AI/gpt4all
1
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2024-10-01 01:06:10 -04:00
Code Issues Packages Projects Releases Wiki Activity
1,815 Commits 491 Branches 56 Tags 46 MiB
8ba7ef4832
Commit Graph

1815 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Jared Van Bortel
ac498f79ac
fix regressions in system prompt handling (#2219) 
* python: fix system prompt being ignored
* fix unintended whitespace after system prompt

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-04-15 11:39:48 -04:00
dependabot[bot]
2273cf145e build(deps): bump tar in /gpt4all-bindings/typescript 
Bumps [tar](https://github.com/isaacs/node-tar) from 6.2.0 to 6.2.1.
- [Release notes](https://github.com/isaacs/node-tar/releases)
- [Changelog](https://github.com/isaacs/node-tar/blob/main/CHANGELOG.md)
- [Commits](https://github.com/isaacs/node-tar/compare/v6.2.0...v6.2.1)

---
updated-dependencies:
- dependency-name: tar
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
 2024-04-15 08:37:39 -05:00
Jared Van Bortel
3f8257c563
llamamodel: fix semantic typo in nomic client dynamic mode (#2216) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-04-12 17:25:15 -04:00
Jared Van Bortel
46818e466e
python: embedding cancel callback for nomic client dynamic mode (#2214) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-04-12 16:00:39 -04:00
Jared Van Bortel
459289b94c
embed4all: small fixes related to nomic client local embeddings (#2213) 
* actually submit larger batches with increased n_ctx
* fix crash when llama_tokenize returns no tokens

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-04-12 10:54:15 -04:00
Andriy Mulyar
1e4c62027b
Update README.md (#2209) 
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
 2024-04-10 16:27:46 -04:00
Jared Van Bortel
1b84a48c47
python: add list_gpus to the GPT4All API (#2194) 
Other changes:
* fix memory leak in llmodel_available_gpu_devices
* drop model argument from llmodel_available_gpu_devices
* breaking: make GPT4All/Embed4All arguments past model_name keyword-only

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-04-04 14:52:13 -04:00
Adam Treat
790320e170 Use consistent names for LocalDocs 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-04-03 08:02:52 -05:00
Adam Treat
aad502f336 Rename these to views. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-04-03 08:02:52 -05:00
Adam Treat
77d5adfb02 Changes to the UI and icons. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-04-03 08:02:52 -05:00
3Simplex
9c23d44ad3 Update ChatView.qml 
Directed the Documentation link specifically to the ChatUI documentation.


Co-authored-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>

Signed-off-by: 3Simplex <10260755+3Simplex@users.noreply.github.com>
 2024-04-01 08:34:49 -05:00
3Simplex
4f6c43aec9 Update ChatView.qml 
Include links for Documentation and FAQ for new users on the "new chat view".


Co-authored-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>

Signed-off-by: 3Simplex <10260755+3Simplex@users.noreply.github.com>
 2024-04-01 08:34:49 -05:00
Robin Verduijn
4852d39699 Fix to set proper app icon on MacOS. 
Signed-off-by: Robin Verduijn <robinverduijn.github@gmail.com>
 2024-04-01 08:34:02 -05:00
Jared Van Bortel
3313c7de0d
python: implement close() and context manager interface (#2177) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-28 16:48:07 -04:00
dependabot[bot]
dddaf49428
typescript: bump ip dep from 2.0.0 to 2.0.1 (#2175) 
Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-28 12:58:03 -04:00
Jacob Nguyen
55f3b056b7
typescript!: chatSessions, fixes, tokenStreams (#2045) 
Signed-off-by: jacob <jacoobes@sern.dev>
Signed-off-by: limez <limez@protonmail.com>
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Co-authored-by: limez <limez@protonmail.com>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-28 12:08:23 -04:00
Jared Van Bortel
6c8a44f6c4
ci: use aws s3 sync to upload docs (#2172) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-27 11:03:10 -04:00
Jared Van Bortel
b743c588e8
python: bump version to 2.3.2 to include *all* of the bugfixes (#2171) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-26 15:26:08 -04:00
Jared Van Bortel
67843edc7c
backend: update llama.cpp submodule for wpm locale fix (#2163) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-26 11:04:22 -04:00
Jared Van Bortel
83ada4ca89
backend: update llama.cpp submodule for Unicode paths fix (#2162) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-26 11:01:02 -04:00
Jared Van Bortel
8d09b2c264 python: bump version 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-25 22:16:50 -07:00
Jared Van Bortel
446668674e python: use TypedDict from typing_extensions on python 3.9 and 3.10 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-25 22:16:50 -07:00
Jared Van Bortel
adea3811ea docs: fix mention of Q6_K quantization in README 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-25 11:03:18 -05:00
Jared Van Bortel
71db8bdc80
python: also delete partial file on KeyboardInterrupt/SystemExit (#2154) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-21 12:59:35 -04:00
Jared Van Bortel
71d7f34d1a
python: improve handling of incomplete downloads (#2152) 
* make sure encoding is identity for Range requests
* use a .part file for partial downloads
* verify using file size and MD5 from models3.json

