whisper.  Ensure get back only chunks of data with url links to data sources.
FAILED tests/test_manual_test.py::test_add_new_doc - NotImplementedError: MANUAL TEST FOR NOW UserData, add new pdf or file to user_path and see if pushing refresh sources updates and shows new file in list, then ask question about that new doc
=========================================================================== 12 failed, 92 passed, 35 skipped, 1 xfailed, 1 xpassed, 10 warnings in 2419.13s (0:40:19) ===========================================================================
(h2ollm) jon@pseudotensor:~/h2ogpt$