Commit Graph

1765 Commits

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