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-21 11:33:41 -04:00
Adam Treat
b4bcc5b37c Fix colors for server chat in all themes. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-20 15:10:26 -05:00
Adam Treat
f571e7e450 Preliminary redesign of the UI. This has no major regression. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-20 11:45:26 -05:00
Jared Van Bortel
0455b80b7f
Embed4All: optionally count tokens, misc fixes (#2145) 
Key changes:
* python: optionally return token count in Embed4All.embed
* python and docs: models2.json -> models3.json
* Embed4All: require explicit prefix for unknown models
* llamamodel: fix shouldAddBOS for Bert and Nomic Bert

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-20 11:24:02 -04:00
Lam Hieu
271e6a529c Rename the model for more clarity 
Signed-off-by: Lam Hieu <lamhieu.vk@gmail.com>
 2024-03-20 10:16:25 -05:00
Lam Hieu
5732928b93 Change download url 
Signed-off-by: Lam Hieu <lamhieu.vk@gmail.com>
 2024-03-20 10:16:25 -05:00
Lam Hieu
6a22b81f44 Update Ghost 7B v0.9.1 configuration 
Signed-off-by: Lam Hieu <lamhieu.vk@gmail.com>
 2024-03-20 10:16:25 -05:00
Lam Hieu
f50bf856b3 Fix invalid model configuration 
Signed-off-by: Lam Hieu <lamhieu.vk@gmail.com>
 2024-03-20 10:16:25 -05:00
Lam Hieu
df79e45195 Support Ghost 7B v0.9.1, fast, powerful and smooth for Vietnamese and English languages. 
Signed-off-by: Lam Hieu <lamhieu.vk@gmail.com>
 2024-03-20 10:16:25 -05:00
Jacob Nguyen
0e9e5237c5
ci: fix build-ts-docs with npm install --ignore-scripts (#2143) 
Signed-off-by: Jacob Nguyen <76754747+jacoobes@users.noreply.github.com>
 2024-03-19 17:28:14 -04:00
Jared Van Bortel
a1bb6084ed
python: documentation update and typing improvements (#2129) 
Key changes:
* revert "python: tweak constructor docstrings"
* docs: update python GPT4All and Embed4All documentation
* breaking: require keyword args to GPT4All.generate

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-19 17:25:22 -04:00
Jared Van Bortel
f30151491d Revert "ci: fix failing build-ts-docs workflow (#2142)" 
According to jacoobes, --ignore-scripts was removed in yarn v2.

This reverts commit c6bd8577a9.

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-19 12:28:43 -04:00
Jacob Nguyen
c6bd8577a9
ci: fix failing build-ts-docs workflow (#2142) 
Signed-off-by: Jacob Nguyen <76754747+jacoobes@users.noreply.github.com>
 2024-03-19 12:20:53 -04:00
Jared Van Bortel
699410014a
fix non-AVX CPU detection (#2141) 
* chat: fix non-AVX CPU detection on Windows
* bindings: throw exception instead of logging to console

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-19 10:56:14 -04:00
Tim453
6c2542e540 Allow changing the install path 
This commit allow changing the install path during CMake configure step using the CMAKE_INSTALL_PREFIX variable. If the variable is not set, it still defaults to {CMAKE_BINARY_DIR}/install.

Signed-off-by: Tim453 <50015765+Tim453@users.noreply.github.com>
 2024-03-18 11:57:56 -05:00
jbl
2bb86f35ee Update README.md 
Add Phorm AI Badge

Signed-off-by: jbl <141294048+bentleylong@users.noreply.github.com>
 2024-03-18 08:34:18 -05:00
Jared Van Bortel
255568fb9a
python: various fixes for GPT4All and Embed4All (#2130) 
Key changes:
* honor empty system prompt argument
* current_chat_session is now read-only and defaults to None
* deprecate fallback prompt template for unknown models
* fix mistakes from #2086

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-15 11:49:58 -04:00
Jared Van Bortel
53f109f519
llamamodel: fix macOS build (#2125) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-14 12:06:07 -04:00
Adam Treat
667f29c2a1 Split the main.qml into two pieces to support multiple views in future. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-14 09:42:23 -05:00
Adam Treat
97de30edd1 Fix bug with removing old .txt chatgpt files in favor of .rmodel 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-13 17:37:18 -05:00
Olyxz16
2c0a660e6e
feat: Add support for Mistral API models (#2053) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Signed-off-by: Cédric Sazos <cedric.sazos@tutanota.com>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-13 18:23:57 -04:00
Jared Van Bortel
406e88b59a
implement local Nomic Embed via llama.cpp (#2086) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-13 18:09:24 -04:00
Adam Treat
171f4e488e Restrict the chat view text width to a reasonable maximum. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-13 17:01:19 -05:00
Adam Treat
6adaa672b4 Default to expanded state. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-13 14:23:04 -05:00
Adam Treat
b68ebb7c15 Rework the left chat panel to be persistently open. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-13 14:23:04 -05:00
Xu Zhen
0072860d24 Fix compatibility with Qt 6.4 
Signed-off-by: Xu Zhen <xuzhen@users.noreply.github.com>
 2024-03-12 07:42:22 -05:00