Commit Graph

630 Commits (8f261d06db2ca91fd6094be08ad32b8a52bc57b1)

Author SHA1 Message Date
Jared Van Bortel 7e1e00f331
chat: fix issues with quickly switching between multiple chats (#2343)
* prevent load progress from getting out of sync with the current chat
* fix memory leak on exit if the LLModelStore contains a model
* do not report cancellation as a failure in console/Mixpanel
* show "waiting for model" separately from "switching context" in UI
* do not show lower "reload" button on error
* skip context switch if unload is pending
* skip unnecessary calls to LLModel::saveState

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
4 months ago
Jared Van Bortel 7f1c3d4275
chatllm: fix model loading progress showing "Reload" sometimes (#2337)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
4 months ago
AT 61cefcfd8a
Fix destruction and tear down of the embedding thread. (#2328)
* Fix destruction and tear down of the embedding thread.

Signed-off-by: Adam Treat <treat.adam@gmail.com>

* Fix order of deletion to prevent use after free.

Signed-off-by: Adam Treat <treat.adam@gmail.com>

---------

Signed-off-by: Adam Treat <treat.adam@gmail.com>
4 months ago
Jared Van Bortel 1427ef7195
chat: fix window icon on Windows (#2321)
* chat: fix window icon on Windows

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

* chat: remove redundant copy of macOS app icon

This has been redundant since PR #2180.

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

---------

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
4 months ago
Tim453 69720fedaa
Update appdata.xml (#2307) 4 months ago
Jared Van Bortel 5fb9d17c00
chatllm: use a better prompt for the generated chat name (#2322)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
4 months ago
Jared Van Bortel f26e8d0d87
chat: do not allow sending a message while the LLM is responding (#2323)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
4 months ago
Jared Van Bortel d54e644d05
ChatView: make context menus more intuitive (#2324)
* ChatView: fix deprecation warning

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

* ChatView: make context menus more intuitive

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

---------

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
4 months ago
Jared Van Bortel 26eaf598b4
chat: add release notes for v2.7.5 and bump version (#2300)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Jared Van Bortel 577ebd4826
mixpanel: report cpu_supports_avx2 on startup (#2299)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Jared Van Bortel 855fd22417
localdocs: load model before checking which model is loaded (#2284)
* localdocs: load model before checking what we loaded

Fixes "WARNING: Request to generate sync embeddings for non-local model
invalid"

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

* fix inverted assertion

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

---------

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Jared Van Bortel adaecb7a72
mixpanel: improved GPU device statistics (plus GPU sort order fix) (#2297)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Jared Van Bortel 27c561aeb7
mixpanel: fix opt-out events after #2238 (#2296)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Jared Van Bortel 6f38fde80b
mixpanel: fix doc_collections_total of localdocs_startup (#2270)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Jared Van Bortel a14193623a
chat: add release notes for v2.7.4 and bump version (#2269)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Jared Van Bortel 4f3c9bbe3e
network: fix use of GNU asm statement with MSVC (#2267)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Jared Van Bortel c622921894
improve mixpanel usage statistics (#2238)
Other changes:
- Always display first start dialog if privacy options are unset (e.g. if the user closed GPT4All without selecting them)
- LocalDocs scanQueue is now always deferred
- Fix a potential crash in magic_match
- LocalDocs indexing is now started after the first start dialog is dismissed so usage stats are included

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Jared Van Bortel 4193533154
models.json: add Phi-3 Mini Instruct (#2252)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Jared Van Bortel 0b78b79b1c
models.json: add Llama 3 Instruct 8B (#2242)
Other changes:
* fix 'requires' for models with %2 in template
* move Ghost 7B to the appropriate location in the file based on where it actually appears in the UI

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Jared Van Bortel aac00d019a
chat: temporarily revert some UI changes before next release (#2234)
* chat: revert PR #2187

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

* chat: revert PR #2148

This reverts commit f571e7e450.

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

---------

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Jared Van Bortel 271d752701
localdocs: small but important fixes to local docs (#2236)
* chat: use .rmodel extension for Nomic Embed

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

* database: fix order of SQL arguments in updateDocument

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

---------

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Jared Van Bortel be93ee75de
responsetext : fix markdown code block trimming (#2232)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Jared Van Bortel 38cc778a0c
models.json: use simpler system prompt for Mistral OpenOrca (#2220)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Adam Treat 94a9943782 Change the behavior of show references setting for localdocs.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
5 months ago
Adam Treat e27653219b Fix bugs with the context link text for localdocs to make the context links
persistently work across application loads and fix scrolling bug with context
links.

