Debanjum Singh Solanky 0f1ebcae18 Upgrade to latest GPT4All. Use Mistral as default offline chat model ...

GPT4all now supports gguf llama.cpp chat models. Latest
GPT4All (+mistral) performs much at least 3x faster.

On Macbook Pro at ~10s response start time vs 30s-120s earlier.
Mistral is also a better chat model, although it hallucinates more
than llama-2

2023-10-22 19:04:23 -07:00

..

data

Fix plaintext HTML parsing and rendering (#464)

2023-08-27 11:24:30 -07:00

__init__.py

Move tests out to project root. Use absolute import in project

2021-09-30 04:12:14 -07:00

conftest.py

Upgrade to latest GPT4All. Use Mistral as default offline chat model

2023-10-22 19:04:23 -07:00

test_cli.py

Remove PySide dependency and deprecate desktop builds (#475)

2023-09-07 11:36:27 -07:00

test_client.py

Mark test_get_configured_types_via_api unit test as flaky

2023-10-17 05:56:00 -07:00

test_conversation_utils.py

Add additional check for chat_messages length in UT

2023-08-01 09:25:52 -07:00

test_date_filter.py

Update date filter test to use compiled rather than raw key

2023-09-18 11:24:56 -07:00

test_file_filter.py

Add method to extract filter terms from query to all filters

2023-08-28 00:55:28 -07:00

test_gpt4all_chat_actors.py

Upgrade to latest GPT4All. Use Mistral as default offline chat model

2023-10-22 19:04:23 -07:00

test_gpt4all_chat_director.py

Enable passing search query filters via chat and test it

2023-08-28 09:24:32 -07:00

test_helpers.py

Use Black to format Khoj server code and tests

2023-02-17 11:55:17 -06:00

test_image_search.py

Update Tests to setup both content_index, search_models before testing

2023-07-14 01:29:48 -07:00

test_jsonl_to_jsonl.py

Prepend entry heading to all compiled org snippets to improve search context

2023-05-03 22:50:31 +08:00

test_markdown_to_jsonl.py

Move to a push-first model for retrieving embeddings from local files (#457)

2023-08-31 12:55:17 -07:00

test_openai_chat_actors.py

Add support for our first Local LLM 🤖🏠 (#330)

2023-07-26 16:27:08 -07:00

test_openai_chat_director.py

Enable passing search query filters via chat and test it

2023-08-28 09:24:32 -07:00

test_org_to_jsonl.py

Move to a push-first model for retrieving embeddings from local files (#457)

2023-08-31 12:55:17 -07:00

test_orgnode.py

Move to a push-first model for retrieving embeddings from local files (#457)

2023-08-31 12:55:17 -07:00

test_pdf_to_jsonl.py

Let fs_syncer pass PDF files directly as binary before indexing

2023-10-17 04:58:13 -07:00

test_plaintext_to_jsonl.py

Move to a push-first model for retrieving embeddings from local files (#457)

2023-08-31 12:55:17 -07:00

test_rawconfig.py

Add front-end Electron application for Khoj local file syncing (#473)

2023-09-06 12:04:18 -07:00

test_text_search.py

Only index files returned by input-filter globs in fs_syncer

2023-10-17 23:32:10 -07:00

test_word_filter.py

Add method to extract filter terms from query to all filters

2023-08-28 00:55:28 -07:00