Signed-off-by: Adam Treat <treat.adam@gmail.com>
5 months ago
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>
5 months ago
Adam Treat 790320e170 Use consistent names for LocalDocs
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Adam Treat aad502f336 Rename these to views.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Adam Treat 77d5adfb02 Changes to the UI and icons.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
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>
6 months ago
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>
6 months ago
Robin Verduijn 4852d39699 Fix to set proper app icon on MacOS.
Signed-off-by: Robin Verduijn <robinverduijn.github@gmail.com>
6 months ago
Adam Treat b4bcc5b37c Fix colors for server chat in all themes.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Adam Treat f571e7e450 Preliminary redesign of the UI. This has no major regression.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Lam Hieu 271e6a529c Rename the model for more clarity
Signed-off-by: Lam Hieu <lamhieu.vk@gmail.com>
6 months ago
Lam Hieu 5732928b93 Change download url
Signed-off-by: Lam Hieu <lamhieu.vk@gmail.com>
6 months ago
Lam Hieu 6a22b81f44 Update Ghost 7B v0.9.1 configuration
Signed-off-by: Lam Hieu <lamhieu.vk@gmail.com>
6 months ago
Lam Hieu f50bf856b3 Fix invalid model configuration
Signed-off-by: Lam Hieu <lamhieu.vk@gmail.com>
6 months ago
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>
6 months ago
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>
6 months ago
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>
6 months ago
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>
6 months ago
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>
6 months ago
Adam Treat 97de30edd1 Fix bug with removing old .txt chatgpt files in favor of .rmodel
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
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>
6 months ago
Jared Van Bortel 406e88b59a
implement local Nomic Embed via llama.cpp (#2086)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
6 months ago
Adam Treat 171f4e488e Restrict the chat view text width to a reasonable maximum.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Adam Treat 6adaa672b4 Default to expanded state.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Adam Treat b68ebb7c15 Rework the left chat panel to be persistently open.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Xu Zhen 0072860d24 Fix compatibility with Qt 6.4
Signed-off-by: Xu Zhen <xuzhen@users.noreply.github.com>
6 months ago
Adam Treat ef9717dbe9 Use translation function for newly introduced strings.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Kryotek afbb30a523 Add context menus to the prompt and the responses
Signed-off-by: Kryotek <gcda@outlook.it>
6 months ago
Adam Treat 11db71e0a7 Bump version and release notes for v2.7.3
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Adam Treat 5ed9aea410 Don't clear installed models.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Adam Treat e2f64f89c9 When the current chat has no model use the first index.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Adam Treat 0daf37ab8a Fixes issue #2105 by using the original url for the download. This fix is
valid because we expect the url to contain the actual filename at the end.
This also allows huggingface to track the download as happening.

Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Adam Treat a6a3e0048a Don't erase the settings, but ignore them.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Adam Treat f36a2874eb Clean up settings properly for removed models and also when user manually deletes.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
chrisbarrera 61d6765361 #2024 Update ModelSettings.qml to default model/char settings combobox to the currently selected chat model
Signed-off-by: chrisbarrera <34655880+chrisbarrera@users.noreply.github.com>
6 months ago
Adam Treat 59f99b7f21 Minor fixes to server port feature.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Daniel Alencar fe653d1489 feat: added api server port setting 6 months ago
Jared Van Bortel 5c248dbec9
models: new MPT model file without duplicated token_embd.weight (#2006)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Adam Treat 6ed3d01f17 Fix issue #2087 where cloned models were lost and listed in download dialog erroneously.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat 6c3903a303 Fixes issue #2092. Don't include disabled from GUI models in application
default model list.

Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat 8ee68d1b6f Increase indent for readability.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat 4251b7beaa Fix issue #2077 part 2. Only sort when actually necessary.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat fc169e739a Add trailing commas for things that need to be added in the future.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat 028a8db6ba No need to use equals here.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat 26cedb83b0 Use initializer lists instead of append where applicable.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat 9c755d25c4 Get rid of unnecessary qMakePair
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat 099459c8b9 Update batch patch following review.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
AT 8474d76fec Update gpt4all-chat/download.cpp
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
Signed-off-by: AT <manyoso@users.noreply.github.com>
7 months ago
Adam Treat 08b5dc8598 Batch all operations for updateData to avoid excessive sort.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat 17dee02287 Fix for issue #2080 where the GUI appears to hang when a chat with a large
model is deleted. There is no reason to save the context for a chat that
is being deleted.

Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Jared Van Bortel 44717682a7
chat: implement display of model loading warnings (#2034)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Jared Van Bortel a0bd96f75d
chat: join ChatLLM threads without calling destructors (#2043)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Jared Van Bortel 5a874be7c1
modellist: rename "deprecated" to "removedIn", disable if equal (#2063)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Jared Van Bortel 402f515a5d
chat: fix ChatGPT after #1970 (#2051)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Jared Van Bortel 2a91ffd73f chatllm: fix undefined behavior in resetContext
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Jared Van Bortel 0fc071d228 chat: better handle case where network reachability is unknown
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Adam Treat be6d3bf9dc Bump version and release notes for 2.7.2
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat 83c76be68a Model discovery.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
ThiloteE f2b4809b72
models3: remove system prompt of Nous-Hermes-2-Mistral-7b-DPO (#2054)
Signed-off-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>
Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
7 months ago
Jared Van Bortel 9fafca5c94 qml: update models.json URL in error message
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Adam Treat 7d1e30766f Fix the hash on the new model.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat 5ddcf61ae4 Shorten the description and provide a valid url.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
ThiloteE 713afb7070 Add-Nous-Hermes-2-Mistral-7B-DPO.Q4_0.gguf
Adds Nous-Hermes-2-Mistral-7B-DPO.Q4_0.gguf, which is the new 7b flagship model of NousResearch.

**Original Model location:**

https://huggingface.co/NousResearch/Nous-Hermes-2-Mistral-7B-DPO-GGUF

**Model description:**

Nous Hermes 2 on Mistral 7B DPO is the new flagship 7B Hermes! This model was DPO'd from Teknium/OpenHermes-2.5-Mistral-7B and has improved across the board on all benchmarks tested - AGIEval, BigBench Reasoning, GPT4All, and TruthfulQA.

The model prior to DPO was trained on 1,000,000 instructions/chats of GPT-4 quality or better, primarily synthetic data as well as other high quality datasets, available from the repository teknium/OpenHermes-2.5.

**Original Dataset Location:**

https://huggingface.co/datasets/teknium/OpenHermes-2.5

**Dataset description:**

This is the dataset that made OpenHermes 2.5 and Nous Hermes 2 series of models.

The Open Hermes 2/2.5 and Nous Hermes 2 models have made significant advancements of SOTA LLM's over recent months, and are underpinned by this exact compilation and curation of many open source datasets and custom created synthetic datasets.

The Open Hermes 2.5 dataset is a continuation of the Open Hermes 1 dataset, at a much larger scale, much more diverse, and much higher quality compilation, reaching 1M, primarily synthetically generated instruction and chat samples.



Signed-off-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>
7 months ago
Jared Van Bortel f500bcf6e5
llmodel: default to a blank line between reply and next prompt (#1996)
Also make some related adjustments to the provided Alpaca-style prompt templates
and system prompts.

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Jared Van Bortel fc1a281381
modellist: fix bad copy-paste in ModelList::clone (#2011)
s/contextLength/gpuLayers/

Fixes #2010

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
AT 7a23b23728 Update gpt4all-chat/modellist.cpp
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
Signed-off-by: AT <manyoso@users.noreply.github.com>
7 months ago
Adam Treat 17a2cdbe35 Fix crasher with layer count
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
chrisbarrera f8b1069a1c
add min_p sampling parameter (#2014)
Signed-off-by: Christopher Barrera <cb@arda.tx.rr.com>
Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
7 months ago
Adam Treat ef518fae3e Fix crash with chatgpt and gpu layers.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Jared Van Bortel c1dcb3f5b8 models.json: fix Mistral OpenOrca filename
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Adam Treat a010a8a7ca Bump version and release notes for v2.7.1
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Jared Van Bortel ef0a67eb94
models: remove gemma from models2.json and models3.json (#1995)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Adam Treat 67bbce43ab Fix state issues with reloading model.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Jared Van Bortel 4fc4d94be4
fix chat-style prompt templates (#1970)
Also use a new version of Mistral OpenOrca.

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Jared Van Bortel b8f5c74f40
add models3.json for new templates (#1993)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Jared Van Bortel c13202a6f5 models2.json: gemma requires a future GPT4All version
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Jared Van Bortel 4a8c6d7f9c gemma: fix default prompt template
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Jared Van Bortel 32837fb3a0 models2.json: add gemma model
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Adam Treat 896fc6fbb7 Save the window size for the user and reuse next load.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat fa0a2129dc Don't try and detect model load error on startup.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat b0c471aed8 Make the reload/regenerate buttons a little bit larger font.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat 67099f80ba Add comment to make this clear.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat ad34c2bdd4 Don't erase context when reloading model by selection.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat fbf5e5e732 Increase padding for elided text in combo.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat ed0f93977d Fixes for issues identified in review.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat d948a4f2ee Complete revamp of model loading to allow for more discreet control by
the user of the models loading behavior.

Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat 16927d9a76 Fix visual artifact with close button in new version dialog.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat f569ae9b22 Bump version and release notes for v2.7.0
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Jared Van Bortel 2020c23edf
chat: set version to 2.7.0 (#1940)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
8 months ago
Adam Treat 260a56c748 Don't show the download button if we are not connected to an online network.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 months ago
Adam Treat 4258bb1f8a Fix issue 1918 for accessibility of screen readers.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 months ago
Adam Treat 490404dbb2 Fix issue 1925, scrollbar missing on main conversation.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 months ago
Jared Van Bortel 513a214eca database: limit supported extensions to txt, pdf, md, rst
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
8 months ago
Jared Van Bortel 78a26cc5e4
models2.json: use ChatML for Mistral OpenOrca (#1935)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
8 months ago
Adam Treat 1b524c4617 Reverse patch so we can minimize down to lowest HD form factor.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 months ago
Adam Treat cb10465127 Make the collection dialog progress bar more readable.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 months ago
Adam Treat 4461af35c7 Fix includes.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 months ago
Jared Van Bortel 10e3f7bbf5
Fix VRAM leak when model loading fails (#1901)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
8 months ago
Adam Treat e1eac00ee0 Fix the download and settings dialog to take more real estate if available on large monitors.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 months ago
Adam Treat 111e152a5d Fix the sizing for model download.
Signed-off-by: Adam Treat <adam@nomic.ai>
8 months ago
Adam Treat ffed2ff823 Fix for progress bar color on legacy theme.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 months ago
Adam Treat a5275ea9e7 Bump the version and release notes for v2.6.2.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 months ago
Adam Treat cdf0fedae2 Make sure to use the search_query tag for nomic embed.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 months ago
Adam Treat d14b95f4bd Add Nomic Embed model for atlas with localdocs. 8 months ago
Jared Van Bortel 0a40e71652
Maxwell/Pascal GPU support and crash fix (#1895)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
8 months ago
Jared Van Bortel 061d1969f8
expose n_gpu_layers parameter of llama.cpp (#1890)
Also dynamically limit the GPU layers and context length fields to the maximum supported by the model.

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
8 months ago
Jared Van Bortel 29d2c936d1
chat: don't show "retrieving localdocs" for zero collections (#1874)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
8 months ago
Adam Treat cfa22ab1c4 Change to a color that exists.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 months ago
Adam Treat 3556f63a29 Make the setting labels font a bit bigger and fix hover.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 months ago
Adam Treat 34de19ebf6 Add a legacy dark mode.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 months ago
Adam Treat c1fce502f7 Fix checkbox background in dark mode.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 months ago
Adam Treat 363f6659e4 Fix the settings font size to be a tad bigger.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 months ago
Adam Treat 6abeefb303 Hover for links and increase font size a bit.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 months ago
Adam Treat 697a5f5d2a New lightmode and darkmode themes with UI revamp.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 months ago
Karthik Nair 0a45dd384e
add fedora command for QT and related packages (#1871)
Signed-off-by: Karthik Nair <realkarthiknair@gmail.com>
Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
8 months ago
Adam Treat 27912f6e1a Fix bug with install of online models. 8 months ago
Jared Van Bortel c7ea283f1f
chatllm: fix deserialization version mismatch (#1859)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
8 months ago
Jared Van Bortel b98e5f396a
docs: add missing dependencies to Linux build instructions (#1728)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
8 months ago
Adam Treat e51a504550 Add the new 2.6.1 release notes and bump the version. 8 months ago
Jared Van Bortel b803d51586 restore network.h #include
The online installers need this.
8 months ago
Jared Van Bortel 7e9786fccf chat: set search path early
This fixes the issues with installed versions of v2.6.0.
8 months ago
Adam Treat f7aeeca884 Revert the release. 8 months ago
Adam Treat 16a84972f6 Bump to new version and right the release notes. 8 months ago
Jared Van Bortel 4dbe2634aa models2.json: update models list for the next release 8 months ago
Adam Treat 233f0c4201 Bump the version for our next release. 9 months ago
Gerhard Stein 3e99b90c0b Some cleanps 9 months ago